CN105631461A - Image recognition system and method - Google Patents
Image recognition system and method Download PDFInfo
- Publication number
- CN105631461A CN105631461A CN201610069999.4A CN201610069999A CN105631461A CN 105631461 A CN105631461 A CN 105631461A CN 201610069999 A CN201610069999 A CN 201610069999A CN 105631461 A CN105631461 A CN 105631461A
- Authority
- CN
- China
- Prior art keywords
- image
- information
- module
- client
- classification
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- 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
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9038—Presentation of query results
Abstract
The invention relates to an image recognition system, and the system comprises a server control end. The server control end is connected with an image input module which is used for inputting an image through employing a client network; a display module which is used for displaying the image; a storage module which is used for storing the image, and storing the structure of the image after classification and recognition; an image classification and recognition module which comprises a plurality of image recognizers; a result extraction module which is used for extracting the image classification information matched with corresponding image feature data from a database in the corresponding image recognizer according to the type of a needed image; and a server providing module which is used for obtaining a preset image corresponding to the image type according to the type of the needed image. The system employs the plurality of image recognizers to carry out the feature extraction of a to-be-recognized image, and can obtain the recognition result of different image types for the same image. Compared with a conventional image recognition method, the method is higher in recognition efficiency.
Description
Technical field
The application relates to image identification technical field, especially relates to a kind of image identification system.
Background technology
Traditional image-recognizing method, the content generally only for some specific area is identified. Such as, or it is identified only for face, or is identified only for word or bar code. In traditional image-recognizing method, also have and the zones of different in piece image is identified, obtain the recognition result of different field. Such as may identify which out the features such as the object in piece image, face, word, carry out characteristic matching for different fields, the recognition result that then display of the zones of different in piece image is corresponding.
But, in these traditional image identification method, if the content only for some specific area is identified, then which field image to be identified is to require user to know, and often user do not know about the information of image before image recognition. And in traditional method that the zones of different in piece image is identified, for some region of image, often also can only provide single recognition result, such as, for the photo of a Liu De China, user may want to understand his micro-blog information, it may also be desirable to understands his film etc., therefore these traditional image identification method, its recognition efficiency is not high.
Summary of the invention
For the deficiencies in the prior art in background technology, the application provides a kind of image identification system, adopt multiple image recognizer that image to be identified is carried out feature extraction, obtain the image feature data of corresponding different images kind, adopt multiple image recognizer to carry out image recognition for different image kinds.
To achieve these goals, technical scheme is as follows.
A kind of image identification system, including server controls end, described server controls end is connected to:
Image input module: in order to input picture, utilize the network input picture of client, this image sources shoots in mobile phone or panel computer;
Display module: in order to display for image, shown for image recognition result;
Storage module: the image for input stores, and is stored for the structure after image Classification and Identification, and other modules can be easy to carry out image data extraction;
Image Classification and Identification module, comprises multiple image recognizer, for obtaining the image in storage module, the image extracted in storage module is carried out feature extraction, obtains the image feature data of corresponding different images kind, and is stored in different image recognizer;
Result extraction module, for the image classification information mated with corresponding image feature data from correspondence with extraction in the data base image recognizer according to required image kind;
Service providing module, for obtaining the image corresponding with described image kind preset according to required image kind, and mated display by the web page interlinkage being connected with service providing module or smart mobile phone end, and can receive corresponding picture appraisal information, display screen or touch screen by being connected with display module can be shown in display module simultaneously.
Further, service providing module is additionally operable to from described information on services to extract service type information; Described system also includes client, and described client includes for information of being classified by the described image display module that carry out represent corresponding to service classification information.
Further, described service type information comprises the link of the service providing page of correspondence; Described client also includes:
Page jump module, for obtaining the click commands of described service type information, jumps to the service providing page corresponding with described service type information according to the link of described service providing page.
Described display module is additionally operable to the classification of described image that information is corresponding with information on services represents.
