CN103489008B - Image product information extracting method and device - Google Patents
Image product information extracting method and device Download PDFInfo
- Publication number
- CN103489008B CN103489008B CN201210195818.4A CN201210195818A CN103489008B CN 103489008 B CN103489008 B CN 103489008B CN 201210195818 A CN201210195818 A CN 201210195818A CN 103489008 B CN103489008 B CN 103489008B
- Authority
- CN
- China
- Prior art keywords
- product
- information
- database
- characteristic information
- characteristic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/532—Query formulation, e.g. graphical querying
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Processing Or Creating Images (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of image product information extracting method and device, methods described includes step：Obtain the target area that user selects in image；Extract the characteristic information of the target area；In product database, the product information matched with the characteristic information is obtained.It is of the invention effectively to utilize trademark information, color, pattern, texture present in picture etc., provide the user product detail information present in picture, avoid the trouble that user is brought by web search product information, make obtaining product information more quick and easy, effectively improve the pleasant feeling of Consumer's Experience.
Description
Technical field
The present invention relates to intelligent terminal technical field, image product information extracting method and device are related specifically to.
Background technology
With becoming increasingly popular for smart mobile phone, user has been not limited only to simply to scene for the requirement of the photo of capture
A kind of record, prior aspect is the useful information excavated in image that can be profound, so as to meet specific demand.It is logical
In the case of often, when user sees the product for having oneself interested on photo, it is necessary to be scanned for by internet, product is searched
Relevant information.Due to when carrying out query search, it is necessary to take a substantial amount of time, be that user brings great inconvenience, reduction
Consumer's Experience.
The content of the invention
The main object of the present invention is offer a kind of easily and efficiently image product information extracting method and device.
The present invention proposes a kind of image product information extracting method, including step：
Obtain the target area that user selects in image；
Extract the characteristic information of the target area；
In product database, the product information matched with the characteristic information is obtained.
Preferably, the step of characteristic information of the extraction target area includes：
The target area is expanded into complete object region, the complete object region is the target area and its week
The connected region summation of side approximate region；
Extract the characteristic information in the complete object region；
Preferably, the characteristic information includes trade mark characteristic information, and the product database includes product brand database；
It is described in product database, obtain matched with the characteristic information product information the step of include：
In the product brand database, the product information matched with the trade mark characteristic information is obtained.
Preferably, the characteristic information includes style characteristics information, and the product database includes product pattern database；
It is described in product database, obtain matched with the characteristic information product information the step of include：
In the product pattern database, the product information with the style characteristics information matches is obtained.
Preferably, described in product database, the step of obtaining the product information matched with the characteristic information includes：
Characteristic information input neural network learning machine is completed into characteristic matching, and output is matched with the characteristic information
Product information, the neural network learning machine for through being stored in the product database product information training after nerve net
Network.
The present invention also proposes a kind of image product information extracting device, including：
Acquisition module, for obtaining the target area that user selects in image；
Characteristic extracting module, the characteristic information for extracting the target area；
Matching module, in product database, obtaining the product information matched with the characteristic information.
Preferably, the characteristic extracting module includes：
Expanding element, for the target area to be expanded into complete object region, the complete object region is described
Target area and its connected region summation of periphery approximate region；
Extraction unit, the characteristic information for extracting the complete object region；
Preferably, the characteristic information includes trade mark characteristic information, and the product database includes product brand database；
The matching module includes：
Trade mark matching unit, in the product brand database, obtaining what is matched with the trade mark characteristic information
Product information.
Preferably, the characteristic information includes style characteristics information, and the product database includes product pattern database；
The matching module includes：
Pattern matching unit, in the product pattern database, obtaining and the style characteristics information matches
Product information.
Preferably, the matching module is additionally operable to：
Characteristic information input neural network learning machine is completed into characteristic matching, and output is matched with the characteristic information
Product information, the neural network learning machine for through being stored in the product database product information training after nerve net
Network.
