KR20120014480A - Integrative image searching system and service method of the same - Google Patents

Abstract

PURPOSE: An integrated image searching system and service method thereof are provided to automatically process searching methods by selecting a decoder according to object types. CONSTITUTION: A capturing unit(120) creates object images by capturing an object. An image recognition unit(140) grasps object types by analyzing the object images based on image recognition. An integrated recognition engine(160) recognizes the object image by automatically operating a decoder according to the object types. The image recognition unit assorts the object types based on a specific point by extracting the specific point based on the image recognition from the object image. The decoder includes a barcode, a QR(Quick Response) code, NFC(Near Field Communication), RFID(Radio Frequency ID), OCR(Optical Character Recognition), and a face/image decoder.

Description

Integrated image retrieval system and its service method {INTEGRATIVE IMAGE SEARCHING SYSTEM AND SERVICE METHOD OF THE SAME}

The present invention relates to an integrated image retrieval system and a service method thereof. More particularly, when an image of an object to be searched is input through a smart phone or a PC-based terminal equipped with a web cam, the input image is based on feature extraction. The integrated image retrieval system and its service method capable of integrated recognition of all objects regardless of the type of the object by analyzing the recognition technology in advance to determine the type of the object and automatically driving the corresponding decoder according to the type of the object. It is about.

In general, when a user watches a movie or commercial program on a television or finds a favorite object (e.g., a person or an object) while shopping, or finds an object of interest to the user in general, the user may note the object. Or, recently, to capture and store by using the camera of the mobile terminal.

However, in the former case, the memo should be habitual and always have a memo paper, and there is a risk of losing the memo paper with the detailed information of the product.

In the latter case, it is easy to carry and manage in that the user always uses the mobile terminal. However, in order to search for a desired object through the captured image, it is necessary to manually input information exposed in the image. For example, the name or product number, shape, and color of the product exposed in the image should be input.

At this time, the search is clearly made about the information that is clearly exposed such as the name of the product or the product number, but there is a problem that the search operation is difficult when there is a characteristic such as a shape or an image or when the video is not known accurate information. .

For this reason, in recent years, technologies in which a decoder (recognition engine) that can be recognized by using an image of an object is applied to a terminal.

That is, a technique is disclosed in which a barcode decoder is mounted on a terminal to recognize a barcode from a barcode image and then searched, or a QR code decoder is mounted on a terminal to recognize a QR code from an image of a QR code and perform a search.

However, the above-described technologies are equipped with decoders for barcode, QR code, face recognition, and image recognition individually, so that recognition is limited according to the direction of the object, and the user directly recognizes the type to recognize the object. The disadvantage is that the request must be fulfilled.

The present invention was devised to solve the above problems, and when the image of the object to be searched is input, the terminal or server utilizes an image recognition technique based on feature extraction to identify the type of the object from the image in advance, and then identifies the corresponding type. It is an object of the present invention to provide a system and method capable of automatically recognizing all objects regardless of the type of an object by automatically calling a decoder to read an object.

To this end, according to a first aspect of the present invention, a terminal for integrated video search according to the present invention is a terminal for requesting a search for a desired object and receiving a search result by accessing a server through a communication network. Photographing means for photographing an object to generate an image of the object, an image recognition unit for analyzing the image of the object generated by the photographing means based on image recognition, and pre-identifying the type of the object; The integrated recognition engine may be configured to automatically drive a readable decoder according to the identified object type to recognize an image of the object.

According to a second aspect of the present invention, an image search server according to the present invention is a server for connecting to a terminal of a client through a communication network and receiving a search request for a desired object from the terminal. An interface module for communicating with a terminal through the communication network; an image recognition module for analyzing the image of the object based on image recognition based on image recognition when an image of the object is input through the interface module; According to the type of the object identified by the image recognition module, characterized in that it comprises an integrated recognition engine for automatically driving the readable decoder to recognize the image of the object.