In above-mentioned image identification system and method, adopt multiple image recognizer that the image in image input module is carried out feature extraction, obtain the image feature data of corresponding different images kind, also can extract the image classification information of correspondence from the data base of different images kind, owing to adopting multiple image recognizer to carry out image recognition for different image kinds, same image can obtain the recognition result of different images kind, and relative to traditional image-recognizing method, its recognition efficiency is higher.
Further, image also can be classified by display module, and information is corresponding with information on services to be represented; Display module can directly represent the image classification information of corresponding different images kind on the image in image input module, when the image classification information of some image kind is selected, then in the dialog box ejected, represent the information on services of this image classification information and correspondence thereof.
Further, above-mentioned different image kind comprises books classification, CD classification, LOGO classification, poster classification, advertisement classification, personage's classification, clothing classification etc. The image feature data of corresponding different images kind then comprises books characteristic, laser disc characteristic, LOGO characteristic, poster characteristic, advertisement characteristic data, character features data, garment feature data etc.
Above-mentioned image-recognizing method, comprises the following steps: obtains the image in image input module, is stored, and shown in display module in storage module; Adopt multiple image recognizer that the image in described image input module is carried out feature extraction, obtain the image feature data of corresponding different images kind; From corresponding data base, the image classification information with corresponding image feature data coupling is extracted according to described image kind.
Additionally, in the method, it is also possible to utilize the image input device in client for obtaining image, and the image in image input device is uploaded onto the server control end by network; The image that image input module obtains passes through the locally stored image of client or carries out, by the image input device of client, the image obtained of taking pictures in real time; Now, image identification system comprises server controls end and client, service end receives the image in the image input module that image input module is uploaded, feature extraction is carried out by multiple image recognizer of corresponding different images kind, obtain the image feature data of corresponding different images kind, then the image feature data to these image kinds obtained, matched image classification information is extracted from the data base of correspondence image kind, the image classification information extracted may return to client, is represented by the display module of client; Or the image recognizer in server controls end is extended, mounts more image recognizer or original image recognizer is updated, to provide the image recognition of larger class, use flexible.
In this situation, server controls end is searched and the information on services of image classification information matches from client by service providing module, and the information on services found or the service type information therefrom extracted are back to client, by display module, by information on services or service type information and image classification, information is corresponding represents; Client only provides interface to server controls end, and therefore, server controls end can be extended by increasing the more interface service type to providing, and to provide the information on services of larger class, is effectively increased the recognition efficiency of image recognition.
This beneficial effect of the invention is in that: in the present invention, adopt multiple image recognizer that image to be identified is carried out feature extraction, obtain the image feature data of corresponding different images kind, also can extract the summary info of correspondence from the data base of different images kind, owing to multiple image recognizer can be adopted to carry out image recognition for different image kinds, same image can obtain the recognition result of different images kind, relative to traditional image-recognizing method, its recognition efficiency is higher, uses convenient.
Accompanying drawing explanation
Fig. 1 is the module rack composition of used system in the embodiment of the present invention.
Detailed description of the invention
Below in conjunction with drawings and Examples, the specific embodiment of the present invention is described, in order to be better understood from the present invention.
Embodiment
Image identification system as shown in Figure 1, including server controls end, described server controls end is connected to:
Image input module: in order to input picture, utilize the network input picture of client, this image sources shoots in mobile phone or panel computer;
Display module: in order to display for image, shown for image recognition result;
Storage module: the image for input stores, and is stored for the structure after image Classification and Identification, and other modules can be easy to carry out image data extraction;
Image Classification and Identification module, comprises multiple image recognizer, for obtaining the image in storage module, the image extracted in storage module is carried out feature extraction, obtains the image feature data of corresponding different images kind, and is stored in different image recognizer;
Result extraction module, for the image classification information mated with corresponding image feature data from correspondence with extraction in the data base image recognizer according to required image kind;
Service providing module, for obtaining the image corresponding with described image kind preset according to required image kind, and mated display by the web page interlinkage being connected with service providing module or smart mobile phone end, and can receive corresponding picture appraisal information, display screen or touch screen by being connected with display module can be shown in display module simultaneously.
Further, service providing module is additionally operable to from described information on services to extract service type information; Described system also includes client, and described client includes for information of being classified by the described image display module that carry out represent corresponding to service classification information.
Further, described service type information comprises the link of the service providing page of correspondence; Described client also includes:
Page jump module, for obtaining the click commands of described service type information, jumps to the service providing page corresponding with described service type information according to the link of described service providing page.
Described display module is additionally operable to the classification of described image that information is corresponding with information on services represents.
Further, above-mentioned different image kind comprises books classification, CD classification, LOGO classification, poster classification, advertisement classification, personage's classification, clothing classification etc. The image feature data of corresponding different images kind then comprises books characteristic, laser disc characteristic, LOGO characteristic, poster characteristic, advertisement characteristic data, character features data, garment feature data etc.
In above-mentioned image identification system and method, adopt multiple image recognizer that the image in image input module is carried out feature extraction, obtain the image feature data of corresponding different images kind, also can extract the image classification information of correspondence from the data base of different images kind, owing to adopting multiple image recognizer to carry out image recognition for different image kinds, same image can obtain the recognition result of different images kind, and relative to traditional image-recognizing method, its recognition efficiency is higher.
Further, image also can be classified by display module, and information is corresponding with information on services to be represented; Display module can directly represent the image classification information of corresponding different images kind on the image in image input module, when the image classification information of some image kind is selected, then in the dialog box ejected, represent the information on services of this image classification information and correspondence thereof.
Above-mentioned image-recognizing method, comprises the following steps: obtains the image in image input module, is stored, and shown in display module in storage module; Adopt multiple image recognizer that the image in described image input module is carried out feature extraction, obtain the image feature data of corresponding different images kind; From corresponding data base, the image classification information with corresponding image feature data coupling is extracted according to described image kind.
Additionally, in the method, it is also possible to utilize the image input device in client for obtaining image, and the image in image input device is uploaded onto the server control end by network; The image that image input module obtains passes through the locally stored image of client or carries out, by the image input device of client, the image obtained of taking pictures in real time; Now, image identification system comprises server controls end and client, service end receives the image in the image input module that image input module is uploaded, feature extraction is carried out by multiple image recognizer of corresponding different images kind, obtain the image feature data of corresponding different images kind, then the image feature data to these image kinds obtained, matched image classification information is extracted from the data base of correspondence image kind, the image classification information extracted may return to client, is represented by the display module of client; Or the image recognizer in server controls end is extended, mounts more image recognizer or original image recognizer is updated, to provide the image recognition of larger class, use flexible.
In this situation, server controls end is searched and the information on services of image classification information matches from client by service providing module, and the information on services found or the service type information therefrom extracted are back to client, by display module, by information on services or service type information and image classification, information is corresponding represents; Client only provides interface to server controls end, and therefore, server controls end can be extended by increasing the more interface service type to providing, and to provide the information on services of larger class, is effectively increased the recognition efficiency of image recognition.
The above is the preferred embodiment of the present invention; it should be pointed out that, for those skilled in the art, under the premise without departing from the principles of the invention; can also making some improvements and modifications, these improvements and modifications are also considered as protection scope of the present invention.
Claims (9)
1. an image identification system, including server controls end, described server controls end is connected to:
Image input module: in order to input picture, utilize the network input picture of client, this image sources shoots in mobile phone or panel computer;
Display module: in order to display for image, shown for image recognition result:
Storage module: the image for input stores, and is stored for the structure after image Classification and Identification, and other modules can be easy to carry out image data extraction;
Image Classification and Identification module, comprises multiple image recognizer, for obtaining the image in storage module, the image extracted in storage module is carried out feature extraction, obtains the image feature data of corresponding different images kind, and is stored in different image recognizer;
Result extraction module, for the image classification information mated with corresponding image feature data from correspondence with extraction in the data base image recognizer according to required image kind;
Service providing module, for obtaining the image corresponding with described image kind preset according to required image kind, and mated display by the web page interlinkage being connected with service providing module or smart mobile phone end, and can receive corresponding picture appraisal information, display screen or touch screen by being connected with display module can be shown in display module simultaneously.
2. image identification system according to claim 1, it is characterised in that: described service providing module is additionally operable to from described information on services to extract service type information; Described system also includes client, and described client includes for information of being classified by the described image display module that carry out represent corresponding to service classification information.
3. image identification system according to claim 2, it is characterised in that: described service type information comprises the link of the service providing page of correspondence; Described client also includes:
Page jump module, for obtaining the click commands of described service type information, jumps to the service providing page corresponding with described service type information according to the link of described service providing page.
4. image identification system according to claim 2, it is characterised in that: described display module is additionally operable to the classification of described image that information is corresponding with information on services represents.
5. image identification system according to claim 1, it is characterized in that: in described image identification system, adopt multiple image recognizer that the image in image input module is carried out feature extraction, obtain the image feature data of corresponding different images kind, also can extract the image classification information of correspondence from the data base of different images kind, owing to adopting multiple image recognizer to carry out image recognition for different image kinds, same image can obtain the recognition result of different images kind, relative to traditional image-recognizing method, its recognition efficiency is higher.
6. image identification system according to claim 1, it is characterised in that: image also can be classified by described display module, and information is corresponding with information on services to be represented; Display module can directly represent the image classification information of corresponding different images kind on the image in image input module, when the image classification information of some image kind is selected, then in the dialog box ejected, represent the information on services of this image classification information and correspondence thereof.
7. an image-recognizing method, it is characterised in that: comprise the following steps: obtain the image in image input module, stored in storage module, and shown in display module; Adopt multiple image recognizer that the image in described image input module is carried out feature extraction, obtain the image feature data of corresponding different images kind; From corresponding data base, the image classification information with corresponding image feature data coupling is extracted according to described image kind.
8. image-recognizing method according to claim 7, it is characterised in that: in described method, it is also possible to utilize the image input device in client for obtaining image, and the image in image input device is uploaded onto the server control end by network; The image that image input module obtains passes through the locally stored image of client or carries out, by the image input device of client, the image obtained of taking pictures in real time; Now, image identification system comprises server controls end and client, service end receives the image in the image input module that image input module is uploaded, feature extraction is carried out by multiple image recognizer of corresponding different images kind, obtain the image feature data of corresponding different images kind, then the image feature data to these image kinds obtained, matched image classification information is extracted from the data base of correspondence image kind, the image classification information extracted may return to client, is represented by the display module of client; Or the image recognizer in server controls end is extended, mounts more image recognizer or original image recognizer is updated, to provide the image recognition of larger class, use flexible.
9. image-recognizing method according to claim 8, it is characterized in that: server controls end is searched and the information on services of image classification information matches from client by service providing module, and the information on services found or the service type information therefrom extracted are back to client, by display module, by information on services or service type information and image classification, information is corresponding represents; Client only provides interface to server controls end, and therefore, server controls end can be extended by increasing the more interface service type to providing, to provide the information on services of larger class.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610069999.4A CN105631461A (en) | 2016-02-01 | 2016-02-01 | Image recognition system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610069999.4A CN105631461A (en) | 2016-02-01 | 2016-02-01 | Image recognition system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105631461A true CN105631461A (en) | 2016-06-01 |