It is of the invention effectively to utilize trademark information, color, pattern, texture present in picture etc., provide the user in picture
The product detail information of presence, it is to avoid the trouble that user is brought by web search product information, makes obtaining product information
It is more quick and easy, effectively improve the pleasant feeling of Consumer's Experience.
Brief description of the drawings
Fig. 1 is the flow chart of image product information extracting method in first embodiment of the invention；
Fig. 2 is the flow chart of image product information extracting method in second embodiment of the invention；
Fig. 3 is the flow chart of image product information extracting method in third embodiment of the invention；
Fig. 4 is the flow chart of image product information extracting method in fourth embodiment of the invention；
Fig. 5 is the flow chart of image product information extracting method in fifth embodiment of the invention；
Fig. 6 is the flow chart of image product information extracting method in sixth embodiment of the invention；
Fig. 7 is the structural representation of image product information extracting device in seventh embodiment of the invention；
Fig. 8 is the structural representation of image product information extracting device in eighth embodiment of the invention；
Fig. 9 is the structural representation of image product information extracting device in ninth embodiment of the invention；
Figure 10 is the structural representation of image product information extracting device in tenth embodiment of the invention.
The realization, functional characteristics and advantage of the object of the invention will be described further referring to the drawings in conjunction with the embodiments.
Embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
As shown in figure 1, Fig. 1 is the flow chart of image product information extracting method in first embodiment of the invention, the implementation
The image product information extracting method that example is mentioned, including：
Step S101, obtains the target area that user selects in image；
In the present embodiment, product of interest is selected in the picture that user is shown using touch-screen on intelligent terminal, is generated
Target area, the target area can be certain part, the cuff of such as dress, collar, clothing angle of product of interest
Deng.
Step S102, extracts the characteristic information of target area；
The characteristic information of the present embodiment may include trade mark, color, texture, style etc..The purpose that Product Feature Information is extracted
It is, the feature quantity of primary products is very big, i.e., original sample is in a higher dimensional space, for the ease of subsequent analysis, needs
The feature in this higher dimensional space is described with the feature of lower dimensional space by way of mapping or converting, is conducive to simplifying production
Product acquisition of information flow, improves the treatment effeciency of product information matching.
Step S103, in product database, obtains the product information matched with characteristic information；
Step S104, shows product information.
The present embodiment is set up in intelligent terminal product database, such as including product brand database and product pattern
Database, in advance stores product brand parameter, product pattern parameter, Business Information parameter etc. to product number as product information
According in storehouse, during information matches, the product information matched with characteristic information is searched in product database, effectively utilizes and is deposited in picture
The information such as trademark information, color, pattern, texture, provide the user product detail information present in picture, or recommend to arrogate to oneself
The Business Information of long such product, it is to avoid the trouble that user is brought by web search product information, obtains product information
Take more quick and easy, effectively improve the pleasant feeling of Consumer's Experience.In addition, the present embodiment can also obtain product information after,
Intelligent terminal is linked to by network on the webpage associated with product information, is easy to the further query search of user interested
The other information of product.
As shown in Fig. 2 Fig. 2 is the flow chart of image product information extracting method in second embodiment of the invention.
Step S201, obtains the target area that user selects in image；
Step S202, complete object region is expanded to by target area；
Step S203, extracts the characteristic information in complete object region；
The complete object region of the present embodiment is the connected region summation of target area and its periphery approximate region, for example,
Target area is cuff, collar or the clothing angle of dress, then in extension, target area is expanded into one integral piece clothes, as
Complete object region.
Step S204, in product database, obtains the product information matched with characteristic information；
Step S205, shows product information.
The present embodiment effectively using trademark information, color, pattern, texture present in picture etc., provides the user picture
Present in product detail information, it is to avoid the trouble that user is brought by web search product information, obtain product information
Take more quick and easy, effectively improve the pleasant feeling of Consumer's Experience.
As shown in figure 3, Fig. 3 is the flow chart of image product information extracting method in third embodiment of the invention.