According to a third aspect of the present invention, a search service method of a terminal according to the present invention is a search service method of a terminal which requests a search for a desired object by receiving a search result by accessing a server through a communication network, When the image of the object is input to the terminal, determining the type of the object in advance by analyzing characteristics of the image based on image recognition; The terminal automatically calling a readable decoder according to the type of the object to request driving; The terminal recognizes the object by reading an image of the object by the decoder requested to drive; The terminal may include receiving a search service by transmitting the recognized object to the server.

According to a fourth aspect of the present invention, a search service method in a server according to the present invention transmits a search result to a terminal when a search request for a desired object is received from the terminal by accessing a terminal of a client through a communication network. A search service method of a server, comprising: when an image of an object is input from a terminal to a server, the server determining a type of an object in advance by analyzing characteristics of the image based on image recognition; The server automatically calling a readable decoder according to the type of the identified object to request driving; The server recognizing an object by reading an image of the object by a decoder requested to be driven; And searching for an object recognized by the server and transmitting a search result to the terminal.

According to the present invention, even if various types of objects such as barcode, face image, QR code, NFC tag, RFID tag are input, the user recognizes the type automatically through image recognition of the object and selects and applies the decoder according to the recognized type so that the user There is an effect that can be automatically processed without the need to manually select and search by type of search. In addition, since integrated recognition of various objects is possible in one terminal or server, a convenient search service may be provided.

In addition, since a server-based integrated recognition engine can be applied to a device that does not have an integrated decoder for searching, a search service can be provided regardless of the device. Furthermore, when a new type of object is added, the corresponding decoder can be easily extended, so that it can be applied quickly.

In addition, when the present invention is linked with a shopping service using an online shopping mall, synergies and new services may be created.

1 is a diagram illustrating a network configuration of an integrated video retrieval system according to an exemplary embodiment of the present invention.
2 is a block diagram showing a detailed configuration of a terminal according to an embodiment of the present invention.
3 is a block diagram showing the detailed configuration of the integrated recognition engine shown in FIG.
4 is a block diagram showing a detailed configuration of an image search server according to an embodiment of the present invention.
5 is a flowchart illustrating a search process of a terminal when the integrated recognition engine is mounted in the terminal according to an embodiment of the present invention.
6 is a flowchart illustrating a search process between a server and a terminal when the integrated recognition engine is mounted on a server according to an exemplary embodiment of the present invention.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. The configuration of the present invention and the operation and effect thereof will be clearly understood through the following detailed description. Prior to the detailed description of the present invention, the same components will be denoted by the same reference numerals even if they are displayed on different drawings, and the detailed description will be omitted when it is determined that the well-known configuration may obscure the gist of the present invention. do.

The objects mentioned below are people, things, and specific bodies that users want to purchase while shopping or accidentally found by themselves, water itself, or objects that are exposed through programs such as identification codes of water or television. And the like. The identification code may be a product number including letters / numbers or the like, or may be a barcode, a QR code, a Near Field Communication (NFC) tag, a Radio Frequency IDentification (RFID) tag, an Optical Character Recognition (OCR) code, or the like. Every object has features in terms of text, shape, use, and functionality, and two or more features can coexist. For example, when an identification code is attached to glasses, the object becomes glasses and the image of the object includes identification code information as well as image information about the glasses.

1 is a diagram illustrating a network configuration of an integrated video retrieval system according to an exemplary embodiment of the present invention.

Integrated image search system according to an embodiment of the present invention, the terminal 100, which can obtain the image of the object to be searched for, to recognize and retrieve the image of the object received through the communication network 200 from the terminal 100 It may be implemented including an image search server 300.

In addition, the apparatus may further include an additional information server 400 for providing additional information about each object to the image search server 300. The additional information may include detailed information about the object when the object is a thing, shopping purchase information (price information, retailer information, etc.), and detailed information related to the person (wearing clothes, accessory information, music, etc.) when the object is a person. Album information, etc.). In the former case, the terminal 100 may be provided with a shopping service for directly purchasing a desired product by directly connecting to the additional information server 400 through the communication network 200.

The terminal 100 according to an exemplary embodiment of the present invention may be applied to any terminal capable of transmitting and receiving data through the communication network 200 and obtaining an image of an object, regardless of the type of the terminal. For example, a PC, a PDA, a digital camera, a web cam, a mobile terminal, or the like may be applied.

