CN107273796A - A kind of fast face recognition and searching method based on face characteristic - Google Patents
A kind of fast face recognition and searching method based on face characteristic Download PDFInfo
- Publication number
- CN107273796A CN107273796A CN201710313906.2A CN201710313906A CN107273796A CN 107273796 A CN107273796 A CN 107273796A CN 201710313906 A CN201710313906 A CN 201710313906A CN 107273796 A CN107273796 A CN 107273796A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- characteristic
- facial image
- recognition
- 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
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- 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
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- 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
- G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Library & Information Science (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of fast face recognition and searching method based on face characteristic, comprise the following steps：Face is registered, and is gathered facial image, is recognized the characteristic in the facial image, the facial image is referred in corresponding classified index table according to this feature data；Recognition of face, gathers facial image, recognizes the characteristic of the facial image, the facial image in current face's image classified index table corresponding with this feature data is contrasted.The present invention recognizes the characteristic in the facial image when face is registered, the facial image is referred in corresponding classified index table according to this feature data, the facial image in current face's image classified index table corresponding with this feature data is contrasted when recognition of face, face search need not be carried out so when face recognition search in whole database, effectively reduce the hunting zone of face, avoid substantial amounts of useless contrast, the burden of system is alleviated, the reaction speed of system is improved.
Description
Technical field
The present invention relates to a kind of face recognition search method, particularly a kind of fast face identification based on face characteristic is searched
Suo Fangfa.
Background technology
Recognition of face, refers in particular to carry out the computer technology of identity discriminating using com-parison and analysis face visual signature information.People
Face identification is to gather image or video flowing containing face, and automatic detect and track people in the picture with video camera or camera
Face, and then a series of correlation techniques of face are carried out to the face that detects, generally also referred to as Identification of Images, face recognition.But
It is that current recognition of face is typically to contrast the face in the face and database on image one by one, due to the people in database
Face is random distribution, when carrying out face contrast, it is often necessary to which that people of contrast can just be found many times by being contrasted
Face, has carried out many useless contrasts, has aggravated the burden of system, reduced the reaction speed of system.
The content of the invention
To solve the above problems, it is an object of the invention to provide a kind of fast face identification that can reduce useless contrast
Searching method.
The present invention solves the technical scheme that is used of its problem：A kind of fast face identification search based on face characteristic
Method, comprises the following steps：
Face is registered, and is gathered facial image, is recognized the characteristic in the facial image, according to this feature data by the people
Face image is referred in corresponding classified index table；
Recognition of face, gathers facial image, the characteristic of the facial image is recognized, by current face's image and this feature
Facial image in the corresponding classified index table of data is contrasted.
Specifically, the characteristic in the identification facial image in face registration and recognition of face each means identification face
The sex and age bracket of face in image.The collection of image is completed by camera, and the form of image is RGB or YUV.
Specifically, face is first determined whether when gathering facial image, when determining whether face, first
Complexion model Face datection is carried out, complexion model Face datection refers to draw face complexion in Y-Cr-Cb face by statistical learning
The complexion model of distribution probability in the colour space, then judges whether the point on image belongs to human face region, skin by complexion model
Viola-Jones Face datections are carried out after color model Face datection again.
Specifically, the age bracket of face is identified by fusion LBP features and HOG features to carry out the age in facial image
Estimation, extracts the partial statistics characteristic with the face of change of age close relation, LBP features and HOG features is used into allusion quotation first
The method of type correlation analysis merges to form face age data storehouse, finally by support vector regression to face age data storehouse
It is trained and tests.
Specifically, the sex of face is identified by Adaboost+SVM face gender two progress of classification in facial image
Judge, first by being pre-processed to sample image, extract the Gabor wavelet feature of image, pass through Adaboost graders
Feature Dimension Reduction is carried out, SVM classifier is trained, trained after SVM classifier, images to be recognized is pre-processed, is carried
The Gabor wavelet feature of image is taken, Feature Dimension Reduction is carried out by Adaboost graders, finally with the SVM classifier trained
It is identified, exports the recognition result of face gender.