Step S301, obtains the target area that user selects in image；
Step S302, complete object region is expanded to by target area；
Step S303, extracts the trade mark characteristic information in complete object region；
The characteristic information of the present embodiment includes trade mark characteristic information, and product brand is typically distributed across a rectangle after formatting
In region, query search can be carried out to trademark information using rank scanning method.
Step S304, in product brand database, obtains the product information matched with trade mark characteristic information；
Step S305, shows product information.
The product database of the present embodiment includes product brand database, i.e., store big in product brand database in advance
Trademark information data are measured, using the trade mark characteristic information extracted in picture as depositing in characteristic parameter, with product brand database
The trademark information data of storage are matched, and by corresponding to the trademark information data of the matching stored in product brand database
Product information output display, it is to avoid the trouble that user is brought by web search product information, makes obtaining product information more
Plus it is quick and easy, effectively improve the pleasant feeling of Consumer's Experience.
As shown in figure 4, Fig. 4 is the flow chart of image product information extracting method in fourth embodiment of the invention.
Step S401, obtains the target area that user selects in image；
Step S402, complete object region is expanded to by target area；
Step S403, extracts the style characteristics information in complete object region；
The characteristic information of the present embodiment includes style characteristics information, such as the color of product, texture, style.
Step S404, in product pattern database, obtains the product information with style characteristics information matches；
Step S405, shows product information.
The product database of the present embodiment includes product pattern database, i.e., store big in product brand database in advance
Product colour, texture, style of amount etc., and consider the product style information number formed after color, texture, style combination
According to regarding the style characteristics information extracted in picture as the style information stored in characteristic parameter, with product pattern database
Data are matched, including to color, texture, style multiple combinations, and by the matching stored in product pattern database
Product information output display corresponding to style information data, it is to avoid the fiber crops that user is brought by web search product information
It is tired, make obtaining product information more quick and easy, effectively improve the pleasant feeling of Consumer's Experience.
As shown in figure 5, Fig. 5 is the flow chart of image product information extracting method in fifth embodiment of the invention.
Step S501, obtains the target area that user selects in image；
Step S502, complete object region is expanded to by target area；
Step S503, scans complete target area, and the inquiry trade mark characteristic information in scanning result；
Step S504, judges whether to inquire trade mark characteristic information；If it is, performing step 505；If it is not, then holding
Row step 507；
Step S505, extracts the trade mark characteristic information in complete object region；
Step S506, in product brand database, obtains the product information matched with trade mark characteristic information, and perform step
Rapid S509；
Step S507, extracts the style characteristics information in complete object region；
Step S508, in product pattern database, obtains the product information with style characteristics information matches, and perform step
Rapid S509；
Step S509, shows product information.
The present embodiment considers that product brand is typically distributed across in a rectangular area after formatting, and can be swept using ranks
Retouch method to trade mark characteristic information carry out query search, trade mark inquiry compared with pattern inquiry is more prone to, processing speed faster, therefore
The trade mark inquiry of product is carried out first.But due to and not all product in can have trade mark characteristic information, can not obtain
In the case of trade mark characteristic information, then using pattern inquiry by the way of, be user recommend it is same or like as product information.Business
The cooperation that mark inquiry is inquired about with pattern, makes the acquisition of product information more comprehensive, the product information accuracy rate obtained is higher, has
Effect improves Consumer's Experience.
As shown in fig. 6, Fig. 6 is the flow chart of image product information extracting method in sixth embodiment of the invention.
Step S601, obtains the target area that user selects in image；
Step S602, complete object region is expanded to by target area；
Step S603, extracts the characteristic information in complete object region；
Step S604, inputs neural network learning machine by characteristic information and completes characteristic matching, and export and characteristic information
The product information matched somebody with somebody；
Step S605, shows product information.