In particular, the terminal 100 according to an exemplary embodiment of the present invention generates and stores an image of an object by photographing an object that is accidentally found during shopping or at a time, and when a user wants to manage detailed information and an object of the object. According to the user's request, the image of the object is transmitted to the image search server 300 through the communication network 200. To this end, the terminal 100 may be provided with a photographing means 120 for photographing an object and generating an image thereof.

In addition, the terminal 100 according to an embodiment of the present invention recognizes the image of the object obtained from the photographing means 120 through the image recognition base to determine what type of object is, and select and apply a decoder according to the identified type This enables integrated recognition of various objects. To this end, the terminal 100 may be provided with an integrated recognition engine that performs the above functions. Its detailed configuration will be described in detail below.

In addition, the terminal 100 according to an embodiment of the present invention, the location information on the location where the object was photographed, the time when the product of interest was taken, that is, the date and time information that is information on the date and time, and the selling price or the store for the object. At least one or more of other information including additional information may be input and included in the image of the object.

In addition, the terminal 100 according to an embodiment of the present invention does not receive location information of an object photographed by a user, and when an object is photographed, the terminal 100 is equipped with a global positioning system (GPS) to photograph a product of interest by itself. The location may be identified and location information may be added to the image of the object.

In addition, the terminal 100 according to an embodiment of the present invention accesses the additional information server 400 using a data communication service or an Internet service provided by the communication network 200, and purchases an object with the additional information server 400. You can get services.

The communication network 200 according to an embodiment of the present invention is a network that provides a service by communicating with the terminal 100 in a wired or wireless manner. That is, the communication network 200 may be a wired internet network, and may be a wireless data network (Internet network, IMS, etc.) connected through a mobile communication network (CDMA, W-CDMA, etc.), or an internet network connected via Wi-Fi. It may include. Specifically, the CDMA network may be connected to a data network through a PDSN (Packet Data Serving Node), and the W-CDMA network may be connected to a data network through a Gateway GPRS Support Node (GGSN). In addition, in an area such as a hot-spot, it may be connected to an internet network through short-range communication such as Wi-Fi.

When the communication network 200 according to an embodiment of the present invention receives a request for transmission of an image of an object from the terminal 100, the communication network 200 receives the corresponding image from the terminal 100 and transmits the image to the image search server 300. On the contrary, when the communication network 200 is requested to transmit the search result information from the image search server 300, the communication network 200 receives the search result information from the image search server 300 and transmits the search result information to the corresponding terminal 100.

The image search server 300 is a server that provides a search function using an image of an object. The image search server 300 receives additional information of each object from the additional information server 400, stores and updates the information in a database, and updates the object from the terminal 100 to the object. If a search is requested, the additional information of the corresponding object is searched and transmitted to the terminal 100.

In the case of a system for performing integrated recognition based on a terminal, the image search server 300 searches for additional information of an object when a search for an object recognized through the terminal 100 is requested and feeds back the search result to the terminal 100. It performs the function.

In the case of a system for performing integrated recognition based on the server, the image search server 300 recognizes the image of the object received from the terminal 100 in the image search server 300 to identify the type of the object and to optimize the type according to the type of the detected object. You can further perform the function of analyzing the object by applying the decoder of. Thereafter, the additional information of the corresponding object is searched and the search result is transmitted to the terminal 100. The detailed configuration thereof will be described in detail with reference to FIG. 4.

The additional information server 400 stores and manages additional information related to various objects and provides additional information of the object to the image search server 300 at regular intervals.

In addition, the additional information server 400 according to an embodiment of the present invention may operate an online shopping mall site for selling objects. In this case, the additional information server 400 sells and delivers the purchased goods in response to the purchase request of the terminal 100.

2 is a block diagram showing a detailed configuration of a terminal according to an embodiment of the present invention.

The terminal 100 illustrated in FIG. 2 has a structure in which an integrated recognition engine for automatically recognizing and reading an image of an object is implemented therein to perform terminal-based integrated recognition.

The terminal 100 may include an interface unit 110, a photographing means 120, a controller 130, an image recognition unit 140, a memory 150, and an integrated recognition engine 160.

The interface unit 110 connects to the image search server 300 of FIG. 1 or the additional information server 400 of FIG. 1 through a communication network 200 of FIG. 1 to interface communication with them.

The photographing means 120 photographs an object and generates an image thereof. In more detail, the photographing means 120 may include a camera, a web cam, or the like provided in the terminal 100.

The memory 150 may store an image photographed by the photographing means 120 and store information recognized by the image recognizer 140 and the integrated recognition engine 160.

The image recognizer 140 analyzes an image of the object generated by the photographing means 120 by an image recognition method based on feature extraction to determine the type of the object. Each object has an image feature point according to the type. For example, if the object is a bar code, there is unique feature information for identifying the shape of the bar code. If the object is a QR code, the unique feature information for identifying the shape of the QR code is provided. There is. As such, when the feature point is extracted from the image of the object through image recognition, the shape of each object may be determined according to the feature point information.

The type identification using the feature point information of the object is possible by using a database implemented in the integrated recognition engine 160.

The integrated recognition engine 160 includes feature point information and a decoder required to recognize an object. The feature point information and the decoder are classified according to the type of the object, and the feature point information is provided to the image recognition unit 140 to determine the type of the object, and the decoder is selectively driven according to the type of the object to read / read the object. Applies to recognition.

In particular, the integrated recognition engine 160 according to an embodiment of the present invention has a feature in that all the decoders according to the types of the objects are built so that the integrated recognition is possible in one terminal even if any object is input.

In addition, the integrated recognition engine 160 according to an embodiment of the present invention is characterized in that integrated recognition is possible even when two or more pieces of information are included in one object, that is, when both image information and barcode information are included. In this case, the image information and the barcode information can be recognized at the same time, but for the reliability of the search, the decoder having the highest recognition rate can be called first and recognized sequentially.

3 illustrates a detailed configuration of an integrated recognition engine according to an exemplary embodiment of the present invention.

As shown, the integrated recognition engine 160 may include a classifier DB 162 including unique feature information for identifying each object type, a decoder 164 for reading each object for each type, and the like. Include.

The classification DB 162 may include a barcode classification DB 1621 including unique feature point information of a barcode, a QR code classification DB 1622 including feature point information of a QR code, and a face (eye, nose, mouth, etc.) for face recognition. Face recognition classification DB (1623) including the feature point information for, NFC classification DB (1624) including the feature point information for the NFC tag, RFID classification DB (1625) including the feature point information for the RFID tag, unique to the OCR code OCR classification DB 1626 including feature point information, and other classification DB 1627 including feature point information for other codes. The unique feature point information for the barcode may use a shape consisting of a black bar and a white bar of the barcode, and the feature point information of the QR code may use a location identification code located at three corners. In addition, NFC tags, RFID tags, and OCR codes can also use their own forms.

The decoder 164 corresponds to the configuration of the classification DB 162, and includes a barcode decoder 1641, a QR code decoder 1644, a face recognition decoder 1643, an NFC tag decoder 1644, an RFID tag decoder 1645, OCR code decoder 1646, other decoder 1647, and the like.

In addition, when the type of the object is newly added, the integrated recognition engine 160 may build the newly added feature information and decoder in the existing configuration.

Referring back to FIG. 2, the controller 130 controls the operations of each unit as a whole and controls the transmission and reception of data through the interface unit 110. The controller 150 stores the image photographed by the photographing means 120 in the memory 150. In addition, when performing image recognition through the image recognition unit 140, the classification DB 162 built in the integrated recognition engine 160 may be provided to the image recognition unit 140.

Accordingly, the terminal 100 according to an embodiment of the present invention provides a convenient search service using the terminal by automatically recognizing an image of an object according to a type in its own device.

Here, the terminal 100 according to an embodiment of the present invention preferably generates an image of the object using the photographing means 120 and uses the image. However, the terminal 100 is not limited thereto, and the image of the object may be obtained through a predetermined web page or a separate device. Can be obtained.

4 is a block diagram illustrating a detailed configuration of an image search server according to an exemplary embodiment of the present invention.