Specifically, when facial image is referred in corresponding classified index table according to characteristic, by the people
Face is saved into face database, and records the index value of the face.
Specifically, when facial image is referred in corresponding classified index table according to characteristic, face characteristic root
Be divided into two species of men and women according to sex, face characteristic according to the age be divided into less than 15 years old, 15 years old to 30 years old, 30
Year to 50 years old, more than 50 years old four species, the corresponding concordance list of every kind of face characteristic, face in facial image according to
Its feature species is referred in corresponding concordance list, and the index value arrangement in index value table is by the sequencing row of registration, index
It is worth the position in face database for face data storage.
Specifically, by the facial image progress pair in current face's image classified index table corresponding with this feature data
Than referring to identify on image after the sex and age bracket of face, corresponding sex concordance list and age concordance list are selected, so
The common factor of sex concordance list and age concordance list is obtained afterwards as face retrieval set.
Specifically, the face retrieved and the face progress pair in face retrieval set will be needed when face retrieval
Than successful two faces of output contrast if contrasting successfully, display comparison success, with face number if contrast is unsuccessful
Carry out contrast retrieval according to whole faces in storehouse, exported if contrast successfully and contrast successful two faces, display comparison into
Work(, if contrast is unsuccessful, directly displays and contrasts unsuccessful, face is contrasted when contrasting by Euclidean distance, contrast
Formula is εk=| | Ω-Ωk||2, wherein Ω represents the face to be differentiated, Ω k represent some face of face database, both
All it is to be represented by the weight of characteristic value, formula is to seek Euclidean distance to both, when distance is less than threshold value, explanation will be sentenced
K-th of face of other face and face database is same person.
The beneficial effects of the invention are as follows：The present invention is a kind of fast face recognition and searching method based on face characteristic, this
Invention recognizes the characteristic in the facial image when face is registered, and is sorted out the facial image according to this feature data
Into corresponding classified index table, by current face's image classified index corresponding with this feature data when recognition of face
Facial image in table is contrasted, and need not carry out face in whole database so when face recognition search searches
Rope, it is only necessary to face search is carried out in corresponding face characteristic concordance list, the hunting zone of face is effectively reduced, it is to avoid
Substantial amounts of useless contrast, alleviates the burden of system, improves the reaction speed of system.
Brief description of the drawings
The invention will be further described with example below in conjunction with the accompanying drawings.
Fig. 1 is the general flow chart of the present invention.
Embodiment
A kind of fast face recognition and searching method based on face characteristic, comprises the following steps：Face is registered, and gathers face
Image, recognizes the characteristic in the facial image, and the facial image is referred into corresponding classification rope according to this feature data
Draw in table；Recognition of face, gathers facial image, the characteristic of the facial image is recognized, by current face's image and this feature
Facial image in the corresponding classified index table of data is contrasted.In identification facial image in face registration and recognition of face
Characteristic each mean identification facial image in face sex and age bracket.The collection of image is completed by camera, figure
The form of picture is RGB or YUV.Face is first determined whether when collection facial image, it is first when determining whether face
Complexion model Face datection is first carried out, complexion model Face datection refers to draw face complexion in Y-Cr-Cb by statistical learning
The complexion model of distribution probability in color space, then judges whether the point on image belongs to human face region by complexion model,
Viola-Jones Face datections are carried out after complexion model Face datection again.The age bracket of face is identified by facial image
Merge LBP features and HOG features to carry out age estimation, the partial statistics with the face of change of age close relation are extracted first
Feature, LBP features and HOG features are merged to form face age data storehouse using the method for canonical correlation analysis, finally by
Support vector regression is trained and tested to face age data storehouse.
