KR101670956B1 - User interface for presenting search results for multiple regions of a visual query - Google Patents

Abstract

Visual queries such as photographs, screen shots, scanned images or video frames are submitted to a visual query retrieval system from a client system. A search system processes a visual query by sending a visual query to a plurality of parallel search systems each implementing a separate visual query search process. A plurality of results are received from the parallel search systems. Using the search results, an interaction result document is generated and sent to the client system. The interaction result document has at least one visual identifier for the sub-portion of the visual query having a selectable link to at least one search result for the sub-portion. The visual identifier may be a bounding box around each sub-portion or may be a semi-transparent label across each sub-portion. Optionally, the bounding box or label is a color coded by the type of result.

Description

USER INTERFACE FOR PRESENTING SEARCH RESULTS FOR MULTIPLE REGIONS OF A VISUAL QUERY < RTI ID = 0.0 >

The disclosed embodiments generally relate to presenting search results by a plurality of parallel search systems for processing visual queries.

Text-based or term-based searches where users enter words or phrases into search engines and receive various results are useful tools for searching. However, term based queries require the user to be able to enter related terms. From time to time, the user may want to know information about the image. For example, the user may want to know the name of the person in the picture, or the user may want to know the name of the flower or bird in the picture. Thus, a system that can receive visual queries and provide search results may be desirable.

In accordance with certain embodiments, a computer-implemented method of processing a visual query includes the steps of: generating a visual query in a server system comprising a memory storing one or more programs for execution by one or more processors and one or more processors, Lt; / RTI > A visual query is received from the client system. A visual query is processed by sending a visual query to a plurality of parallel search systems for concurrent processing. Each of the plurality of search systems implements a separate visual query retrieval process among a plurality of visual query retrieval processes. Thereafter, the server system receives a plurality of search results from one or more of the plurality of parallel search systems. The server system generates an interaction result document that includes one or more visual identifiers of each of the sub-portions of the visual query. Each time identifier has at least one user selectable link to at least one of the search results. Finally, the server system sends the interaction result document to the client system. In certain embodiments, the search results include data associated with corresponding sub-portions of the visual query.

In certain embodiments, the transmitting step further comprises transmitting a subset of the plurality of search results in a search result list for display in an interaction result document. Optionally, the method further comprises: receiving a user selection of at least one user selectable link; And identifying the search result in a list of search results corresponding to the selected link.

In certain embodiments, the visual identifiers include one or more bounding boxes around each sub-portion of the visual query. The bounding boxes may be square or may represent the outline of each sub-portion of the visual query. Optionally, some bounding boxes include smaller bounding boxes within them.

In certain embodiments, each of the bounding boxes includes a user selectable link to one or more search results, and the user selectable link has an active area corresponding to a sub-portion of the visual query enclosed by the bounding box . In embodiments where the visual identifiers are not bounding boxes, each user selectable link has an active area corresponding to the sub-part of the visual query associated with the corresponding visual identifier.

In certain embodiments, when the selectable sub-portion comprises text, the method further comprises transmitting the selectable sub-portion of text to a text-based query processing system. In other embodiments, when the sub-portion of the visual query corresponds to a respective visual identifier comprising text, the search results corresponding to each visual identifier may be associated with at least one of the terms in the text, Results.

In certain embodiments, when the sub-portion of the visual query corresponding to each visual identifier includes a person's face, the search results corresponding to each visual identifier may include a name, handle, contact information, account information, address The current location of the associated mobile device associated with the person having the face included in the selectable sub-portion, other images of the person having the face included in the selectable sub-portion, and / or potential image matching .

In some embodiments, when the sub-portion of the visual query corresponding to each visual identifier includes an object, the search results corresponding to each visual identifier may include object information, an object review, an option to initiate the purchase of the object An option to initiate a bid on the item, a list of similar items, and / or a list of related items.

In certain embodiments, the respective visual identifiers of the one or more visual identifiers are formatted for display in a visually distinct manner depending on the type of entity recognized in each sub-portion of the visual query. Each visual identifier is formatted for visually distinct displays such as overlay color, overlay pattern, label background color, label background pattern, label font color, and border color.

In certain embodiments, the time identifier of each of the one or more visual identifiers comprises a label consisting of at least one term associated with the image in each sub-portion of the visual query. The label is formatted for display in an interactive result document on or near each sub-portion.

1 is a block diagram illustrating a computer network including a visual query server system.
2 is a flow diagram illustrating a process for responding to a visual query, in accordance with certain embodiments.
3 is a flow diagram illustrating a process for responding to a visual query using an interaction result document, in accordance with certain embodiments.
4 is a flow diagram illustrating communications between a client and a visual query server system, in accordance with certain embodiments.
5 is a block diagram illustrating a client system, in accordance with certain embodiments.
6 is a block diagram illustrating a front end visual query processing server system, in accordance with certain embodiments.
7 is a block diagram illustrating a generic system of parallel search systems used to process visual queries, in accordance with certain embodiments.
8 is a block diagram illustrating an OCR retrieval system used to process a visual query, in accordance with certain embodiments.
9 is a block diagram illustrating a face recognition retrieval system utilized to process a visual query, in accordance with certain embodiments.
10 is a block diagram illustrating an image-to-terms search system used to process a visual query, in accordance with certain embodiments.
Figure 11 illustrates a client system with screen shots of an exemplary visual query, in accordance with certain embodiments.
Figures 12A and 12B each illustrate a client system with screen shots of an interaction result document with bounding boxes, in accordance with certain embodiments.
Figure 13 illustrates a client system with screen shots of interaction result documents coded by type, in accordance with certain embodiments.
Figure 14 illustrates a client system with screen shots of an interaction result document with labels, in accordance with certain embodiments.
Figure 15 shows a screenshot of an interaction result document and a visual query displayed simultaneously with a result list, in accordance with certain embodiments.
Like reference numerals refer to corresponding parts throughout the figures.

Reference will now be made in detail to the embodiments described in the accompanying drawings. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced without these specific details. In other instances, well-known methods, procedures, components, circuits, and networks have not been described in detail in order not to unnecessarily obscure aspects of the embodiments.

It is also to be understood that although the terms first, second, etc. may exist in this specification to describe various elements, such elements should not be limited by these terms. These terms are only used to distinguish one element from another. Without departing from the scope of the present invention, for example, the first contact may be referred to as a second contact, and similarly, the second contact may be referred to as a first contact. The first contact and the second contact are both contacts, but are not the same contact.

It is to be understood that the terminology used herein should not be construed as limiting the scope of the present invention. As used in the description of the present invention and the appended claims, the singular forms are intended to include the plural forms as well, unless the context clearly indicates otherwise. It is also to be understood that the term "and / or" as used herein refers to and includes any and all possible combinations of one or more of the associated listed items. It should also be understood that the terms " comprises and / or comprising "when used in this specification will identify the stated features, integers, steps, operations, elements, and / But does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

The term " if, " as used herein, means either "when" or "upon" or "in response to a determination" or "in response to detection" . ≪ / RTI > Similarly, the phrases "when determined" or " when detected "refer to a condition or event (referred to as "Quot; in response to detection ").

1 is a block diagram illustrating a computer network including a visual query server system according to certain embodiments. The computer network 100 includes one or more client systems 102 and a visual query server system 106. One or more communication networks 104 interconnect these components. Communications network 104 may be any of a variety of networks, including local area networks (LANs), wide area networks (WAN), wireless networks, wired networks, the Internet, or a combination of such networks.

Client system 102 includes a client application 108 that is executed by a client system to receive a visual query (e.g., visual query 1102 of FIG. 11). A visual query is an image submitted as a query to a search engine or a search system. Examples of non-limiting visual queries include photographs, scanned documents and images and pictures. In certain embodiments, the client application 108 is selected from a set consisting of a search application, a search engine plug-in for the browser application, and a search engine extension for the browser application. In some embodiments, the client application 108 is an " omnivorous "search box, which allows the user to drag and drop images of any format to be used as a visual query into the search box.

The client system 102 sends queries to the visual query server system 106 and receives data from the visual query server system 106. The client system 102 may be any computer or other device capable of communicating with the visual query server system 106. Non-limiting examples include desktop and notebook computers, mainframe computers, server computers, mobile devices such as mobile phones and personal digital assistants, network terminals and set-top boxes.

The visual query server system 106 includes a front end visual query processing server 110. The front end server 110 receives the visual query from the client 102 and sends the visual query to the plurality of parallel search systems 112 for concurrent processing. Each of the search systems 112 implements a separate visual query search process and accesses their corresponding databases 114 as needed to process the visual query by their own separate search process. For example, the face recognition search system 112-A will access the face image database 114-A to find face matches for the image query. As described in more detail with respect to FIG. 9, when the visual query includes a face, the face recognition search system 112-A receives one or more search results (e.g., Names, matching faces, etc.). In another example, an optical character recognition (OCR) search system 112-B converts any recognizable text in the visual query into text for return as one or more search results. In optical character recognition (OCR) retrieval system 112-B, OCR database 114-B may be accessed to recognize certain fonts or text patterns that are described in more detail with respect to FIG.