The neural network learning machine of the present embodiment is the nerve net after the product information training through being stored in product database
Network, pre-establishes neutral net, the merchandise news according to present in database, trains corresponding neutral net, obtains nerve net
Network learning machine.For example, selection BP neural network（Back Propagation）, its topological structure include input layer（input）, it is hidden
Layer (hide layer) and output layer (output layer), can learn and store substantial amounts of input-output mode map relation,
The math equation of this mapping relations is described without disclosing in advance；Its learning rules are to use steepest descent method, by anti-
Carry out the continuous weights and threshold value for adjusting network to propagating, make the error sum of squares of network minimum.In order to ensure the accuracy of data,
Product database and neural network learning machine can be stored in high in the clouds, and determined according to goods marks, commodity modal shift situation
Phase updates high in the clouds data.
As shown in fig. 7, Fig. 7 is the structural representation of image product information extracting device in seventh embodiment of the invention, should
A kind of image product information extracting device that embodiment is mentioned, including：
Acquisition module 10, for obtaining the target area that user selects in image；
Characteristic extracting module 20, the characteristic information for extracting target area；
Matching module 30, in product database, obtaining the product information matched with characteristic information.
In the present embodiment, product of interest is selected in the picture that user is shown using touch-screen on intelligent terminal, is generated
Target area, and export to acquisition module 10, the target area can be certain part, such as one clothing of product of interest
Cuff, collar, clothing angle of clothes etc..The characteristic information extraction from target area of characteristic extracting module 20, this feature information may include
Trade mark, color, texture, style etc..The purpose that Product Feature Information is extracted is that the feature quantity of primary products is very big, i.e., former
Beginning sample is in a higher dimensional space, for the ease of subsequent analysis, need to be empty by this higher-dimension by way of mapping or converting
Between in feature described with the feature of lower dimensional space, be conducive to simplifying obtaining product information flow, improve product information matching
Treatment effeciency.Due to being pre-established with product database in intelligent terminal, such as including product brand database and product sample
Formula database, in advance stores product brand parameter, product pattern parameter, Business Information parameter etc. to product as product information
In database, during information matches, matching module 30 searches the product information matched with characteristic information in product database, effectively
Using information such as trademark information present in picture, color, pattern, textures, product present in picture is provided the user detailed
Information, or recommend to be good at the Business Information of such product, it is to avoid the trouble that user is brought by web search product information,
Make obtaining product information more quick and easy, effectively improve the pleasant feeling of Consumer's Experience.In addition, the present embodiment can also obtained
Take after product information, intelligent terminal is linked to by network on the webpage associated with product information, is easy to user further
The other information of query search product of interest.
The matching module 30 of the embodiment of the present invention is additionally operable to, and characteristic information is inputted into neural network learning machine completes feature
Match somebody with somebody, and export the product information matched with characteristic information, neural network learning machine is the product letter through being stored in product database
Neutral net after breath training.
The neural network learning machine that the matching module 30 of the present embodiment is used is believed for the product through being stored in product database
Neutral net after breath training, pre-establishes neutral net, and the merchandise news according to present in database trains corresponding nerve
Network, obtains neural network learning machine.For example, selection BP neural network（Back Propagation）, its topological structure includes
Input layer（input）, hidden layer (hide layer) and output layer (output layer), can learn and store substantial amounts of input-
Output mode mapping relations, the math equation of this mapping relations is described without disclosing in advance；Its learning rules are to use
Steepest descent method, the weights and threshold value of network are constantly adjusted by backpropagation, make the error sum of squares of network minimum.In order to
Ensure the accuracy of data, product database and neural network learning machine can be stored in high in the clouds, and according to goods marks, business
Product modal shift situation regularly updates high in the clouds data.
As shown in figure 8, Fig. 8 is the structural representation of image product information extracting device in eighth embodiment of the invention.It is special
Levying extraction module 20 includes：
Expanding element 21, for target area to be expanded into complete object region, complete object region be target area and
The connected region summation of its periphery approximate region；
Extraction unit 22, the characteristic information for extracting complete object region；
The expanding element 21 of the present embodiment has expanded to the connected region summation of target area and its periphery approximate region
Whole target area, for example, target area is cuff, collar or the clothing angle of dress, then in extension, target area is extended
For one integral piece clothes, as complete object region, using extraction unit 22 extract trademark information present in picture, color, pattern,
Texture eigenvalue information parameter, provide the user product detail information present in picture, it is to avoid user passes through web search
The trouble that product information is brought, makes obtaining product information more quick and easy, effectively improves the pleasant feeling of Consumer's Experience.