It is preferred that, the sex of face is identified by Adaboost+SVM face gender classification in facial image of the invention
Two are judged, first by being pre-processed to sample image, are extracted the Gabor wavelet feature of image, are passed through Adaboost
Grader carries out Feature Dimension Reduction, and SVM classifier is trained, trained after SVM classifier, images to be recognized is located in advance
Reason, extracts the Gabor wavelet feature of image, and Feature Dimension Reduction is carried out by Adaboost graders, finally with SVM points trained
Class device is identified, and exports the recognition result of face gender.Facial image is referred to by corresponding classification rope according to characteristic
When drawing in table, the face is saved into face database, and record the index value of the face.According to characteristic by face
When graphic collection is into corresponding classified index table, face characteristic is divided into two species of men and women, face characteristic root according to sex
Less than 15 years old, 15 years old to 30 years old, 30 years old to 50 years old, more than 50 years old four species are divided into according to the age, it is every kind of
Face in face characteristic one concordance list of correspondence, facial image is referred in corresponding concordance list according to its feature species, rope
The index value arrangement drawn in value table is arranged by the sequencing of registration, and index value is position of the face data storage in face database
Put.
It is preferred that, the facial image in the classified index table corresponding with this feature data of the invention by current face's image
Carry out contrast to refer to identify on image after the sex and age bracket of face, select corresponding sex concordance list and age index
Table, then obtains the common factor of sex concordance list and age concordance list as face retrieval set.It will be needed when face retrieval
The face of retrieval is contrasted with the face in face retrieval set, successful two people of output contrast if contrasting successfully
Face, display comparison success carries out contrast retrieval if contrast is unsuccessful with whole faces in face database, if contrast
Successful then successful two faces of output contrast, display comparison success, if contrast is unsuccessful, directly display contrast not into
Work(, face is contrasted when contrasting by Euclidean distance, and contrast equation is εk=| | Ω-Ωk||2, wherein Ω, which is represented, to be differentiated
Face, Ω k represent some face of face database, are both represented by the weight of characteristic value, and formula is pair
Both seek Euclidean distance, and k-th of face that the face and face database to be differentiated is illustrated when distance is less than threshold value is same person
's.
Fig. 1 is the general flow chart of the present invention, as shown in figure 1, a kind of fast face identification searcher based on face characteristic
Method, comprises the following steps：
S10, chooses whether to start face registration, is to go to step S20, otherwise goes to step S30；
S20, carries out face registration, goes to step S10；
S30, carries out face retrieval, goes to step S10；
Step S20 comprises the following steps,
S21, passes through camera collection image；
Whether there is face in S22, the image for judging camera collection, be to go to step S23, otherwise go to step S21；
The age bracket of face in S23, identification image；
The sex of face in S24, identification image；
S25, preserves the age bracket human face data and sex human face data identified；
S26, updates the search index in face concordance list, goes to step S10, the face concordance list system development when
Time is set up.
The present invention recognizes characteristic in the facial image when face is registered, according to this feature data by the people
Face image is referred in corresponding classified index table, when recognition of face that current face's image is relative with this feature data
Answer the facial image in classified index table to be contrasted, need not enter so when face recognition search in whole database
Pedestrian's face is searched for, it is only necessary to face search is carried out in corresponding face characteristic concordance list, the search model of face is effectively reduced
Enclose, it is to avoid substantial amounts of useless contrast, alleviate the burden of system, improve the reaction speed of system.
Specifically, step S30 comprises the following steps：
S31, passes through camera collection image；
Whether there is face in S32, the image for judging camera collection, be to go to step S33, otherwise go to step S31；
The age bracket of face in S33, identification image；
The sex of face in S34, identification image；
S35, corresponding face concordance list is selected according to the face age bracket and face gender identified；
S36, the face age bracket concordance list chosen and face gender concordance list are gone to occur simultaneously, will current people to be retrieved
Face is matched with the face in occuring simultaneously, and is carried out face retrieval, is gone to step S10.
It is preferred that, the collection of image of the present invention is completed by camera, and the form of image is RGB or YUV.The present invention is sentencing
It is disconnected when whether have face, complexion model Face datection is carried out first, and complexion model Face datection refers to by statistical learning
The complexion model of face complexion distribution probability in Y-Cr-Cb color spaces is drawn, is then judged by complexion model on image
Point whether belong to human face region, complexion model Face datection after carry out Viola-Jones Face datections again.The year of the present invention
Age section is identified by fusion LBP features and HOG features to carry out age estimation, and the people with change of age close relation is extracted first
The partial statistics characteristic of face, LBP features and HOG features are merged to form face age data using the method for canonical correlation analysis
Storehouse, is trained and tests to face age data storehouse finally by support vector regression.When identity of the present invention is other
Judged by Adaboost+SVM face gender classification two, first by being pre-processed to sample image, extract figure
The Gabor wavelet feature of picture, carries out Feature Dimension Reduction by Adaboost graders, SVM classifier is trained, trained
After SVM classifier, images to be recognized is pre-processed, the Gabor wavelet feature of image is extracted, passes through Adaboost graders
Feature Dimension Reduction is carried out, is finally identified with the SVM classifier trained, the recognition result of face gender is exported.
It is preferred that, human face data is saved into face database, and recording indexes by the present invention when preserving human face data
Value.Update search index to refer to set up an index value table for every kind of face characteristic, face characteristic is divided into men and women according to sex
Two species, face characteristic according to the age be divided into less than 15 years old, 15 years old to 30 years old, 30 years old to 50 years old, 50
Index value arrangement in more than year four species, index value table is by the sequencing row of registration, and index value is face data storage
Position in face database.Selection search index table refers to identify on image after the sex and age bracket of face, selected
Corresponding sex concordance list and age concordance list are selected, the common factor for then obtaining sex concordance list and age concordance list is examined as face
Suo Jihe.
It is preferred that, when face retrieval of the present invention the face retrieved will be needed to be carried out with the face in face retrieval set
Contrast, successful two faces of output contrast if contrasting successfully, display comparison success, with face if contrast is unsuccessful
Whole faces in database carry out contrast retrieval, successful two faces of output contrast, display comparison if contrasting successfully
Success, if contrast is unsuccessful, directly displays and contrasts unsuccessful, face is contrasted when contrasting by Euclidean distance, right
It is ε than formulak=| | Ω-Ωk||2, wherein Ω represents the face to be differentiated, Ω k represent some face of face database, two
Person is represented by the weight of characteristic value, and formula is to seek Euclidean distance to both, and when distance is less than threshold value, explanation will
The face of differentiation and k-th of face of face database are same persons.
It is described above, simply presently preferred embodiments of the present invention, the invention is not limited in above-mentioned embodiment, as long as
It reaches the technique effect of the present invention with identical means, should all belong to protection scope of the present invention.
Claims (10)
1. a kind of fast face recognition and searching method based on face characteristic, it is characterised in that comprise the following steps：
Face is registered, and is gathered facial image, is recognized the characteristic in the facial image, according to this feature data by the face figure
As being referred in corresponding classified index table；
Recognition of face, gathers facial image, the characteristic of the facial image is recognized, by current face's image and this feature data
Facial image in corresponding classified index table is contrasted.
2. a kind of fast face recognition and searching method based on face characteristic according to claim 1, it is characterised in that：People
Face register and recognition of face in identification facial image in characteristic each mean identification facial image in face sex with
Age bracket.
3. a kind of fast face recognition and searching method based on face characteristic according to claim 1, it is characterised in that：Figure
The collection of picture is completed by camera, and the form of image is RGB or YUV.
4. a kind of fast face recognition and searching method based on face characteristic according to claim 1, it is characterised in that：Adopt
Face is first determined whether when collection facial image, when determining whether face, complexion model face inspection is carried out first
Survey, complexion model Face datection refers to draw face complexion distribution probability in Y-Cr-Cb color spaces by statistical learning
Complexion model, then judges whether the point on image belongs to after human face region, complexion model Face datection by complexion model
Viola-Jones Face datections are carried out again.
5. a kind of fast face recognition and searching method based on face characteristic according to claim 2, it is characterised in that：People
The age bracket of face is identified by fusion LBP features and HOG features to carry out age estimation in face image, extracts first and the age
The partial statistics characteristic of the close face of variation relation, LBP features and HOG features are merged using the method for canonical correlation analysis
Face age data storehouse is formed, face age data storehouse is trained and tested finally by support vector regression.
6. a kind of fast face recognition and searching method based on face characteristic according to claim 2, it is characterised in that：People
The sex of face is identified by Adaboost+SVM face gender classification and two judged in face image, first by sample
Image is pre-processed, and extracts the Gabor wavelet feature of image, and Feature Dimension Reduction is carried out by Adaboost graders, to SVM points
Class device is trained, and is trained after SVM classifier, and images to be recognized is pre-processed, and the Gabor wavelet for extracting image is special
Levy, Feature Dimension Reduction is carried out by Adaboost graders, is finally identified with the SVM classifier trained, export face
Other recognition result.
7. a kind of fast face recognition and searching method based on face characteristic according to claim 1, it is characterised in that：Root
When facial image is referred in corresponding classified index table according to characteristic, the face is saved into face database,
And record the index value of the face.
8. a kind of fast face recognition and searching method based on face characteristic according to claim 2, it is characterised in that：Root
When according to characteristic, facial image is referred in corresponding classified index table, face characteristic is divided into men and women two according to sex
Species, face characteristic according to the age be divided into less than 15 years old, 15 years old to 30 years old, 30 years old to 50 years old, 50 years old with
Face in upper four species, one concordance list of every kind of face characteristic correspondence, facial image is referred to phase according to its feature species
In the concordance list answered, the index value arrangement in index value table is by the sequencing row of registration, and index value is that face data storage exists
Position in face database.
9. a kind of fast face recognition and searching method based on face characteristic according to claim 2, it is characterised in that：Will
Facial image in current face's image classified index table corresponding with this feature data carries out contrast and refers to identify on image
After the sex and age bracket of face, select corresponding sex concordance list and age concordance list, then obtain sex concordance list and
The common factor of age concordance list is used as face retrieval set.
10. a kind of fast face recognition and searching method based on face characteristic according to claim 9, it is characterised in that：
The face for needing to retrieve is contrasted with the face in face retrieval set when face retrieval, it is defeated if contrasting successfully
Go out to contrast successful two faces, display comparison success is entered if contrast is unsuccessful with whole faces in face database
Row contrast retrieval, successful two faces of output contrast if contrasting successfully, display comparison success, if contrast is unsuccessful,
Then directly display contrast unsuccessful, face is contrasted when contrasting by Euclidean distance, and contrast equation is εt=| | Ω-Ωt|
|2, wherein Ω represents the face to be differentiated, Ω k represent some face of face database, both pass through the power of characteristic value
Again come what is represented, formula is to seek Euclidean distance to both, illustrates the face and face database to be differentiated when distance is less than threshold value
K-th of face be same person.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710313906.2A CN107273796A (en) | 2017-05-05 | 2017-05-05 | A kind of fast face recognition and searching method based on face characteristic |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710313906.2A CN107273796A (en) | 2017-05-05 | 2017-05-05 | A kind of fast face recognition and searching method based on face characteristic |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107273796A true CN107273796A (en) | 2017-10-20 |
Family
ID=60073732
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710313906.2A Pending CN107273796A (en) | 2017-05-05 | 2017-05-05 | A kind of fast face recognition and searching method based on face characteristic |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107273796A (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108009521A (en) * | 2017-12-21 | 2018-05-08 | 广东欧珀移动通信有限公司 | Humanface image matching method, device, terminal and storage medium |
| CN108848364A (en) * | 2018-06-20 | 2018-11-20 | 温州大学 | A kind of color calibration method of the color space conversion based on support vector regression |
| CN109271917A (en) * | 2018-09-10 | 2019-01-25 | 广州杰赛科技股份有限公司 | Face identification method, device, computer equipment and readable storage medium storing program for executing |
| CN109408651A (en) * | 2018-09-21 | 2019-03-01 | 神思电子技术股份有限公司 | A kind of face retrieval method based on the identification of face face gesture |
| CN109492611A (en) * | 2018-11-27 | 2019-03-19 | 电卫士智能电器（北京）有限公司 | Electrical Safety method for early warning and device |
| CN109493490A (en) * | 2018-11-27 | 2019-03-19 | 电卫士智能电器（北京）有限公司 | Electricity consumption user right judgment method and device |
| CN109584417A (en) * | 2018-11-27 | 2019-04-05 | 电卫士智能电器（北京）有限公司 | Door-access control method and device |
| CN109635148A (en) * | 2018-12-14 | 2019-04-16 | 深圳英飞拓科技股份有限公司 | Face picture storage method and device |
| CN109697622A (en) * | 2017-10-23 | 2019-04-30 | 北京京东尚科信息技术有限公司 | Information generating method and device based on intelligent shop |
| CN109697388A (en) * | 2017-10-23 | 2019-04-30 | 北京京东尚科信息技术有限公司 | Face identification method and device |
| CN109829071A (en) * | 2018-12-14 | 2019-05-31 | 平安科技（深圳）有限公司 | Face image searching method, server, computer equipment and storage medium |
| CN109919093A (en) * | 2019-03-07 | 2019-06-21 | 苏州科达科技股份有限公司 | A kind of face identification method, device, equipment and readable storage medium storing program for executing |
| CN109993042A (en) * | 2017-12-29 | 2019-07-09 | 国民技术股份有限公司 | A kind of face identification method and its device |
| CN110210414A (en) * | 2019-06-05 | 2019-09-06 | 北京京投信安科技发展有限公司 | The quick intersection identification technology of magnanimity face database |
| CN110728522A (en) * | 2019-10-11 | 2020-01-24 | 上海可充电子商务有限公司 | Face brushing public traffic system |
| CN110807119A (en) * | 2018-07-19 | 2020-02-18 | 浙江宇视科技有限公司 | Face duplicate checking method and device |
| CN111325174A (en) * | 2019-04-02 | 2020-06-23 | 北京航空航天大学 | Face recognition system for high-speed rail air conditioner adjustment |
| CN112052733A (en) * | 2020-07-31 | 2020-12-08 | 中国建设银行股份有限公司 | Database construction method, face recognition device and electronic equipment |
| CN112329589A (en) * | 2020-10-30 | 2021-02-05 | 四川天翼网络服务有限公司 | Face recognition method based on high-dimensional feature algorithm |
| CN112597803A (en) * | 2020-11-26 | 2021-04-02 | 深圳泰首智能技术有限公司 | Face recognition method, device and system and electronic equipment |
| WO2021107826A1 (en) | 2019-11-25 | 2021-06-03 | Telefonaktiebolaget Lm Ericsson (Publ) | Blockchain based facial anonymization system |
| CN113674470A (en) * | 2021-08-13 | 2021-11-19 | 大匠智联(深圳)科技有限公司 | Access control system face recognition method and access control system |
| WO2022179046A1 (en) * | 2021-02-26 | 2022-09-01 | 深圳壹账通智能科技有限公司 | Facial recognition method and apparatus, computer device, and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101201894A (en) * | 2007-11-06 | 2008-06-18 | 重庆大学 | Method for recognizing human face from commercial human face database based on gridding computing technology |
| CN101226591A (en) * | 2008-01-31 | 2008-07-23 | 上海交通大学 | Personal identification method based on mobile phone pick-up head combining with human face recognition technique |
| CN103235825A (en) * | 2013-05-08 | 2013-08-07 | 重庆大学 | Method used for designing large-quantity face recognition search engine and based on Hadoop cloud computing frame |
| CN105138681A (en) * | 2015-09-15 | 2015-12-09 | 成都品果科技有限公司 | Picture search method and system based on space coordinate positioning |
-
2017
- 2017-05-05 CN CN201710313906.2A patent/CN107273796A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101201894A (en) * | 2007-11-06 | 2008-06-18 | 重庆大学 | Method for recognizing human face from commercial human face database based on gridding computing technology |
| CN101226591A (en) * | 2008-01-31 | 2008-07-23 | 上海交通大学 | Personal identification method based on mobile phone pick-up head combining with human face recognition technique |
| CN103235825A (en) * | 2013-05-08 | 2013-08-07 | 重庆大学 | Method used for designing large-quantity face recognition search engine and based on Hadoop cloud computing frame |
| CN105138681A (en) * | 2015-09-15 | 2015-12-09 | 成都品果科技有限公司 | Picture search method and system based on space coordinate positioning |
Non-Patent Citations (2)
| Title |
|---|
| 林辉: "性别、种族人脸识别方法研究", 《中国优秀博硕士学位论文全文数据库信息科技辑》 * |
| 瞿中 等: "典型相关分析融合 LBP和 HOG特征的人脸年龄估计", 《重庆大学学报》 * |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109697622A (en) * | 2017-10-23 | 2019-04-30 | 北京京东尚科信息技术有限公司 | Information generating method and device based on intelligent shop |
| CN109697388A (en) * | 2017-10-23 | 2019-04-30 | 北京京东尚科信息技术有限公司 | Face identification method and device |
| CN108009521B (en) * | 2017-12-21 | 2021-05-04 | Oppo广东移动通信有限公司 | Face image matching method, device, terminal and storage medium |
| CN108009521A (en) * | 2017-12-21 | 2018-05-08 | 广东欧珀移动通信有限公司 | Humanface image matching method, device, terminal and storage medium |
| CN109993042A (en) * | 2017-12-29 | 2019-07-09 | 国民技术股份有限公司 | A kind of face identification method and its device |
| CN108848364A (en) * | 2018-06-20 | 2018-11-20 | 温州大学 | A kind of color calibration method of the color space conversion based on support vector regression |
| CN108848364B (en) * | 2018-06-20 | 2020-12-29 | 温州大学 | Color correction method for color space conversion based on support vector regression |
| CN110807119A (en) * | 2018-07-19 | 2020-02-18 | 浙江宇视科技有限公司 | Face duplicate checking method and device |
| CN109271917A (en) * | 2018-09-10 | 2019-01-25 | 广州杰赛科技股份有限公司 | Face identification method, device, computer equipment and readable storage medium storing program for executing |
| CN109408651A (en) * | 2018-09-21 | 2019-03-01 | 神思电子技术股份有限公司 | A kind of face retrieval method based on the identification of face face gesture |
| CN109408651B (en) * | 2018-09-21 | 2020-09-29 | 神思电子技术股份有限公司 | Face retrieval method based on face gesture recognition |
| CN109493490A (en) * | 2018-11-27 | 2019-03-19 | 电卫士智能电器（北京）有限公司 | Electricity consumption user right judgment method and device |
| CN109584417A (en) * | 2018-11-27 | 2019-04-05 | 电卫士智能电器（北京）有限公司 | Door-access control method and device |
| CN109492611A (en) * | 2018-11-27 | 2019-03-19 | 电卫士智能电器（北京）有限公司 | Electrical Safety method for early warning and device |
| CN109829071A (en) * | 2018-12-14 | 2019-05-31 | 平安科技（深圳）有限公司 | Face image searching method, server, computer equipment and storage medium |
| CN109635148A (en) * | 2018-12-14 | 2019-04-16 | 深圳英飞拓科技股份有限公司 | Face picture storage method and device |
| CN109829071B (en) * | 2018-12-14 | 2023-09-05 | 平安科技（深圳）有限公司 | Face image searching method, server, computer device and storage medium |
| CN109635148B (en) * | 2018-12-14 | 2021-06-15 | 深圳英飞拓科技股份有限公司 | Face picture storage method and device |
| CN109919093A (en) * | 2019-03-07 | 2019-06-21 | 苏州科达科技股份有限公司 | A kind of face identification method, device, equipment and readable storage medium storing program for executing |
| CN111325174A (en) * | 2019-04-02 | 2020-06-23 | 北京航空航天大学 | Face recognition system for high-speed rail air conditioner adjustment |
| CN110210414A (en) * | 2019-06-05 | 2019-09-06 | 北京京投信安科技发展有限公司 | The quick intersection identification technology of magnanimity face database |
| CN110728522A (en) * | 2019-10-11 | 2020-01-24 | 上海可充电子商务有限公司 | Face brushing public traffic system |
| WO2021107826A1 (en) | 2019-11-25 | 2021-06-03 | Telefonaktiebolaget Lm Ericsson (Publ) | Blockchain based facial anonymization system |
| EP4066137A4 (en) * | 2019-11-25 | 2023-08-23 | Telefonaktiebolaget LM Ericsson (publ) | Blockchain based facial anonymization system |
| CN112052733A (en) * | 2020-07-31 | 2020-12-08 | 中国建设银行股份有限公司 | Database construction method, face recognition device and electronic equipment |
| CN112329589A (en) * | 2020-10-30 | 2021-02-05 | 四川天翼网络服务有限公司 | Face recognition method based on high-dimensional feature algorithm |
| CN112329589B (en) * | 2020-10-30 | 2023-03-24 | 四川天翼网络股份有限公司 | Face recognition method based on high-dimensional feature algorithm |
| CN112597803A (en) * | 2020-11-26 | 2021-04-02 | 深圳泰首智能技术有限公司 | Face recognition method, device and system and electronic equipment |
| WO2022179046A1 (en) * | 2021-02-26 | 2022-09-01 | 深圳壹账通智能科技有限公司 | Facial recognition method and apparatus, computer device, and storage medium |
| CN113674470A (en) * | 2021-08-13 | 2021-11-19 | 大匠智联(深圳)科技有限公司 | Access control system face recognition method and access control system |
| CN113674470B (en) * | 2021-08-13 | 2023-05-05 | 大匠智联(深圳)科技有限公司 | Face recognition method of access control system and access control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107273796A (en) | A kind of fast face recognition and searching method based on face characteristic | |
| Borenstein et al. | Learning to segment | |
| Layne et al. | Person re-identification by attributes. | |
| CN105160317B (en) | One kind being based on area dividing pedestrian gender identification method | |
| CN109558810B (en) | Target person identification method based on part segmentation and fusion | |
| CN109829467A (en) | Image labeling method, electronic device and non-transient computer-readable storage medium | |
| US8170343B2 (en) | Method and system for searching images with figures and recording medium storing metadata of image | |
| EP2955645A1 (en) | System for automated segmentation of images through layout classification | |
| US20130044944A1 (en) | Clothing search in images | |
| CN106446015A (en) | Video content access prediction and recommendation method based on user behavior preference | |
| CN102103690A (en) | Method for automatically portioning hair area | |
| CN103996046A (en) | Personnel recognition method based on multi-visual-feature fusion | |
| CN110348416A (en) | Multi-task face recognition method based on multi-scale feature fusion convolutional neural network | |
| CN106845513B (en) | Manpower detector and method based on condition random forest | |
| CN104281572B (en) | A kind of target matching method and its system based on mutual information | |
| KR101835333B1 (en) | Method for providing face recognition service in order to find out aging point | |
| Salah et al. | Fusing local binary patterns with wavelet features for ethnicity identification | |
| CN108960142B (en) | Pedestrian re-identification method based on global feature loss function | |
| CN108319672B (en) | Mobile terminal bad information filtering method and system based on cloud computing | |
| JP2014016968A (en) | Person retrieval device and data collection device | |
| Wang et al. | S 3 D: Scalable pedestrian detection via score scale surface discrimination | |
| Chen et al. | Automatic training image acquisition and effective feature selection from community-contributed photos for facial attribute detection | |
| CN105404682B (en) | A kind of book retrieval method based on digital image content | |
| Cushen et al. | Mobile visual clothing search | |
| CN111738039B (en) | Pedestrian re-identification method, terminal and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171020 |