Family
ID=56046373
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610069999.4A Pending CN105631461A (en) | 2016-02-01 | 2016-02-01 | Image recognition system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105631461A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108021939A (en) * | 2017-11-30 | 2018-05-11 | 安徽理工大学 | A kind of automatic classification method of old books |
CN108460626A (en) * | 2018-02-09 | 2018-08-28 | 天津城建大学 | Book on-the-spot acquisitioning method and system based on augmented reality |
CN109034380A (en) * | 2018-06-08 | 2018-12-18 | 四川斐讯信息技术有限公司 | A kind of distributed image identification system and its method |
WO2019096179A1 (en) * | 2017-11-14 | 2019-05-23 | 深圳码隆科技有限公司 | Clothes logo effect detection method and apparatus, and electronic device |
CN110868543A (en) * | 2019-11-25 | 2020-03-06 | 三星电子(中国)研发中心 | Intelligent photographing method and device and computer readable storage medium |
US20230133678A1 (en) * | 2021-11-03 | 2023-05-04 | Hong Fu Jin Precision Industry (Wuhan) Co., Ltd. | Method for processing augmented reality applications, electronic device employing method, and non-transitory storage medium |
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 |
CN103425993A (en) * | 2012-05-22 | 2013-12-04 | 腾讯科技(深圳)有限公司 | Method and system for recognizing images |
-
2016
- 2016-02-01 CN CN201610069999.4A patent/CN105631461A/en active Pending
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 |
CN103425993A (en) * | 2012-05-22 | 2013-12-04 | 腾讯科技(深圳)有限公司 | Method and system for recognizing images |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019096179A1 (en) * | 2017-11-14 | 2019-05-23 | 深圳码隆科技有限公司 | Clothes logo effect detection method and apparatus, and electronic device |
CN108021939A (en) * | 2017-11-30 | 2018-05-11 | 安徽理工大学 | A kind of automatic classification method of old books |
CN108460626A (en) * | 2018-02-09 | 2018-08-28 | 天津城建大学 | Book on-the-spot acquisitioning method and system based on augmented reality |
CN109034380A (en) * | 2018-06-08 | 2018-12-18 | 四川斐讯信息技术有限公司 | A kind of distributed image identification system and its method |
CN110868543A (en) * | 2019-11-25 | 2020-03-06 | 三星电子(中国)研发中心 | Intelligent photographing method and device and computer readable storage medium |
US20230133678A1 (en) * | 2021-11-03 | 2023-05-04 | Hong Fu Jin Precision Industry (Wuhan) Co., Ltd. | Method for processing augmented reality applications, electronic device employing method, and non-transitory storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105631461A (en) | Image recognition system and method | |
CN103425993B (en) | Image-recognizing method and system | |
CN103369049B (en) | Mobile terminal and server exchange method and system thereof | |
CN108536414B (en) | Voice processing method, device and system and mobile terminal | |
US11551424B2 (en) | Interaction analysis systems and methods | |
CN106412229B (en) | Method and device for interaction and information provision of mobile terminal and method and device for providing contact information and mobile terminal | |
US20140111542A1 (en) | Platform for recognising text using mobile devices with a built-in device video camera and automatically retrieving associated content based on the recognised text | |
CN104602128A (en) | Video processing method and device | |
CN103050025A (en) | Mobile terminal learning method and learning system thereof | |
CN105631051A (en) | Character recognition based mobile augmented reality reading method and reading system thereof | |
US20170337222A1 (en) | Image searching method and apparatus, an apparatus and non-volatile computer storage medium | |
CN103678305A (en) | Method and system for displaying inquiring information based on image recognition | |
CN103428539A (en) | Pushed information publishing method and device | |
CN106649629B (en) | System for associating books with electronic resources | |
CN106446880A (en) | Information providing system and computer program | |
CN113536172B (en) | Encyclopedia information display method and device and computer storage medium | |
CN104866627A (en) | Searching system and searching method for photo information | |
US20170103124A1 (en) | Remote search engine using camera | |
US20170169108A1 (en) | Bright spot prompting method and device based on search key | |
CN113869063A (en) | Data recommendation method and device, electronic equipment and storage medium | |
KR101523349B1 (en) | Social Network Service System Based Upon Visual Information of Subjects | |
KR20120109265A (en) | Food information provision system and method thereof using qr code limked with broadcasting program | |
US11010978B2 (en) | Method and system for generating augmented reality interactive content | |
JP2022181319A (en) | Video search apparatus, video search system, and program | |
CN113641857A (en) | Visual media personalized search method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160601 |
|
RJ01 | Rejection of invention patent application after publication |