As shown in figure 9, Fig. 9 is the structural representation of image product information extracting device in ninth embodiment of the invention.
Include with module 30：
Trade mark matching unit 31, the product letter matched in product brand database, obtaining with trade mark characteristic information
Breath.
The characteristic information of the present embodiment includes trade mark characteristic information, and product brand is typically distributed across a rectangle after formatting
In region, it can be realized using extraction unit 22 to target area or complete object region procession scan method to trade mark
The query search of information.Product database includes product brand database, i.e., store a large amount of in product brand database in advance
Trademark information data, using trade mark matching unit 31 using the trade mark characteristic information extracted in picture as characteristic parameter, with production
The trademark information data stored in product trademark database are matched, and by the trade mark of the matching stored in product brand database
Product information output display corresponding to information data, it is to avoid the trouble that user is brought by web search product information,
Make obtaining product information more quick and easy, effectively improve the pleasant feeling of Consumer's Experience.
As shown in Figure 10, Figure 10 is the structural representation of image product information extracting device in tenth embodiment of the invention.
Matching module 30 includes：
Pattern matching unit 32, the product in product pattern database, obtaining with style characteristics information matches is believed
Breath.
The characteristic information of the present embodiment includes style characteristics information, such as the color of product, texture, style, can adopt
Style information query search is carried out to target area or complete object region with extraction unit 22.Product database includes product sample
Formula database, i.e., in product brand database store substantial amounts of product colour, texture, style etc. in advance, and consider face
The product style information data that are formed after color, texture, style combination, using pattern matching unit 32 by the sample extracted in picture
Formula characteristic information is matched as characteristic parameter with the style information data stored in product pattern database, including to face
Color, texture, the multiple combinations of style, and by the production corresponding to the style information data of the matching stored in product pattern database
Product information output display, it is to avoid the trouble that user is brought by web search product information, makes obtaining product information more
It is quick and easy, effectively improve the pleasant feeling of Consumer's Experience.
In addition, the present embodiment considers that product brand is typically distributed across in a rectangular area after formatting, can be first
Query search is carried out to trade mark characteristic information using the rank scanning method of extraction unit 22, trade mark inquiry is inquired about more compared with pattern
Easily, processing speed is faster.But due to and not all product in can have trade mark characteristic information, can not in extraction unit 22
Obtain trade mark characteristic information in the case of, then using pattern inquiry by the way of, be user recommend it is same or like as product letter
Breath.The cooperation that trade mark inquiry is inquired about with pattern, makes the acquisition of product information more comprehensive, the product information accuracy rate obtained is more
Height, effectively improves Consumer's Experience.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the scope of the invention, it is every to utilize
Equivalent structure or equivalent flow conversion that description of the invention and accompanying drawing content are made, or directly or indirectly it is used in other correlations
Technical field, be included within the scope of the present invention.
Claims (8)
1. a kind of image product information extracting method, it is characterised in that including step：
Obtain the target area that user selects in image；
Extract the characteristic information of the target area；
In product database, the product information matched with the characteristic information is obtained；
Wherein, in the product database, obtain the product information matched with the characteristic information and specifically include：
Carried out the characteristic information extracted as the characteristic information data stored in characteristic parameter, with the product database
Match somebody with somebody, to obtain the product information；
The step of characteristic information of the extraction target area, includes：
The target area is expanded into complete object region, the complete object region is that the target area and its periphery are near
Like the connected region summation in region；
Extract the characteristic information in the complete object region.
2. image product information extracting method according to claim 1, it is characterised in that the characteristic information includes trade mark
Characteristic information, the product database includes product brand database；
It is described in product database, obtain matched with the characteristic information product information the step of include：
In the product brand database, the product information matched with the trade mark characteristic information is obtained.