The image retrieval server 300 shown in FIG. 4 is a structure in which the integrated recognition engine (160 of FIG. 2) described in the terminal configuration of FIG. 2 is built on a server other than the terminal (100 of FIG. 2). In this case, the image search server 300 may provide an integrated recognition service using the integrated recognition engine 350 to the terminal through a communication network including a WiFi wireless network.

The image search server 300 may be implemented to include an interface module 310, an image recognition module 320, a control module 330, an additional information management module 340, and an integrated recognition engine 350.

The interface module 310 interfaces the communication between the terminal connected through the communication network and the additional information server like the interface unit 110 of FIG. 1.

Like the image recognition unit 140 of FIG. 2, when the image of the object is received from the terminal, the image recognition module 320 determines the type of the object by performing image recognition based on feature extraction.

The integrated recognition engine 350 includes decoders and feature points necessary to recognize various objects. The feature point information is provided to the image recognition module 320 and applied to determine the type of the object, and the object is read by driving an optimal decoder 354 suitable for the object identified through the image recognition module 320.

In this case, the image search server 300 arranges the decoder 354 and the classification DB 352 built in the integrated recognition engine 350 in the order of the highest recognition rate, and sorts the search results in the order in which the search results are arranged. Can be.

The control module 330 controls their operations, and the additional information management module 340 receives, stores, and updates additional information of each object stored in the additional information server 400 of FIG. 1 at regular intervals.

On the other hand, the configuration and functions not described in detail above are the control unit (130 of FIG. 2), the image recognition unit (140 of FIG. 2), the integrated recognition engine (160 of FIG. 2) of the terminal (100 of FIG. 2) described in FIG. ) The same as the configuration and function of the) will not be repeated.

Therefore, as described above, in the embodiment of the present invention, an integrated recognition engine for recognizing an image of an object, identifying a type of an object, and driving a corresponding decoder to read an object according to the detected type is mounted on the terminal 100 as a client area. It may be a structure to call the necessary information to the server, or may be a structure that can be called by analyzing the image of the object is mounted in the image search server 300 in real time. Regardless of the structure, the search results through the image search may be arranged in order by ranking in the form of the best recognition rate for reliability.

Next, a process of serving using the integrated image retrieval system based on the above configuration will be described with reference to FIGS. 5 and 6.

5 is a flowchart illustrating a search process of a terminal when an integrated recognition engine is mounted in the terminal according to an embodiment of the present invention. For reference, it will be described in connection with the components of FIG. 2.

The terminal 100 inputs an image of an object photographed through the photographing means 120, a web page, or an image of an object obtained through a separate device (S10).

Then, the terminal 100 analyzes the characteristics of the image based on the classification DB of the integrated recognition engine 160 on the image of the input object (S20).

The analysis method applies a feature extraction based image recognition technology that extracts feature points from an image. For example, the image of the barcode may recognize that the object is in the form of a barcode by image recognition based on feature points.

The terminal 100 classifies the type of the object through the above analysis process (S30).

Then, the terminal 100 calls the corresponding decoder for reading the classified object and requests its driving (S40). That is, when a barcode is detected through image recognition based on a feature point from an image of an object, a barcode decoder for reading a barcode is called and driven, and when a feature point information about a face is detected, a facial recognition decoder for recognize a face is called and driven. can do.

Thereafter, the terminal 100 identifies the object by analyzing the image of the object with a decoder requested to be driven (S50).

The terminal 100 transmits the identified object information to the image search server and requests a search. When the terminal 100 receives additional information about the object from the image search server in response thereto, the terminal 100 displays the displayed object information.

6 is a flowchart illustrating a search process between a server and a terminal when an integrated recognition engine is mounted in a server according to an embodiment of the present invention. For reference, the operation of FIG. 6 will be described in connection with the components of FIG. 4.

When the image of the object photographed by the photographing means or the image of the object acquired through the web page or a separate device is input, the terminal 100 transmits the image of the input object to the image search server 300 (S110). , S120).