Any number of parallel search systems 112 may be used. Some embodiments include a face recognition system 112-A, an OCR system 112-B, an image-to-term search system 112-C (which may recognize an object or an object category) (Which may be configured to recognize 2-D images such as book covers and CDs and may also be configured to recognize 3-D images such as furniture), a bar code recognition search system (1D and 2D style (E.g., recognizing bar codes), a naming entity recognition search system, landmark recognition (such as the Eiffel Tower, and is also configured to recognize corpus of distinct images such as billboards Location awareness, color-aware search systems, and similar images that are assisted by geo-location information provided by the client system 102 or the GPS receiver of the mobile telephone network It includes a color system (also search for similar images in time query and identification). Additional search systems may be added as additional parallel search systems, as shown in FIG. 1, by system 112-N. All search systems, except the OCR search system, are collectively defined herein as search systems that perform an image-matching process. All search systems, including OCR search systems, are collectively referred to as image query query systems. In certain embodiments, the visual query server system 106 includes a face recognition search system 112-A, an OCR search system 112-B, and a query search system 112 by at least one other image do.

Each of the parallel search systems 112 processes the visual search queries individually and returns their results to the front end server system 110. In some embodiments, the front-end server 100 may be configured to merge the results into a compound document, to select a subset of the results to display, and to rank the results as described in more detail with respect to FIG. ≪ / RTI > one or more of the search results. The front-end server 110 communicates search results to the client system 102.

The client system 102 presents one or more search results to the user. The results can be presented on a display, by an audio speaker, or by any other means used to communicate information to a user. The user can interact with the search results in a variety of ways. In some embodiments, the user's selections, annotations, and other interactions with the search results are sent to the visual query server system 106 and recorded in the query and annotation database 116 along with the visual query. The information in the query and annotation databases can be used to improve visual query results. In some embodiments, the information from the query and annotation database 116 is periodically pushed to the parallel search systems 112, and any relevant portions of information may be communicated to each of the individual databases < RTI ID = 0.0 > 0.0 > 114 < / RTI >

The computer network 100 optionally includes a term query server system 118 for performing searches in response to term queries. A term query is a query that includes one or more terms, as opposed to a visual query that includes an image. Term query server system 118 may be used to generate search results supplementing information produced by various search engines in visual query server system 106. Results returned from term query server system 118 may include any format. Term query server system 118 may include text documents, images, video, and the like. Optionally, the visual query server system 106 may include a term query server system 118, although the term query server system 118 is shown as a separate system in FIG.

Additional information regarding the operation of the visual query server system 106 is provided below with respect to the flowcharts in Figures 2-4.

2 is a flow diagram illustrating a visual query server system method for responding to a visual query, in accordance with certain embodiments of the present invention. Each of the operations illustrated in FIG. 2 may correspond to instructions stored in a computer memory or a computer-readable storage medium.

The visual query server system receives the visual query from the client system (202). For example, the client system may be a desktop computer device, a mobile device, or other similar device as described with reference to FIG. An exemplary visual query in an exemplary client system is shown in FIG.

The visual query is an image document of any suitable format. For example, the visual query may be a photograph, a screen shot, a scanned image, or a sequence of multiple frames of a frame or video (206). In certain embodiments, the visual query is a picture produced by the content authoring program 736 (FIG. 5). Thus, in certain embodiments, the user "draws " a visual query while in other embodiments, the user scans or photographs the visual query. Any visual queries are generated using an image generation application such as Acrobat, a photo editing program, a picture program, or an image editing program. For example, a visual query can come from a user taking a picture of his friend on his cell phone and then submitting the picture as a visual query to the server system. The visual query can also come from a user scanning a page of a magazine or taking a screenshot of a web page on a desktop computer and then submitting a scan or screenshot as a visual query to the server system. In certain embodiments, the visual query is submitted to the server system 106 via a browser application's search engine extension, through a plug-in to the browser application, or by a search application executed by the client system 102 . The visual queries may also be submitted by other application programs (executed by the client system) that support or generate images that can be transmitted to the server remotely located by the client system.

The visual query may be a combination of text and non-text elements (208). For example, the query may be a scan of a magazine page that includes images and text, such as a person standing next to a road sign. The visual query may include an image of a person's face or a document scanned or otherwise received by the client system, which is captured by a camera embedded in the client system. The visual query may also be a scan of a document containing only text. Visual queries are also an image of many distinct subjects such as birds, people and objects in the forest (e.g., cars, park benches, etc.), people and animals (e.g., pets, farm animals, . Visual queries can have two or more distinct elements. For example, the visual query may include the barcode of the article and the article name of the image or article package. For example, the visual query may be a picture of a book cover including a book title, cover art, and bar code. In any of the examples, one visual query will yield two or more distinct search results corresponding to different parts of the visual query, as discussed in more detail below.

The server system processes the following visual query. The front-end server system sends a visual query to a plurality of parallel search systems for concurrent processing (210). Each search system implements a separate visual query search process, i.e., the individual search system processes the visual query by its own processing scheme.

In certain embodiments, one of the search systems to which a visual query is sent for processing is an optical character recognition (OCR) search system. In certain embodiments, one of the search systems to which a visual query is sent for processing is a face recognition search system. In some embodiments, a plurality of search systems that execute separate visual query search processes include at least a query process by optical character recognition (OCR), face recognition, and other images besides OCR and face recognition 212 ). The query process by another image is selected 212 from a set of processes including, but not limited to, object recognition, bar code recognition, object-or-object-category recognition, naming entity recognition and color recognition.

In certain embodiments, the naming entity recognition occurs as a post process of an OCR retrieval system, the textual results of the OCR are analyzed against known people, locations, objects, etc., and then the terms identified as naming entities are termed Is retrieved from query server system 118 (FIG. 1). In other embodiments, images of famous landmarks, logos, people, album covers, brands, etc. are recognized by the image-to-term search system. In other embodiments, a query process by a separate named entity image separate from the image-to-term search system is used. The object-or-object category recognition system recognizes comprehensive result types such as "car ". In certain embodiments, the system recognizes objects brands, specific object models, and the like, and provides more detailed descriptions such as "Porsche ". Some of the search systems may be special user specific search systems. For example, certain versions of color recognition and face recognition may be special search systems used by blinds.

The front end server system receives results from the parallel search systems (214). In certain embodiments, the results are accompanied by a search score. For any visual queries, some of the search systems will not find relevant results. For example, if the visual query is a picture of a flower, the face recognition search system and the bar code search system will not find any relevant results. In certain embodiments, if no relevant results are found, a null or zero search score is received from the search system (216). In certain embodiments, if the front-end server does not receive results from the search system after a pre-defined period of time (e.g., 0.2, 0.5, 1, 2, or 5 seconds) It will process the received results as if it had yielded a null search score and will process the results received from other search systems.

Optionally, when at least two of the received search results satisfy a pre-defined criterion, they are ranked (218). In certain embodiments, one of the predefined criteria excludes invalid results. A pre-defined criterion is that the results are not invalid. In certain embodiments, one of the predefined criteria excludes results (e.g., for related factors) that have a numeric score below a pre-defined minimum score. Optionally, a plurality of search results are filtered 220. In certain embodiments, the results are filtered only if the total number of results exceeds a pre-defined threshold. In certain embodiments, all results are ranked, but results that are below a pre-defined minimum score are excluded. For any visual queries, the contents of the results are filtered. For example, if some of the results include private or personal protection information, these results are filtered out.

Optionally, the visual query server system generates a complex search result (222). One embodiment of this is when more than one search system result is embedded in the interaction result document, as described with respect to FIG. The term query server system 118 (FIG. 1) may augment results from one of the parallel search systems with results from a term search, and additional results may include links to documents or information sources, And / or additional information that may be relevant to the visual query. Thus, for example, the composite search result may include an OCR result and a link to the naming entity in the OCR document (224).

In certain embodiments, the OCR search system 112-B (FIG. 1) or the front end visual query processing server 110 (FIG. 1) recognize similar related words in the text. For example, naming entities such as famous people or places can be recognized. The naming entities are submitted as query terms to the term query server system 118 (FIG. 1). In certain embodiments, the term query results produced by the term query server system are embedded in the results of the visual query as "links ". In certain embodiments, the term query results are returned as separate links. For example, if the picture of the book cover is a visual query, then the object recognition and retrieval system is likely to yield a high score hit for the book. Thus, a term query for a title of a book may be executed in the term query server system 118, and the term query results are returned with the results of the visual query. In certain embodiments, the term query results are presented in a labeled group to distinguish themselves from the visual query results. The results may be retrieved individually, or the retrieval may be performed using all recognized naming entities in the search query, in particular to yield additional related search results. For example, if the visual query is a scanned travel brochure about Paris, the returned result may include links to the term query server system 118 to initiate a search in the term query " have. Similarly, composite search results include results from text searches on recognized well-known images. For example, in the same travel brochure, live links to the term query results for famous destinations shown as pictures in brochures such as "Eiffel Tower" and "Louvre" Top "and" Louvre "may not appear in the brochure themselves).

The visual query server system then sends (226) at least one result to the client system. Typically, if the visual query processing server receives a plurality of search results from at least some of the plurality of search systems, the visual query processing server will transmit at least one of the plurality of search results to the client system. For any visual queries, only one search system will return relevant results. For example, in a visual query involving only an image of text, only the results of the OCR server may be relevant. For any visual queries, only one result from one search system may be relevant. For example, only items related to the scanned bar code may be relevant. In these examples, the front end visual processing server will return only the relevant search result (s). For any visual queries, a plurality of search results are sent to the client system, and the plurality of search results include search results from two or more of the parallel search systems (228). This can happen when two or more distinct images are in the visual query. For example, if the visual query is a picture of a horse rider, the results of human face recognition may be displayed along with the object recognition results for the horse. In certain embodiments, all results for a particular query by the image search system are grouped together and presented. For example, the top N face recognition results are displayed under the title "Face Recognition Results" and the top N object recognition results are displayed together under the title "Object Recognition Results ". Alternatively, as discussed below, the search results from a particular image search system may be grouped by image region. For example, if the visual query includes two faces, both faces will produce face recognition results, and the results for each face can be presented as a separate group. For any visual queries (e.g., a visual query that includes an image of text and one or more objects), the search results may include both OCR results and one or more image-matching results 230 ).

In certain embodiments, a user may want to be more aware of a particular search result. For example, if the visual query is a picture of a dolphin and the "image vs. terms" retrieval system returns the following terms "water", "dolphin", "blue" and "web" You may want to perform a text-based query term search. Query term server system 118 (FIG. 1) is accessed when a user wants to perform a search on a term query (e.g., by a user clicking on a corresponding link in search results or otherwise selecting) , The search is performed on the selected term (s). Corresponding search term results are displayed (232) on the client system with or without visual query results. In some embodiments, the front end visual query processing server 110 (Figure 1) automatically selects one or more higher potential results for the visual query (i.e., without receiving any user commands other than the initial visual query) (232) these query results along with the visual query results as part of executing these textual results on the term query server system 118 and then sending at least one search result to the client system. In the above example, if the "webbing" is the first term result for the dolphin's visual quality picture, the front end server executes the term query on the "webs" and returns these term query results along with the visual query results to the client system do. This embodiment, in which the term result considered to be selected by the user is automatically executed before sending the search results to the user from the visual query saves user time. In certain embodiments, these results are displayed 222 as a composite search result as described above. In other embodiments, the results are part of a search result list in addition to or in addition to the compound search results.

3 is a flow chart illustrating a process for responding to a visual query using an interaction result document. The first three operations 202, 210, 214 are described above with reference to FIG. From the search results received from the parallel search systems 214, an interaction result document is generated 302.

The creation (302) of the interaction result document will now be described in detail. For any visual queries, the interaction result document includes one or more visual identifiers of each of the sub-portions of the visual query. Each time identifier has at least one user selectable link to at least one of the search results. The time identifier identifies each sub-portion of the visual query. For any visual queries, the interaction result document has only one visual identifier with one user selectable link to one or more results. In certain embodiments, each user selectable link for one or more of the search results has an active area, and the active area corresponds to a sub-part of the visual query associated with the corresponding time identifier.

In certain embodiments, the visual identifier is a bounding box 304. [ In certain embodiments, the bounding box surrounds the sub-portion of the visual query as shown in FIG. 12A. The bounding box does not need to be a square or rectangular box shape and may be circular, elliptical, conformal, irregular, or as shown in Fig. 12 (e.g., for objects of visual query, But may be any other shape. For any visual queries, the bounding box represents the outline of the boundary of the entity that is identifiable in the sub-portion of the visual query (306). In certain embodiments, each bounding box includes a user selectable link to one or more search results, and the user selectable link includes an active area corresponding to a sub-portion of the visual query that is rounded by the bounding box I have. When the space in the bounding box is selected by the user (the active area of the user selectable link), the search results corresponding to the image in the outlined sub-part are returned.

In certain embodiments, the visual identifier is a label as shown in FIG. 14 (307). In certain embodiments, the label includes at least one term associated with the image in each sub-portion of the visual query. Each label is formatted for display as an interactive result document at or around each sub-portion. In certain embodiments, the labels are color coded.

In certain embodiments, each individual visual identifier is formatted for display in a visually distinct manner depending on the type of entity recognized in each sub-portion of the visual query. For example, as shown in FIG. 13, the objects, the person, the trademark, and the bounding boxes around the two text areas are represented by separate cross-hatching patterns, each representing differently colored transparent bounding boxes . In certain embodiments, the visual identifiers are formatted for display in visually distinct ways such as overlay color, overlay pattern, label background color, label background pattern, label font color and border color.

In certain embodiments, the user selectable link of the interaction result document is a link to a document or object 308 that includes one or more results related to the corresponding sub-portion of the visual query. In certain embodiments, the at least one search result includes data relating to a corresponding sub-portion of the visual query. Thus, when the user selects a selectable link associated with each sub-portion, the user is guided to search results corresponding to the recognized entity in each sub-portion of the visual query.

For example, if the visual query was a picture of a bar code, there may be portions of the picture that are related portions of the packaging to which the bar code is attached. The interaction result document may only contain bounding boxes around the bar code. When the user selects within the outlined bar code bounding box, the bar code search result is displayed. The bar code search result may include a single result, the name of the item corresponding to the bar code, or the bar code results may include multiple results, such as various locations where the item may be a purchase, a review, have.

In certain embodiments, when the sub-portion of the visual query corresponding to the individual visual identifier includes text that includes one or more terms, the search results corresponding to the individual visual identifiers are associated with at least one of the terms of the text Includes results from a search term query. In some embodiments, at least one matching (i.e., a search result) in which the sub-portion of the visual query corresponding to the individual visual identifier satisfies a predefined confidence (or other) criterion, The search results corresponding to the individual time identifiers include the name, handle, contact information, account information, address information, the current location of the associated mobile device associated with the person having the face included in the selectable sub-portion, - other images of a person having a face included in the portion, and potential image matches for that person ' s face. In certain embodiments, at least one matching (i.e., search result) in which a sub-portion of a visual query corresponding to a respective visual identifier satisfies a predefined confidence (or other) criterion The search results corresponding to the individual visual identifiers include at least one of object information, object review, an option to initiate the purchase of the item, an option to initiate the bid to the item, a list of similar items, and a list of related items .

Optionally, the individual user selectable links in the interaction result document include anchor text, which is displayed on the document without activating the link. The anchor text provides information such as key words or terms related to the information obtained when the link is activated. The anchor text may be displayed (307) as part of the label or displayed in a portion of the bounding box (304), or when the user causes the cursor to roll over a user-selectable link for a pre- As additional information.

Optionally, an individual user selectable link in the interaction result document is a link to a search engine for retrieving documents or information corresponding to a text-based query (sometimes referred to herein as a query term). Activation of the link causes execution of the search by the search engine, and the query and search engine are specified by the link, with the results returned to the client system (e.g., the search engine is specified by the URL in the link, - based search query is specified by the URL parameter of the link). Optionally, in this embodiment, the link may include anchor text that specifies terms or text in the search query.

In certain embodiments, an interaction result document that is computed in response to a visual query may include a plurality of links corresponding to results from the same search system. For example, the visual query may be a picture or an image of a group of people. The interaction result document may include bounding boxes around each person and return results from the face recognition search system for each face in the group when activated. For any visual queries, a plurality of links in an interaction result document corresponds to search results from two or more search systems (310). For example, if a person and a dog's pictures were submitted as visual queries, the bounding boxes in the interaction result document can separate out the person and dog and outline. When the individuals are selected (in the interaction result document), the search results are returned from the face recognition search system, and when the dog is selected (in the interaction result document), the results are returned from the image-to-terms search system. For any visual queries, the interaction result document includes an OCR result and an image matching result (312). For example, if a person's picture standing next to the signpost is submitted as a visual query, the interaction result document may include visual identifiers for the text of the sign and for the person. Similarly, if a scan of a magazine is used as a visual query, the interaction result document may also include visual identifiers for photographs or brands in advertisements on the page, as well as visual identifiers for the text of the articles on the page have.

After the interaction result document is generated, it is transmitted to the client system (314). In some embodiments, the interaction result document (e.g., document 1200, FIG. 15) includes a list of search results from one or more parallel search systems, as described above with reference to FIG. 2, do. In certain embodiments, the interaction result document is displayed (315) on the client system on or above the list of search results from one or more parallel search systems, as shown in FIG. 15, adjacent to the list.

Optionally, the user will interact with the resulting document by selecting the time identifier in the resulting document. The server system receives (316) information from the client system about the user selection of the visual identifier in the recipient document. As discussed above, in certain embodiments, the link is activated by selecting the active area in the bounding box. In other embodiments, the link is activated by user selection of the time identifier of the sub-portion of the visual query, rather than the bounding box. In certain embodiments, the linked time identifier is a hot button, a label located near the sub-portion, a word underlined in the text, or other indication of the object or subject in the visual query.

In embodiments where a search result list is displayed (315) as an interaction result document, when a user selects (316) a user selectable link, the search result is identified in the search result list corresponding to the selected link. In certain embodiments, the cursor will jump to the first result corresponding to the selected link or automatically to the first result. In some embodiments in which the display of the client 102 is too small to display both the interaction result document and the entire search result list, selecting a link in the interaction result document may include selecting at least one first result To scroll or jump the search result list. In certain other embodiments, in response to user selection of the link in the interaction result document, the result list is re-ordered such that the first result corresponding to the link is displayed on top of the result list.

In any of the embodiments, when the user selects 316 the user selectable link, the visual query server system sends at least a subset of the results related to the corresponding sub-portion of the visual query to the client for display to the user (318). In certain embodiments, a user may simultaneously select multiple time identifiers and simultaneously receive a subset of the results for all selected time identifiers. In other embodiments, the search results corresponding to the user selectable links may include a portion of the user selectable links to provide search results to the user instantaneously in response to a user selection of the one or more links of the interaction result document Lt; RTI ID = 0.0 > user < / RTI >

4 is a flow chart illustrating communications between a client and a visual query server system. The client 102 receives the visual query from the user / queryer (402). In certain embodiments, the visual queries can only be accepted from users who sign up or "opt in" to the visual query system. In certain embodiments, searches for face recognition matches are performed only for users signing up for the face recognition visual query system, while other types of visual queries are based on whether users are "opting in " Regardless of who you are.

As described above, the format of the visual query can take many forms. The visual query will likely include one or more subjects located in the sub-portions of the visual query document. For any visual queries, the client system 102 performs type aware line-processing on the visual query (404). In certain embodiments, the client system 102 retrieves certain recognizable patterns in this pre-processing system. For example, the client may recognize colors for arbitrary visual queries. For any visual queries, the client may recognize that the particular sub-portion is likely to contain text (since the region is made up of small dark characters circumscribed by a light space, etc.). The client may include any number of pre-processing type recognizers or type recognition modules. In certain embodiments, the client will have a type recognition module to recognize bar codes (bar code recognition 406). This can be done by recognizing unique stripe patterns in the rectangular region. In certain embodiments, the client will have a type recognition module (face detection 408) to recognize that a sub-portion of the visual query or a particular subject is likely to contain a face.

In certain embodiments, the recognized "type" is returned to the user for verification. For example, the client system 102 may return a message saying "the barcode is found in your visual query, are you interested in receiving the barcode query results?" In some embodiments, the message may also represent a sub-portion of the visual query for which the type is found. In certain embodiments, this representation is similar to the interaction result document described with reference to FIG. For example, an outline of a sub-portion of a visual query may be displayed, indicating that the sub-portion is likely to include a face, and the user may be asked if they are interested in receiving face recognition results.

After the client 102 performs selective pre-processing of the visual query, the client sends the visual query to the visual query server system 106, particularly to the front end visual query processing server 110. In some embodiments, it can be determined that pre-processing yields related results, i.e., if one of the type recognition modules determines that the sub-portion of the query or query is likely to be of a particular type (face, text, bar code, etc.) , The client will pass information about the results of the pre-processing. For example, the client may indicate that the facial recognition module is 75% certain that a particular sub-portion of the visual query includes a face. More generally, the pre-processing results include one or more subject type values (e.g., bar code, face, text, etc.), if any. Optionally, the pre-processing results sent to the visual query server system include information identifying the sub-portion of the visual query corresponding to the subject type value for each subject type in the pre-processing results, For each subject type, one or more of the identification of the corresponding sub-portion of the visual query and / or a confidence value indicating the level of confidence in the subject type value.

The front-end server 110 receives the visual query from the client system (202). The received visual query may include the pre-processing information discussed above. As described above, the front end server sends a visual query to a plurality of parallel search systems (210). If the front-end server 110 receives pre-processing information regarding the possibility that a sub-portion includes a subject of a particular type, the front-end server may pass this information according to one or more of the parallel search systems . For example, the facial recognition retrieval system 112-A may pass information that a particular sub-portion may be a face so that it can first process that sub-section of the visual query. Similarly, transmission of the same information (where a particular sub-portion may be a face) may be used by other parallel search systems to ignore the sub-portion or to analyze other sub-portions first. In some embodiments, the front end server will not pass pre-processing information to the parallel search systems, but will use this information instead to augment the way to process the results received from the parallel search systems.

As described with reference to FIG. 2, for some visual queries, the front-end server 110 receives 214 a plurality of search results from the parallel search systems. The front end server may then perform various ranking and filtering and may generate the interactive search result document described with reference to Figures 2 and 3. If the front-end server 110 receives pre-processing information regarding the likelihood that a sub-portion includes a subject of a particular type, filtering is performed by giving preference to these results matching the pre-processed recognized subject type And order. If the commercial user indicates that a particular type of result has been requested, the front-end server will consider the user's requests when processing the results. For example, the front-end server may filter out all the different results only when the user requests bar code information, or list all results included in the requested type before the front-end server lists the other results. If an interactive visual query document is returned, the server pre-searches for links associated with the results of the type that the user indicated interest in, while providing links to perform related searches on other subjects shown in the interaction result document . The front end server 110 then sends the search results to the client system (226).

The client 102 receives the results from the server system (412). When applicable, these results will include results matching the type of results found in the pre-processing stage. For example, in certain embodiments, the results may include one or more bar code results (414) or one or more face recognition results (416). If the client's pre-processing modules indicate that a particular type of result is favored and the result is found, then the found results of that type will be listed prominently.

Optionally, the user may select one or more of the results or annotate (418). The user can select one search result, select a particular type of search result, and / or select a portion of the interaction result document (420). The selection of the result is an implied feedback that the result returned is related to the query. Such feedback information may be used for future query processing operations. Annotations also provide explicit feedback on the returned results that can be used in future query processing operations. Annotations take the form of separate annotations (free form or structured form) or corrections of the returned result parts (such as corrections to mis-OCRed words).

The user's selection of one search result is generally the process of choosing between " correct "results from several of the same type (e.g., selecting the correct result from the face recognition server) . The user's selection of a particular type of search result (e.g., also selecting the type of interest in the magazine rather than the visual results for the ads on the same page), typically selecting a result type of interest from the returned results of several different types Selecting the OCR text of the article) is a process referred to as the clarification of the intent. The user can similarly select certain linked words (such as recognized naming entities) in the OCRed document described in detail with reference to FIG.

The user may alternatively or additionally attempt to annotate particular search results. The annotation may be in a free-style or structured format (422). The annotations may be descriptions of the results or may be reviews of the results. For example, annotations may indicate the name of the subject (s) in the result, or the annotations may indicate "this is a good book" or "this item was broken in the year of purchase ". Another example of an annotation is a bounding box drawn by a user around a sub-portion of a user-provided textual and visual query identifying a subject or object within a bounding box. User annotations are described in more detail with reference to FIG.

Other annotations and user selections of search results are transmitted 424 to the server system. The front-end server 110 receives the selections and annotations and additionally processes them (426). If the information is a selection of an object, sub-region or term in the interaction result document, additional information regarding the selection may be suitably requested. For example, if the selection is a visual result, more information about the visual result may be requested. If the choice is a word (from an OCR server or image-to-term server), a text search of the term may be sent to the term query server system 118. If the selection is from a facial image recognition retrieval system, the profile of the person may be requested. If the selection is for a specific part of the interactive search result document, the underlined visual query results may be requested.

When the server system receives an annotation, the annotation is stored in the query and annotation database 116 described with reference to FIG. The information from the annotation database 116 is then periodically copied to individual annotation databases for one or more of the parallel server systems, as discussed below with reference to Figures 7-10.

5 is a block diagram illustrating a client system 102 in accordance with one embodiment of the present invention. Client system 102 typically includes one or more processing units (CPUs) 702, one or more networks or other communication interfaces 704, a memory 712, and one or more communication buses 714). The client system 102 includes a user interface 705. The user interface 705 includes a display device 706 and optionally includes input means such as a keyboard, a mouse or other input buttons 708. Alternatively or additionally, the display device 706 includes a touch sensitive surface 709, wherein the display 706/709 is a touch sensitive display. In client systems having touch sensitive displays 706/709, the physical keyboard is optional (e.g., a soft keyboard may be displayed when a keyboard input is needed). In addition, any client systems use a microphone and voice recognition to supplement or replace the keyboard. Optionally, the client 102 includes a global positioning satellite (GPS) receiver or other location sensing device 707 for determining the location of the client system. In any implementation, visual querying devices are provided that require the client system 102 to provide a visual query server system to receive location information indicative of the location of the client system 102.

The client system 102 also includes an image capture device 710, such as a camera or a scanner. The memory 712 includes a high speed random access memory, such as DRAM, SRAM, DDR RAM or other random access solid state memory devices, and may include one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, Non-volatile memory such as other non-volatile solid state storage devices. The memory 712 may optionally include one or more storage devices remotely located from the CPU (s) Non-volatile memory device (s) in memory 712 or alternatively memory 712 include non-volatile computer readable storage media. In certain embodiments, the memory 712 or computer readable storage medium of memory 712 stores the following programs, modules and data structures or a subset thereof:

An operating system 716 including procedures for performing hardware dependent tasks and handling various basic system services;

- to one or more communication networks, such as the Internet, other wide area networks, local area networks, city area networks, etc., and to other computers via one or more communication network interfaces 704 (wired or wireless) A network communication module 718 used to connect the network interface module 718;

An image capture module 720 for processing the individual images captured by the image capture device / camera 710, where the individual images are displayed as visual queries (e.g., by a client application module) to a visual query server system, Can be transmitted;

A query submission module 724 for submitting visual queries to the visual query server system; A region of interest selection module 725 that detects the selection of the region of interest (such as operation on the touch sensitive display 706/709) in the image and prepares the region of interest as a visual query; A result browser 726 for displaying the results of the visual query; An annotation module 728 having optional modules for structured annotation text input 730 such as freehand annotation text input 732 or one form of file annotation that can accept annotations from various formats, Various aspects of the query by image, including (but not limited to) an image region selection module 734 (sometimes referred to herein as a result selection module) that allows a user to select a particular sub-portion of an image for annotation One or more client application modules (722) for handling the client applications;

Optional content authoring application (s) 736 that allows the user to author a visual query by creating or editing an image directly over the captured image device 710 directly; Optionally, one or these applications 736 may include instructions that enable a user to select a sub-portion of an image for use as a visual query;

An optional local image analysis module 738 for pre-processing the visual query before sending the visual query to the visual query server system. Local image analysis can recognize certain types of images or sub-areas within an image. Examples of image types that can be recognized by these modules 738 include face type (face image recognized in visual query), barcode type (bar code recognized in visual query), and text type ≪ / RTI >text); And

Additional optional client applications 740 such as email applications, phone applications, browser applications, mapping applications, instant messaging applications, social networking applications, and the like. In certain embodiments, an application corresponding to an appropriate executable search result may be launched or accessed when an executable search result is selected.

Optionally, the image region selection module 734, which allows the user to select a particular sub-portion of the image for the annotation, also allows the user to select the search result as an "accurate " hit without further annotation. For example, the user can be presented with the top N face recognition matches and select the correct people from the result list. More than one type of result will be displayed for any search queries, and the user will select the type of result. For example, an image query can include a person standing next to a tree, but only the results of a person are of interest to the user. Thus, the image selection module 734 allows the user to indicate which type of image is the "correct" type, i.e., the type that the user desires to receive. The user may also wish to annotate the search results by adding personal comments or explanatory words using the free-form annotation text input module 732 or the annotation text input module 730 (for annotating in one form).

In optional embodiments, optional local image analysis module 738 is part of client application 108 (FIG. 1). Also, in certain embodiments, the optional local image analysis module 738 includes one or more programs for performing local image analysis to pre-process or categorize visual queries or portions thereof. For example, the client application 722 may recognize that the image includes a bar code, face, or text before submitting a visual query to the search engine. In certain embodiments, when the local image analysis module 738 detects that the visual query includes a particular type of image, the module asks the user if they are interested in the type of search results they have. For example, the local image analysis module 738 may detect a face based on its general characteristics (i.e., without determining which person's face it is), and may prompt the user immediately before sending the query to the visual query server system Feedback can be provided. You can return results such as "Are you interested in getting face recognition matches for this face?" This may save time for the visual query server system 106 (FIG. 1). For any visual queries, the front end visual query processing server 110 (FIG. 1) sends a visual query to the search system 112 corresponding only to the type of image recognized by the local image analysis module 738 . In other embodiments, the visual query for the retrieval system 112 may send a visual query to all of the retrieval systems 112A-N, but may correspond to the type of image recognized by the local image analysis module 738 Lt; RTI ID = 0.0 > 112 < / RTI > In certain embodiments, the manner in which the local image analysis affects the operation of the visual query server system depends on the configuration of the client system or the configuration or processing of parameters associated with the user or client system. In addition, the actual content of any particular visual query and the results computed by the local image analysis may cause different visual queries to be handled differently in either or both of the client system and the visual query server system.

In certain embodiments, bar code recognition is performed in two steps, using an analysis of whether the visual query includes bar codes performed on the client system in the local image analysis module 738. [ The visual query is then passed to the barcode search system only if the client determines that the visual query is likely to contain the barcode. In other embodiments, the barcode search system processes all visual queries.

Optionally, client system 102 includes additional client applications 740.

6 is a block diagram illustrating a front end visual query processing server system 110 in accordance with one embodiment of the present invention. The front end server 110 typically includes one or more processing units (CPUs) 802, one or more networks or other communication interfaces 804, a memory 812, and one or more communication buses 814 < / RTI > The memory 812 includes a high speed random access memory, such as DRAM, SRAM, DDR RAM or other random access solid state memory devices, and may include one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, Non-volatile memory, such as other non-volatile solid state storage devices. The memory 812 may optionally include one or more storage devices remotely located from the CPU (s) Non-volatile memory device (s) in memory 812, or alternatively memory 812, include non-transitory computer readable storage media. In certain embodiments, the computer-readable storage medium of memory 812 or memory 812 stores the following programs, modules and data structures or a subset thereof:

An operating system 816 including procedures for performing hardware dependent tasks and handling various basic system services;

One or more communication networks, such as the Internet, other wide area networks, local area networks, city area networks, etc., and other computers via one or more communication network interfaces 804 (wired or wireless) A network communication module (818) used to connect the network (110);

A query manager 820 for handling incoming visual queries from the client system 102 and sending them to two or more parallel search systems; As described elsewhere in this application, in any special situations, the visual query may be performed, for example, when the visual query includes a client-generated command (e.g., "face recognition search only"), Can be guided to only one search systems;

A result filtering module 822 for selectively filtering results from the one or more parallel search systems and for sending higher or "related" results to the client system 102 for display;

A result ranking and formatting module 824 for selectively ranking results from one or more parallel search systems and formatting the results for display;

A result document generation module 826 is used when appropriate to generate an interactive search result document; Module 826 may include sub-modules including but not limited to bounding box generation module 828 and link generation module 830;

A label generation module 831 for generating labels which are visual identifiers of individual sub-portions of the visual query;

An annotation module 832 for receiving annotations from the user and sending them to the annotation database 116;

An executable search result module 838 for generating one or more executable search result elements in response to a visual query, each being configured to launch a client-side execution; Examples of executable search result elements are buttons for initiating a phone call, initiating an email message, mapping an address, reserving a restaurant, and providing an option to purchase an item; And

A query and annotation database 116 that includes the database itself 834 and an index 836 for the database;

Results ranking and formatting module 824 ranks the results returned from one or more parallel search systems 112-A-112-N (FIG. 1). As already mentioned above, for any visual queries, only results from one search system can be related. In this example, only relevant search results from one search system are ranked. In these examples, in some embodiments, different types of search results may be associated. In these examples, in some embodiments, the result ranking and formatting module 824 may generate a result (e.g., a result with the highest relevance score) that is most relevant on the results for the less relevant search systems The branch will rank all results from the search system. In other embodiments, the result ranking and formatting module 824 ranks the top results from each relevant search system on the remaining results. In some embodiments, the result ranking and formatting module 824 ranks the results according to the relevance scores calculated for each of the search results. For any visual queries, the enhanced text queries are performed in addition to searching in parallel visual search systems. In certain embodiments, and also when text queries are performed, their results are displayed in a visually distinct manner from the visual search system results.

The result ranking and formatting module 824 also formats the results. In certain embodiments, the results are displayed in list format. In certain embodiments, the results are indicated by an interaction result document. In certain embodiments, both an interaction result document and a list of results are displayed. In certain embodiments, the type of query determines how the results are displayed. For example, if more than one searchable subject is detected in the visual query, then the interaction result document is calculated, whereas if only one searchable subject is detected, the results will be displayed in list format only.

Result document generation module 826 is used to generate an interactive search result document. The interactive search result document may have one or more detected and retrieved subjects. The bounding box creation module 828 creates a bounding box around one or more of the retrieved subjects. The bounding boxes may be rectangular boxes or may represent the contour of the shape (s) of the subject (s). The link generation module 830 generates links to search results associated with their respective subjects in the interactive search result document. In certain embodiments, a click in the bounding box area activates a corresponding link inserted by the link creation module.