3. image product information extracting method according to claim 1, it is characterised in that the characteristic information includes pattern
Characteristic information, the product database includes product pattern database；
It is described in product database, obtain matched with the characteristic information product information the step of include：
In the product pattern database, the product information with the style characteristics information matches is obtained.
4. the image product information extracting method according to any one of claims 1 to 3, it is characterised in that described in product
In database, the step of obtaining the product information matched with the characteristic information includes：
Characteristic information input neural network learning machine is completed into characteristic matching, and exports the production matched with the characteristic information
Product information, the neural network learning machine is the neutral net after the product information training through being stored in the product database.
5. a kind of image product information extracting device, it is characterised in that including：
Acquisition module, for obtaining the target area that user selects in image；
Characteristic extracting module, the characteristic information for extracting the target area；
Matching module, in product database, obtaining the product information matched with the characteristic information；
Wherein, the matching module specifically for：
Carried out the characteristic information extracted as the characteristic information data stored in characteristic parameter, with the product database
Match somebody with somebody, to obtain the product information；
The characteristic extracting module includes：
Expanding element, for the target area to be expanded into complete object region, the complete object region is the target
Region and its connected region summation of periphery approximate region；
Extraction unit, the characteristic information for extracting the complete object region.
6. image product information extracting device according to claim 5, it is characterised in that the characteristic information includes trade mark
Characteristic information, the product database includes product brand database；
The matching module includes：
Trade mark matching unit, in the product brand database, obtaining the product matched with the trade mark characteristic information
Information.
7. image product information extracting device according to claim 5, it is characterised in that the characteristic information includes pattern
Characteristic information, the product database includes product pattern database；
The matching module includes：
Pattern matching unit, in the product pattern database, obtaining the product with the style characteristics information matches
Information.
8. the image product information extracting device according to any one of claim 5 to 7, it is characterised in that the matching mould
Block is additionally operable to：
Characteristic information input neural network learning machine is completed into characteristic matching, and exports the production matched with the characteristic information
Product information, the neural network learning machine is the neutral net after the product information training through being stored in the product database.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210195818.4A CN103489008B (en) | 2012-06-14 | 2012-06-14 | Image product information extracting method and device |
| PCT/CN2012/081363 WO2013185420A1 (en) | 2012-06-14 | 2012-09-13 | Method and device for extracting information of image product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210195818.4A CN103489008B (en) | 2012-06-14 | 2012-06-14 | Image product information extracting method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103489008A CN103489008A (en) | 2014-01-01 |
| CN103489008B true CN103489008B (en) | 2017-07-28 |
Family
ID=49757466
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210195818.4A Active CN103489008B (en) | 2012-06-14 | 2012-06-14 | Image product information extracting method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN103489008B (en) |
| WO (1) | WO2013185420A1 (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104778170A (en) * | 2014-01-09 | 2015-07-15 | 阿里巴巴集团控股有限公司 | Method and device for searching and displaying commodity image |
| CN103984711B (en) * | 2014-05-05 | 2018-05-18 | 华为技术有限公司 | A kind of information search method and server |
| US11314826B2 (en) | 2014-05-23 | 2022-04-26 | Samsung Electronics Co., Ltd. | Method for searching and device thereof |
| CN110825928A (en) * | 2014-05-23 | 2020-02-21 | 三星电子株式会社 | Searching method and device |
| CN104021229B (en) * | 2014-06-25 | 2017-07-25 | 厦门大学 | A kind of shape representation and matching process for trademark image retrieval |