The image search server 300 analyzes the feature of the image through feature recognition based on the image of the object received from the terminal 100 (S130). This analysis process may be distinguished using the classification DB 352 and the image recognition module 320 built in the integrated recognition engine 350.

After the analysis, the image retrieval server 300 classifies the types of objects according to the features, calls the corresponding decoders for reading the classified objects, and automatically drives them (S140 and S150). The image search server 300 analyzes the image of the object with the driven decoder to identify the corresponding object (S160).

In addition, the image search server 300 searches for whether there is additional information on the identified object and transmits the search result to the corresponding terminal 100 (S170 and S180).

The terminal 100 displays and displays the search result received from the image search server 300, that is, additional information of the object (S190).

Through such a search process, the present invention can be utilized for a price comparison service in an internet shopping mall. In this case, if a user only has an image of an object, the user can use a shopping purchase service through comparing prices of products as well as products.

In addition, the present invention can be utilized for vision, graphics technology, network technology, DB construction technology related to pattern recognition.

The above description is merely illustrative of the present invention, and various modifications may be made by those skilled in the art without departing from the technical spirit of the present invention. Therefore, it can be applied to a wide range of technical fields such as vision, graphic technology, network technology, DB construction technology related to pattern recognition. Therefore, the embodiments disclosed in the specification of the present invention are not intended to limit the present invention. The scope of the present invention should be construed by the claims below, and all techniques within the scope equivalent thereto will be construed as being included in the scope of the present invention.

Conventional video search service has a limitation that it is individual because the recognition engine for barcode, QR code, face recognition, image recognition, etc. is mounted on each terminal individually, and the user has to request a request for direct recognition. However, in the present invention, when an image of an object is input, the type of the object is identified through image recognition and the decoder is selected and applied according to the identified type to read the object, thereby enabling integrated recognition of various objects, and identifying the type before object recognition. Therefore, the user can automatically recognize and search without having to request a recognition request. For this reason, if the technology included in the present invention is linked to a price comparison service or a shopping purchase service in an online shopping mall, the current image search service business may be activated.

100: terminal 200: communication network
300: image search server 400: additional information server
110: interface unit 120: photographing means
130: control unit 140: image recognition unit
150: memory 160: integrated recognition engine
162: classification DB 164: decoder
310: interface module 320: image recognition module
330: control module 340: additional information management module
350: integrated recognition engine

Claims (25)

A terminal that accesses a server through a communication network and requests a search for a desired object and receives the search result.
Photographing means for photographing the desired object to generate an image of the object;
An image recognition unit which analyzes an image of the object generated by the photographing means based on image recognition, and grasps the type of the object in advance;
Integrated recognition engine for automatically driving the readable decoder to recognize the image of the object according to the type of the object identified by the image recognition unit
Terminal for an integrated video search comprising a. The method of claim 1,
And the image recognition unit extracts a feature point from the image of the object based on image recognition and distinguishes the type of the object by the extracted feature point. The method of claim 2,
Characteristic point information that can distinguish the type of the object is stored in the integrated recognition engine for each type, the terminal for the integrated image search, characterized in that the reference data to determine the type of the object in the image recognition unit. The method of claim 1,
The integrated recognition engine includes all of the decoders readable according to the type of the object. The method according to claim 1 or 4,
The decoder may include a barcode decoder, a QR code decoder, a near field communication (NFC) decoder, a radio frequency identification (RFID) decoder, an optical character recognition (OCR) decoder, a face recognition decoder, and an image recognition decoder. Terminal for video search. The method of claim 1,
The object type may include one or more of an object or a person, a specific body part, a product number including a letter / number, a barcode, a QR code, an NFC tag, an RFID tag, and an OCR code. terminal. As a server for connecting to a terminal of a client through a communication network and receiving a search request for a desired object from the terminal, the server transmits the search result to the terminal.
An interface module for communicating with a terminal through the communication network;
An image recognition module that analyzes an image of the object based on image recognition based on image recognition when an image of the object is input through the interface module;
An integrated recognition engine for automatically driving a readable decoder to recognize an image of the object according to the type of the object identified by the image recognition module.
Image retrieval server comprising a. The method of claim 7, wherein
The image recognition module extracts a feature point based on image recognition from an image of the object and distinguishes the type of the object by the extracted feature point. The method of claim 2,
Characteristic point information that can distinguish the type of the object is stored in the integrated recognition engine for each type, the image retrieval server, characterized in that the reference data to determine the type of the object in the image recognition module. The method of claim 7, wherein
And the integrated recognition engine includes all of the decoders readable according to the type of the object. The method according to claim 7 or 10,
The decoder includes a barcode decoder, a QR code decoder, a near field communication (NFC) decoder, a radio frequency identification (RFID) decoder, an optical character recognition (OCR) decoder, a face recognition decoder, and an image recognition decoder. Search server. The method of claim 7, wherein
The object type may include an object or a person, a specific body part, a product number including a letter / number, etc., any one or more of a barcode, a QR code, an NFC tag, an RFID tag, and an OCR code. A system for providing a search service for a desired object by connecting a client terminal and a server through a communication network,
The terminal of the client requests the server to search for a desired object and is provided with a search result according to the request.
Before requesting a search to the server, photograph the desired object through a photographing means to generate an image of the object, and analyze the image of the generated object based on image recognition to determine the type of the object in advance, and identify the object And automatically driving a readable decoder according to the type of the image to recognize the image of the object. A system for providing a search service for a desired object by connecting a client terminal and a server through a communication network,
The server receives a search request for a desired object from the terminal of the client, and transmits a search result according to the request to the terminal of the client,
When an image of a desired object is input together with a search request of the client, the image of the object is analyzed based on image recognition to determine the type of the object in advance, and automatically drive a readable decoder according to the type of the identified object. And recognizing the image, and then performing a search based on the recognized object. The method according to claim 13 or 14,
And an additional information server that stores and manages additional information related to the object and provides the stored additional information according to a request of a terminal or a server of the client. A search service method of a terminal that accesses a server through a communication network and requests a search for a desired object and receives the search result.
Determining a type of the object in advance by analyzing characteristics of the image based on image recognition when an image of the object is input to the terminal;
The terminal automatically calling a readable decoder according to the type of the object to request driving;
The terminal recognizes the object by reading an image of the object by the decoder requested to drive;
The terminal receiving the search service by transmitting the recognized object to the server;
Integrated video retrieval service method comprising a. The method of claim 16,
The image for the object
Integrated image retrieval service method characterized in that the image is taken and generated by the photographing means provided in the terminal, or obtained from a web page or a separate device through a communication network. The method of claim 16,
Identifying the type of the object,
And extracting a feature point from the image of the object based on image recognition and comparing the extracted feature point with previously stored feature point information to distinguish the type of the object. The method of claim 16,
And a plurality of decoders are provided according to the type of the object. The method of claim 16,
The decoder may include a barcode decoder, a QR code decoder, a near field communication (NFC) decoder, a radio frequency identification (RFID) decoder, an optical character recognition (OCR) decoder, a face recognition decoder, and an image recognition decoder. Search service method. A search service method of a server that connects to a terminal of a client through a communication network and receives a search request for a desired object from the terminal.
When the image of the object is input to the server from the terminal, the server analyzing the characteristics of the image based on image recognition to determine the type of the object in advance;
The server automatically calling a readable decoder according to the type of the identified object to request driving;
The server recognizing an object by reading an image of the object by a decoder requested to be driven;
And searching for an object recognized by the server and transmitting a search result to the terminal. The method of claim 21,
The image for the object
Integrated image retrieval service method characterized in that the image is taken and generated by the photographing means provided in the terminal, or obtained from a web page or a separate device through a communication network. The method of claim 21,
Identifying the type of the object,
And extracting a feature point from the image of the object based on image recognition and comparing the extracted feature point with previously stored feature point information to distinguish the type of the object. The method of claim 21,
And a plurality of decoders are provided according to the type of the object. The method of claim 21,
The decoder may include a barcode decoder, a QR code decoder, a near field communication (NFC) decoder, a radio frequency identification (RFID) decoder, an optical character recognition (OCR) decoder, a face recognition decoder, and an image recognition decoder. Search service method.

Images