The query and annotation database 116 contains information that can be used to improve visual query results. In certain embodiments, the user may annotate the image after the visual query results are displayed. Further, in certain embodiments, the user may annotate the image prior to sending the image to the visual query retrieval system. Line-annotations can help visual query processing by focusing on results or by performing text-based searches on annotated words in parallel with visual query retrieval. In some embodiments, annotated versions of a picture may be known to be returned as a latent image matching hit (e.g., by specifying the image and annotation (s) so that the user is, for example, When giving permission). For example, if a user annotates an image by taking a picture of the flower and giving genus and species information to the flower, the user may be able to see someone who performs the visual quality search for the flower The user may wish to have the image displayed. In some embodiments, the information from the query and annotation database 116 is periodically (e.g., periodically) added to the parallel search systems 112, which incorporates the relevant portions of information (if any) into their respective individual databases 114 / RTI >

7 is a block diagram illustrating one of the parallel search systems used to process the visual query. FIG. 7 illustrates a " generic "server system 112-N in accordance with one embodiment of the present invention. This server system is comprehensive only when displaying any one of the visual query servers 112-N. A generic server system 112-N typically includes one or more processing units (CPUs) 502, one or more networks or other communication interfaces 504, a memory 512, and one Or more communication buses 514. Memory 512 includes high speed random access memory, such as DRAM, SRAM, DDR RAM, or other random access solid state memory devices; And non-volatile memory, such as one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid state storage devices. The memory 512 may optionally include one or more storage devices remotely located from the CPU (s) 502. Non-volatile memory device (s) in memory 512 or alternatively memory 512 include non-volatile computer readable storage media. In certain embodiments, the memory 512 or a computer readable storage medium of the memory 512 stores the following programs, modules and data structures or a subset thereof;

An operating system 516 for carrying out hardware dependent tasks and including procedures for handling various basic system services;

A generic server system (e.g., the Internet) may be provided to other computers via one or more communication networks and one or more communication network interfaces 504 (wired or wireless), such as the Internet, other wide area networks, local area networks, 112-N; < / RTI >

A search application 520 specific to a particular server system, e.g., a barcode search application, a color recognition search application, a goods recognition search application, an object-or-object category search application, and the like;

An optional index 522 when a particular search application uses the index;

An optional image database 524 for storing images associated with a particular retrieval application, if present, the stored image data being dependent on the retrieval process type;

A selective result ranking module 526 (sometimes referred to as an associated scoring module) for ranking results from the search application, the ranking module may assign relevance scores for each result from a search application, If the pre-defined minimum score is not reached, a null and zero value score may be returned to the front end visual query processing server indicating that the results from this server system are not relevant; And

To receive annotation information from the annotation database 116 (Figure 1) that determines whether some of the annotation information is relevant to a particular search application and to integrate any determined relevant portions of annotation information into each annotation database 530 Annotation module 528.

FIG. 8 is a block diagram illustrating an OCR retrieval system 112-B used to process a visual query in accordance with an embodiment of the present invention. OCR retrieval system 112-B typically includes one or more processing units (CPUs) 602, one or more networks or other communication interfaces 604, a memory 612, and one or more Communication busses 614. Memory 612 includes high speed random access memory such as DRAM, SRAM, DDR RAM or other random access solid state memory devices; Non-volatile memory such as one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid state storage devices. The memory 612 may optionally include one or more storage devices remotely located from the CPU (s) Non-volatile memory device (s) in memory 612, or alternatively memory 612, include non-volatile computer readable storage media. In certain embodiments, the computer-readable storage medium of memory 612 or memory 612 stores the following programs, modules and data structures or a subset thereof;

An operating system 616 that includes procedures for handling various base system services and performing hardware dependent tasks;

- an OCR search system (such as the Internet), to other computers via one or more communication networks and one or more communication network interfaces 604 (wireless or wired), such as the Internet, other wide area networks, local area networks, 112-B); < / RTI >

An Optical Character Recognition (OCR) module 620 that attempts to recognize text in a visual query and transforms images of characters into characters;

An optional OCR database 114-B used by the OCR module 620 to recognize certain fonts, text patterns, and other properties that are unique to character recognition;

An optional spell checking module 622 for identifying transformed words for the dictionary and replacing potentially mis-transformed characters with words that match other dictionary words, ;

Retrieving the naming entities within the translated text, sending the recognized naming entities as terms of query term to the term query server system 118 (FIG. 1), linking the OCRed text associated with the recognized naming entities An optional naming entity recognition module (624) for providing results from the term querying server system

To identify the translated segments (such as translated sentences and phrases) for the database of text segments, and to identify OCRed text segments that match potentially mis-converted characters to another text matching application text segment In some embodiments, the text segment found by the text matching application is provided as a link to the user (e. G., ≪ RTI ID = 0.0 > If the user has scanned a page in the New York Times, the text-matching application can provide a link to the entire posted article on the New York Times website);

A result ranking and formatting module 626 for formatting the OCR results for display and formatting optional links to naming entities and optionally for ranking any related results from the text matching application; And

From annotation database 116 (FIG. 1) that determines whether any annotation information is relevant to the OCR search system, and incorporates any determined relevant portions of annotation information into each annotation database 630 Gt; 628 < / RTI >

9 is a block diagram illustrating a face recognition retrieval system 112-A used to process a visual query in accordance with an embodiment of the present invention. A face recognition system 112-A typically includes one or more processing units (CPUs) 902, one or more networks or other communication interfaces 904, a memory 912, and one or more And communication buses 914. [ Memory 912 includes high speed random access memory such as DRAM, SRAM, DDR RAM or other random access solid state memory devices; Non-volatile memory such as one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid state storage devices. The memory 912 may optionally include one or more storage devices remotely located from the CPU (s) 902. Non-volatile memory device (s) in memory 912 or alternatively memory 912 include non-volatile computer readable storage media. In certain embodiments, the memory 912 or computer readable storage medium of memory 912 stores the following programs, modules and data structures or a subset thereof:

An operating system 916 that includes procedures for handling various basic system services and performing hardware dependent tasks;

One or more communication networks, such as the Internet, other wide area networks, local area networks, city area networks, etc., and other computers via one or more communication network interfaces 904 (wired or wireless) A network communication module 918 used to connect to the network 112-A;

A face recognition search application 920 for searching for face images that match the face (s) displayed in the visual query in the face image database 114-A may be used for each match found in the face image database 114- The social network database 922 is searched.

A face image database (114-A) for storing one or more face images for a plurality of users; Optionally, the facial image database includes facial images for people other than users, such as others, who are known by family members and users and identified as appearing in images included in the facial image database 114-A ; Optionally, the face image database includes face images obtained from external sources, such as, for example, vendors of face images legally in the public domain;

Alternatively, as described in more detail with reference to FIG. 12A, the name, address, occupation, group memberships, social network connections, current GPS location of the mobile device, shared preferences, interests, age, A social network database 922 that includes information about users of the social network, such as statistics, job information, and the like;

A result ranking and formatting module 924 for ranking potential face matches (e.g., assigning related and / or matching quality scores) from the face image database 114-A and formatting the results for display; ; In certain embodiments, the ranking or scoring of results uses relevant information retrieved from the aforementioned social network database; In certain embodiments, the search format results include potential image matches as well as a subset of information from the social network database; And

Receiving annotation information from annotation database 116 (Figure 1) that determines whether any annotation information is relevant to the face recognition search system and storing any determined relevant portions of annotation information in each annotation database 928 (926).

10 is a block diagram illustrating an image-to-terms retrieval system 112-C used to process a visual query in accordance with an embodiment of the present invention. In certain embodiments, the image-to-term search system recognizes objects in a visual query (instance aware). In other embodiments, the image-to-term search system recognizes object categories in a visual query (type recognition). In certain embodiments, the image-to-terms system recognizes both objects and object-categories. The image-to-vocabulary search system returns potential term matches for images in a visual query. The image-to-term search system 112-C typically includes one or more processing units (CPUs) 1002, one or more networks or other communication interfaces 1004, a memory 1012, And one or more communication buses 1014 for connection. The memory 1012 may include a high-speed random access memory, such as DRAM, SRAM, DDR RAM or other random access solid state memory devices, and may include one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, Non-volatile memory such as non-volatile solid state storage devices. The memory 1012 optionally includes one or more storage devices remotely located from the CPU (s) 1002. Non-volatile memory device (s) in memory 1012 or alternatively memory 1012 include non-volatile computer readable storage media. In certain embodiments, the memory 1012 or computer readable storage medium of memory 1012 stores the following programs, modules and data structures or a subset thereof:

An operating system 1016 that includes procedures for handling various base system services and performing hardware dependent tasks;

Image-to-computer communication with other computers via one or more communication networks and one or more communication network interfaces 1004 (wired or wireless), such as the Internet, other wide area networks, local area networks, A network communication module 1018 used to connect terms search system 112-C;

Image-to-term search application 1020 for searching images in the image search database 114-C for images that match subjects or subjects in a visual query;

An image search database 114-C that can be retrieved by the search application 1020 to find similar images in the subject (s) of the visual query;

A term-to-image reverse index 1022 that stores text terms used by users when retrieving images using a text based query search engine 1006;

A result ranking and formatting module 1024 for ranking potential image matches and / or ranking terms associated with potential image matches identified in terms-to-image inverse index 1022; And

- receives annotation information from the annotation database 116 (FIG. 1) that determines whether any annotation information is associated with the image-to-term search system 112-C and sends to each annotation database 1028, An annotation module 1026 for storing determined relevant portions of the annotation module.

5-10 are intended to be functional descriptions of various features that may be represented by a set of computer systems rather than the structural schematics of the embodiments described herein. Indeed, and as will be appreciated by those skilled in the art, the separately shown items can be combined and any items can be separated. For example, any of the items shown separately in these figures may be implemented in a single server and the single items may be implemented in one or more servers. The actual number of systems used to implement visual query processing and which features are allocated between them will vary depending on the implementation.

Each of the methods described herein may be supervised by instructions stored on a non-transitory computer readable storage medium and executed by one or more processors of one or more servers or clients. The identified modules or programs (i. E. Sets of instructions) need not be implemented as separate software programs, procedures or modules, and therefore various subsets of such modules may be combined in various embodiments Or otherwise rearranged. Each of the operations illustrated in FIGS. 5-10 may correspond to instructions stored in computer memory or non-temporary computer-readable storage media.

FIG. 11 shows a client system 102 with a screen shot of an exemplary visual query 1102. The client system 102 shown in Fig. 11 is a mobile device such as a cellular phone, a portable music player, or a portable e-mail device. The client system 102 includes one or more input means 708, such as a display 706 and the buttons shown in this figure. In some embodiments, the display 706 is a touch sensitive display 709. In embodiments having a touch sensitive display 709, the soft buttons displayed on the display 709 can selectively replace some or all of the electromechanical buttons 708. [ The touch sensitive displays can also help to interact with the visual query results, as described in more detail below. The client system 102 also includes an image capture mechanism, such as a camera 710.

Figure 11 shows a video query 1102 that is a video frame or picture of a package on a store shelf. In the embodiments described herein, the visual query is a two-dimensional image with a resolution corresponding to the magnitude of the visual query at each pixel of the two dimensions. In this embodiment, visual query 1102 is a two-dimensional image of three-dimensional objects. Visual query 1102 includes various types of packaging including background elements, object package 1104 and human image 1106, image of trademark 1108, image of object 1110 and various text elements 1112 Lt; / RTI >

As described with reference to FIG. 3, the visual query 1102 includes a front end 1102 that sends a visual query 1102 to a plurality of parallel search systems 112A-N, receives results and generates an interaction result document And transmitted to the server 110.

Figures 12a and 12b each illustrate a client system 102 with screen shots of an embodiment of an interaction result document 1200. The interaction result document 1200 includes one or more visual identifiers 1202 of each of the sub-portions of the visual query 1102, each containing a user selectable link to a subset of search results. Figures 12a and 12b illustrate interaction result document 1200 with visual identifiers that are bounding boxes 1202 (e.g., bounding boxes 1202-1, 1202-2, and 1202-3) do. In the embodiments shown in Figures 12a and 12b, the user activates the display of search results corresponding to a particular sub-portion by tapping the active region within the space delineated by its bounding box 1202 do. For example, the user may activate search results corresponding to a person's image by tapping a bounding box 1306 (Figure 13) that surrounds the person's image. In other embodiments, the selectable link is selected using a mouse or keyboard rather than a touch sensitive display. In certain embodiments, the first corresponding search result is displayed when the user previews the bounding box 1202 (i.e., when the user once makes a mistake, taps once, or walks the pointer over the bounding box) . The user activates the display of a plurality of corresponding search results when the user selects a bounding box (i.e., the user double-clicks, double-tapes, or uses other mechanisms to represent the selection).

In the figures 12a and 12b, the time identifiers are bounding boxes 1202 that surround the sub-portions of the visual query. Figure 12a shows bounding boxes 1202 that are square or rectangular. Figure 12b shows a bounding box 1202 that represents the outline of the boundaries of identifiable entities in a sub-portion of a visual query, such as bounding box 1202-3 for a soda bottle. In some embodiments, each bounding box 1202 includes smaller bounding boxes 1202 therein. For example, in Figures 12a and 12b, a bounding box that identifies the package 1202-1 surrounds both the bounding box and other bounding boxes 1202 that identify the trademark 1202-2. In some embodiments including text, it also includes active hot links 1204 for some of the text terms. Figure 12b shows an embodiment in which "Active Drink" and "United States" are displayed as hot links 1204. The search results corresponding to these terms are the results received from the term query server system 118, while the results corresponding to the bounding boxes are the results from the query by the image search systems.

Figure 13 shows a client system 102 with a screenshot of an interaction result document 1200 coded by the type of entity recognized in the visual query. The visual query of Figure 11 includes a human image 1106, an image of a trademark 1108, an image of an object 1110, and various text elements 1112. Thus, the interaction result document 1200 displayed in Figure 13 includes a person 1306, a trademark 1308, an object 1310, and bounding boxes 1202 around the two text areas 1312. [ The bounding boxes of FIG. 13 are each represented using separate cross-hatching representing differently colored transparent bounding boxes 1202. In some embodiments, the time identifiers (and / or labels or other visual identifiers in the interaction result document 1200) of the bounding boxes may include an overlay color, an overlay pattern, a label background color, a label background pattern, Color, and bounding box border color. The type coding for certain recognized entities is shown with respect to the bounding boxes in FIG. 13, but coding by type can also be applied to time identifiers that are labels.

Figure 14 illustrates a client device 102 with a screen shot of an interaction result document 1200 having labels 1402 that are time identifiers of respective sub-portions of the visual query 1102 of Figure 11. Each of the label visual identifiers 1402 includes a user selectable link for a subset of corresponding search results. In certain embodiments, the selectable link is identified by the descriptive text displayed in the area of the label 1402. [ Certain embodiments include a plurality of links in one label 1402. [ For example, in FIG. 14, a label hovering over an image of a woman drinking a beverage includes a link to face recognition results for a woman and a link to the particular picture (e.g., images of other objects or advertisements that use the same picture ) ≪ / RTI > to the image recognition results.

In FIG. 14, labels 1402 are displayed as partially transparent regions having text positioned over their respective sub-portions of the interaction result document. In other embodiments, each label is positioned near but not above its respective sub-portion of the interaction result document. In certain embodiments, the labels are coded by type in the same manner as discussed with reference to FIG. In certain embodiments, the user may display the search results corresponding to the particular sub-portion corresponding to the label 1302 by tapping the active area within the space delineated by the perimeter or edges of the label 1302 Activate. The same preview and selection functions discussed above with reference to the bounding boxes of Figures 12a and 12b also apply to the visual identifiers, which are labels 1402. [

FIG. 15 shows a screen shot of the original visual query 1102 and the interaction result document 1200 displayed simultaneously with the result list 1500. In certain embodiments, the interaction result document 1200 is displayed by itself as shown in Figures 12-14. In other embodiments, the interaction result document 1200 is displayed simultaneously with the original visual query, as shown in FIG. In certain embodiments, the list of visual query results 1500 is displayed simultaneously with the original visual query 1102 and / or the interaction result document 1200. The type of client system and the amount of free space on the display 706 can determine if a list of results 1500 is displayed simultaneously with the interaction result document 1200. In some embodiments, the client system 102 not only receives both a list of results (1500) and an interaction result document (1200) in response to a visual query submitted to the visual query server system, And displays a list of results 1500 when scrolling down the interaction result document 1200. [ In some of these embodiments, the client system 102 may be re-established since the list of results 1500 is received by the client system 102 in response to a visual query and then stored locally in the client system 102 Displays the results corresponding to the user selected time identifier 1202/1402 without having to query the server.

In any of the embodiments, the list of results 1500 is organized into categories 1502. Each category includes at least one result (1503). In certain embodiments, category titles are highlighted to distinguish themselves from the results 1503. The categories 1502 are ordered according to their calculated category weights. In certain embodiments, the category weight is a combination of the weights of the top N results in the category. Thus, a category that is likely to yield more relevant results is displayed first. In embodiments in which more than one category 1502 is returned for the same recognized entity (such as facial image recognition matching and image matching shown in FIG. 15), the category displayed first has a higher category weight.

3, when the selectable link in the interaction result document 1200 is selected by the user of the client system 102, the cursor is moved to the appropriate category 1502 or, alternatively, Will automatically move to the first result 1503 in the category. Alternatively, when a selectable link in the interaction result document is selected by a user of the client system 102, the list of results 1500 is reordered such that the categories or categories associated with the selected link are displayed first. This is accomplished, for example, by coding selectable links into information identifying corresponding search results, or representing corresponding selectable links, or coding search results to indicate corresponding result categories.

In certain embodiments, the categories of search results correspond to a query query system by images that yield these search results. For example, in FIG. 15, some of the categories are object matching 1506, logo matching 1508, face recognition matching 1510, and image matching 1512. The original visual query 1102 and / or the interaction result document 1200 may be displayed similar to category titles such as query 1504. Similarly, results from any term search performed by the term query server may also be displayed as separate categories, such as web results 1514. [ In other embodiments, two or more entities in the visual query will yield results from the query system by the same image. For example, the visual query may include two different faces that can return results that are separate from the face recognition search system. Thus, in certain embodiments, the categories 1502 are partitioned by the recognized entity rather than by the search system. In some embodiments, the image of the recognized entity may be modified so that the results for the recognized entity are distinguishable from the results for other recognized entities, even if two results are produced by the same query by the image retrieval system. Is displayed in the recognized entity category header 1502. For example, in FIG. 15, the item matching category 1506 includes two entity entity entities and also two entity categories 1502 - a boxed object 1516 and a bottled object 1518, , Each having a plurality of corresponding search results 1503. In certain embodiments, the categories may be partitioned by the type of query system by the recognized entities and images. For example, in FIG. 15, there are two separate entities that returned relevant results under a thing matching category thing.

In certain embodiments, the results 1503 include thumbnail images. For example, as shown for the face recognition matching results in Fig. 15, smaller versions (also referred to as thumbnail images) of pictures of face matches for "actress X" and "social network friend Y" Such as the name of the person in the image.

For purposes of explanation, the above description has been described with reference to specific embodiments. It should be understood, however, that the foregoing illustrative discussions are not intended to limit, or to limit the invention to the precise forms disclosed. Many modifications and variations are possible in light of the above teachings. The embodiments were chosen and described in order to best explain the principles of the invention and its practical application, thereby enabling those skilled in the art to best utilize the invention and various embodiments with various modifications as are suited to the particular use contemplated. have.

Claims (28)

A computer-implemented method,
Based on applying the query image to at least an image-based search process that is specific to an image search component, from at least a first image search component and a second image search component, wherein the query image is submitted, Obtaining a set of resources to identify as matching an image;
(i) selecting a particular resource that the first image retrieval component identifies as matching the query image, and (ii) a particular resource that the second image retrieval component identifies as matching the query image;
(i) an area of the query image associated with the particular resource that the first image search component identifies as matching the query image, and (ii) the second image search component is identified as matching the query image Determining an area of the query image associated with the particular resource; And
(i) determining, in a first region of a search results page associated with the first image search component, the query image that is determined to be associated with the particular resource that the first image search component identifies as matching the query image A first interaction-search result that includes a thumbnail image associated with the region, the first interaction-search result includes a link to the particular resource that the first image search component identifies as matching the query image, (Ii) determining, in a second, different region of a search result page associated with the second image search component, that the second image search component is associated with the particular resource identified as matching the query image A second mutual image containing a thumbnail image associated with an area of the query image Wherein the second interaction-search result is linked to the particular resource that the second image search component identifies as matching the query image; and (iii) Generating an image search result page including a third region of the result page
/ RTI >
Computer-implemented method. The method according to claim 1,
Wherein the region of the query image determined to be associated with the particular resource that the first image retrieval component identifies as matching the query image comprises a bounding box representing the outline of the bounds of the identifiable entity in the sub- / RTI >
Computer-implemented method. 3. The method of claim 2,
Wherein the bounding box is associated with an active area of a user selectable link and the user selectable link associated with one or more search results corresponds to a sub-
Computer-implemented method. 3. The method of claim 2,
Identifying the type of identifiable entity in the sub-portion of the query image; And
Formatting the visual display of the bounding box based on the identified type of identifiable entity in the sub-portion of the query image
≪ / RTI >
Computer-implemented method. The method according to claim 1,
Wherein the region of the query image determined to be associated with the particular resource that the first image search component identifies as matching the query image comprises a text element, the method comprising:
Obtaining, from a term query retrieval component, a further set of resources based on the text element; And
Reinforcing the image search result page to include the additional set of resources
≪ / RTI >
Computer-implemented method. The method according to claim 1,
Wherein the region of the query image determined to be associated with the particular resource that the first image search component identifies as matching the query image comprises a face image, the method comprising:
Identifying one or more attributes associated with the person matching the face image; And
Reinforcing the image search result page to include one or more attributes associated with a person matching the face image
≪ / RTI >
Computer-implemented method. The method according to claim 1,
Wherein the generating the image search result page comprises:
(i) a specific resource that the first image search component identifies as matching the query image, and (ii) a search result list associated with a particular resource that the second image search component identifies as matching the query image Generating the image search result page to include the image search result page;
(ii) a user selection associated with one of the specific resources that the second image retrieval component identifies as matching the query image, the method comprising: (i) selecting a particular resource that the first image retrieval component identifies as matching the query image; and Receiving a selection of a possible link; And
Identifying a search result of the search result list corresponding to the selection of the user selectable link
≪ / RTI >
Computer-implemented method. The method according to claim 1,
(ii) a user selection associated with one of the specific resources that the second image retrieval component identifies as matching the query image, the method comprising: (i) selecting a particular resource that the first image retrieval component identifies as matching the query image; and Receiving a selection of a possible link; And
(I) a particular resource that the first image search component identifies as matching the query image, and (ii) the second image search component matches the query image Providing a subset of the search results associated with one of the specific resources identified as < RTI ID = 0.0 >
≪ / RTI >
Computer-implemented method. The method according to claim 1,
Wherein the first image retrieval component and the second image retrieval component are identical,
Computer-implemented method. The method according to claim 1,
Wherein the first image retrieval component and the second image retrieval component are different,
Computer-implemented method. As a system,
One or more storage devices storing instructions operable to cause the one or more computers to perform operations when executed by one or more computers and the one or more computers, , Said operations comprising:
Based on applying the query image to at least an image-based search process that is specific to an image search component, from at least a first image search component and a second image search component, wherein the query image is submitted, Acquiring a set of resources to identify as matching an image;
(i) selecting a particular resource that the first image search component identifies as matching the query image, and (ii) a particular resource that the second image search component identifies as matching the query image;
(i) an area of the query image associated with the particular resource that the first image search component identifies as matching the query image, and (ii) the second image search component is identified as matching the query image Determining an area of the query image associated with the particular resource; And
(i) determining, in a first region of a search results page associated with the first image search component, the query image that is determined to be associated with the particular resource that the first image search component identifies as matching the query image A first interaction-search result that includes a thumbnail image associated with the region, the first interaction-search result is linked to the particular resource that the first image search component identifies as matching the query image; ii) in a different second region of a search result page associated with the second image search component, the second image search component is associated with the query image, which is determined to be associated with the particular resource identified as matching the query image A second interaction-sword comprising a thumbnail image associated with the region Wherein the second interaction-search result is linked to the particular resource that the second image search component identifies as matching the query image; and (iii) the second interaction-search result of the search result page associated with the query image An operation of generating an image search result page including the third region
/ RTI >
system. 12. The method of claim 11,
Wherein the region of the query image determined to be associated with the particular resource that the first image retrieval component identifies as matching the query image comprises a bounding box representing the outline of the bounds of the identifiable entity in the sub- / RTI >
system. 13. The method of claim 12,
Wherein the bounding box is associated with an active area of a user selectable link and the user selectable link associated with one or more search results corresponds to a sub-
system. 13. The method of claim 12,
The operations include:
Identifying a type of an identifiable entity in a sub-portion of the query image; And
Formatting the visual display of the bounding box based on the identified type of identifiable entity in the sub-portion of the query image
≪ / RTI >
system. 12. The method of claim 11,
Wherein the region of the query image that is determined to be associated with the particular resource that the first image search component identifies as matching the query image comprises a text element,
Obtaining from the term query retrieval component an additional set of resources based on the text element; And
Wherein the image search result page includes an additional set of resources
≪ / RTI >
system. 12. The method of claim 11,
Wherein the region of the query image that is determined to be associated with the particular resource that the first image search component identifies as matching the query image comprises a face image,
Identifying one or more attributes associated with a person matching the face image; And
Reinforcing the image search result page to include one or more attributes associated with a person matching the face image
≪ / RTI >
system. 12. The method of claim 11,
The act of generating the image search result page includes:
(i) a specific resource that the first image search component identifies as matching the query image, and (ii) a search result list associated with a particular resource that the second image search component identifies as matching the query image Creating an image search result page to include;
(ii) a user selection associated with one of the specific resources that the second image retrieval component identifies as matching the query image, the method comprising: (i) selecting a particular resource that the first image retrieval component identifies as matching the query image; and Receiving a selection of a possible link; And
An operation of identifying a search result of the search result list corresponding to the selection of the user-
≪ / RTI >
system. 21. A computer-readable storage medium storing software comprising instructions executable by the one or more computers to cause one or more computers to perform operations when executed,
The operations include:
Based on an application of the query image to at least an image-based search process specific to an image search component, from each of at least a first image search component and a second image search component to which a query image is submitted, Obtaining a set of resources to identify as matching to a set of resources;
(i) selecting a particular resource that the first image search component identifies as matching the query image, and (ii) a particular resource that the second image search component identifies as matching the query image;
(i) an area of the query image associated with the particular resource that the first image search component identifies as matching the query image, and (ii) the second image search component is identified as matching the query image Determining an area of the query image associated with the particular resource; And
(i) determining, in a first region of a search results page associated with the first image search component, the query image that is determined to be associated with the particular resource that the first image search component identifies as matching the query image A first interaction-search result that includes a thumbnail image associated with the region, the first interaction-search result is linked to the particular resource that the first image search component identifies as matching the query image; ii) in a different second region of a search result page associated with the second image search component, the second image search component is associated with the query image, which is determined to be associated with the particular resource identified as matching the query image A second interaction-sword comprising a thumbnail image associated with the region Wherein the second interaction-search result is linked to the particular resource that the second image search component identifies as matching the query image; and (iii) the second interaction-search result of the search result page associated with the query image An operation of generating an image search result page including the third region
/ RTI >
Computer-readable storage medium. 19. The method of claim 18,
Wherein the region of the query image determined to be associated with the particular resource that the first image retrieval component identifies as matching the query image comprises a bounding box representing the outline of the bounds of the identifiable entity in the sub- / RTI >
Computer-readable storage medium. 20. The method of claim 19,
Wherein the bounding box is associated with an active area of a user selectable link and the user selectable link associated with one or more search results corresponds to a sub-
Computer-readable storage medium. delete delete delete delete delete delete delete delete

Images