| CN105138610A (en) * | 2015-08-07 | 2015-12-09 | 深圳码隆科技有限公司 | Image element based image feature value prediction method and apparatus |
| CN105867855A (en) * | 2015-12-04 | 2016-08-17 | 乐视致新电子科技（天津）有限公司 | Display method and equipment of virtual equipment image |
| CN106021317A (en) * | 2016-05-06 | 2016-10-12 | 长沙市麓智信息科技有限公司 | Product infringement analysis auxiliary system and auxiliary method thereof |
| CN106021328A (en) * | 2016-05-06 | 2016-10-12 | 长沙市麓智信息科技有限公司 | A product infringement analysis system and an analysis method thereof |
| CN107665441B (en) * | 2016-07-27 | 2021-06-29 | 北京嘀嘀无限科技发展有限公司 | Accurate product recommendation method and device based on coordinate axis |
| CN107169028A (en) * | 2017-04-13 | 2017-09-15 | 南京信息工程大学 | Poster searching method and user terminal |
| CN107609057B (en) * | 2017-08-25 | 2020-12-22 | 百度在线网络技术（北京）有限公司 | Method and device for acquiring character data of trademark image |
| CN107729900B (en) * | 2017-09-15 | 2021-04-27 | 广州唯品会研究院有限公司 | Method and equipment for completing input information completion by utilizing picture attribute extraction |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101847161A (en) * | 2010-06-02 | 2010-09-29 | 苏州搜图网络技术有限公司 | Method for searching web pages and establishing database |
| CN102063436A (en) * | 2009-11-18 | 2011-05-18 | 腾讯科技（深圳）有限公司 | System and method for realizing merchandise information searching by using terminal to acquire images |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5578077B2 (en) * | 2008-08-08 | 2014-08-27 | 株式会社ニコン | Search support system, search support method, and search support program |
-
2012
- 2012-06-14 CN CN201210195818.4A patent/CN103489008B/en active Active
- 2012-09-13 WO PCT/CN2012/081363 patent/WO2013185420A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102063436A (en) * | 2009-11-18 | 2011-05-18 | 腾讯科技（深圳）有限公司 | System and method for realizing merchandise information searching by using terminal to acquire images |
| CN101847161A (en) * | 2010-06-02 | 2010-09-29 | 苏州搜图网络技术有限公司 | Method for searching web pages and establishing database |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103489008A (en) | 2014-01-01 |
| WO2013185420A1 (en) | 2013-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103489008B (en) | Image product information extracting method and device | |
| JP7136156B2 (en) | Search support system, search support method and program | |
| CN103559636B (en) | Restaurant management system based on cloud computing and intelligent analysis | |
| CN101206749B (en) | Merchandise recommending system and method using multi-path image retrieval module thereof | |
| CN103412938B (en) | A kind of commodity price-comparing method extracted based on picture interactive multiobjective | |
| CN110035314A (en) | Methods of exhibiting and device, storage medium, the electronic device of information | |
| CN107209962A (en) | For the method for the 3D virtual body models for generating the people combined with 3D clothes images, and related device, system and computer program product | |
| CN106447388A (en) | Method and system for recommending dishes | |
| CN104281864B (en) | A kind of method and apparatus for generating Quick Response Code | |
| CN106649383A (en) | Clothes management method and system | |
| CN106294420B (en) | The method and device of business object collocation information is provided | |
| CN105117924A (en) | Personalized commodity recommendation system | |
| CN103186666B (en) | Method, device and equipment for searching based on favorites | |
| CN104318446A (en) | Virtual fitting method and system | |
| CN107122447A (en) | The network searching system and control method of a kind of multi-data source fusion based on preference | |
| CN108960985A (en) | Body parameter generation method and online shopping item recommendation method based on image or video | |
| CN105913297A (en) | Fitting recommendation method based on big data and system | |
| CN109416693A (en) | Server unit, terminal installation and information processing method | |
| JP2016071537A (en) | Commodity recommendation apparatus and commodity recommendation method | |
| CN107092435A (en) | Recognized based on brand logo and interactive method and system | |
| US20190304008A1 (en) | Color palette guided shopping | |
| CN106030578A (en) | Search system, server system, and method for controlling search system and server system | |
| CN106557489A (en) | A kind of dress ornament searching method based on mobile terminal | |
| US20220405825A1 (en) | Flowerbed sales order system, flowerbed sales order program, and flowerbed sales order method | |
| KR101345119B1 (en) | System and method for generating and diagonizing image concept identity code, and system for providing information and method for providing services thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |