CN106991448A - A kind of portrait compares processing method - Google Patents
A kind of portrait compares processing method Download PDFInfo
- Publication number
- CN106991448A CN106991448A CN201710227879.7A CN201710227879A CN106991448A CN 106991448 A CN106991448 A CN 106991448A CN 201710227879 A CN201710227879 A CN 201710227879A CN 106991448 A CN106991448 A CN 106991448A
- Authority
- CN
- China
- Prior art keywords
- portrait
- characteristic
- effective
- data set
- portrait 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/258—Data format conversion from or to a database
-
- 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
Abstract
Processing method is compared the invention discloses a kind of portrait, this method also includes following process step:Step 1:Processing system receives the original photograph of input and carries out portrait characteristic extraction to original photograph, forms people's feature as data set;Step 2:Effective portrait judgement is carried out to portrait characteristic data set, effective portrait characteristic data set is obtained;Step 3:Quality verification is carried out to effective portrait characteristic data set, the portrait characteristic data set that mass meets sets requirement is extracted;Step 4:The portrait characteristic data set that sets requirement is met to quality carries out corresponding portrait characteristic extraction and carries out structural data conversion, so as to generate specific structural data portrait condition code;Step 5:Structural data portrait condition code in structural data portrait condition code and existing property data base is subjected to similarity system design and exported the similarity fractions that draw are compared.The present invention can effectively improve discrimination and authentication efficiency.
Description
Technical field
Processing method is compared the present invention relates to a kind of portrait, more particularly to a kind of discrimination and the high portrait of certification rate are compared
Processing method.
Background technology
In recent years, security protection industry has started the upsurge of a ripple Identification of Images, and numerous manufacturers are proposed Related product, made one after another
Obtaining Identification of Images becomes the hot spot technology direction in industry.
Although existing portrait recognition technology function is huge, in actual applications, we, which remain unchanged, can run into many problems.Its
In, influence of the portrait image quality to discrimination is higher, and poor image quality, identification is low, and validity feature seldom, is used sometimes
Naked eyes also are difficult to confirm identity.Picture quality is again affected by many factors, such as illumination, posture, expression, portrait size, definition
Deng.Contrasted by picture of the same person under different illumination, it is possible to find out that picture of the same person under different illumination is used
Naked eyes also are difficult to distinguish.Thus, current face recognition system can only be carried out in the environment of some are compared with specification, and such as light is equal
Even, portrait needs to face video camera, and guarantor in picture as there is certain pixel wide.But in actual security protection
Monitor in occasion, these restrictive conditions are difficult to meet one by one.At present, in verification process, existing checking equipment needs mostly
Degree of precision can just be drawn by carrying out large area contrast with database portrait to being certified people so that such processing mode need compared with
The long time is compared and compares that angle is single, serious influence verification efficiency and precision.
The content of the invention
Processing method is compared it is an object of the present invention to provide a kind of portrait, discrimination and accuracy of identification can be effectively improved.
Realize that the purpose compares processing method there is provided a kind of portrait for this, this method also includes following process step:
Step 1:Processing system receives the original photograph of input and carries out portrait characteristic extraction, shape to original photograph
Adult is as characteristic data set;
Step 2:Effective portrait judgement is carried out to portrait characteristic data set, effective portrait characteristic data set is obtained;
Step 3:Quality verification is carried out to effective portrait characteristic data set, the portrait spy that mass meets sets requirement is extracted
Levy data set;
Step 4:The portrait characteristic data set that sets requirement is met to quality carries out corresponding portrait characteristic extraction simultaneously
And structural data conversion is carried out, so as to generate specific structural data portrait condition code;
Step 5:By the structuring number in above-mentioned specific structural data portrait condition code and existing property data base
Similarity system design is carried out according to portrait condition code and is exported the similarity fractions that draw are compared.
Preferably, in step 1, the two-dimensional coordinate point of each portrait characteristic point is also obtained when extracting portrait characteristic, is obtained
The process for obtaining the two-dimensional coordinate point of each portrait characteristic point is as follows:
Picture element scan line by line is first carried out on original image and obtains the characteristic point for all meeting doubtful portrait, is then obtained one by one
Two-dimensional coordinate point of the characteristic point of doubtful portrait on original image must be met, then the two-dimensional coordinate point periphery of acquisition is entered one by one
Row relevant people is as characteristic is scanned so as to be confirmed.
Preferably, the characteristic point of the doubtful portrait is that satisfaction can see eyes.
Preferably, in step 1, portrait characteristic data set includes the two-dimensional coordinate of portrait characteristic and portrait characteristic point
Point.
Preferably, in step 2, people is concentrated to the portrait characteristic of formation according to effective portrait criterion of setting
As characteristic carries out effective portrait judgement one by one, if judging, the portrait characteristic is not effective portrait, is terminated, if judging
The portrait characteristic is effective portrait, then records, so as to obtain effective portrait characteristic data set.
Preferably, in step 2, obtain after effective portrait characteristic data set, also whether portrait feature set is all completed to have
Effect portrait detection is judged, if finding there is untreated portrait characteristic, is continued to untreated portrait characteristic
Judgement processing is carried out, if no discovery does not have untreated portrait characteristic, step 3 is carried out.
Preferably, in step 3, when carrying out quality verification to effective portrait characteristic data set, according to effective people of setting
As integrity degree standard concentrates effective portrait characteristic to carry out quality score effective portrait characteristic one by one, so as to draw full
The portrait characteristic data set of foot setting mass fraction.
Preferably, the effective portrait standard set is the definition of the portrait picture of setting, the angle of the portrait of setting
Spend scope and eyes can be seen.
Preferably, in step 4, the structural data portrait condition code of gained is also deposited into existing property data base.
Compared with prior art, its advantage is the present invention:
The present invention is by setting up portrait characteristic data set to original image scanning and showing that meeting quality wants by processing
The portrait characteristic data set asked, by changing into structural data portrait condition code and the structuring in existing property data base
Data portrait condition code carries out similarity system design, can effectively improve discrimination and accuracy of identification.The present invention has identification accurate simultaneously
Exactness is high, and acquisition rate is high, to the anti-interference strong ability of light;Personnel identity identification is carried out by the present invention, can make to be verified
People can be transferred through identification in different angles, the degree of accuracy of the efficiency passed through and identification can greatly be lifted, while can also
It is collected into and is certified people's information.
Brief description of the drawings
Fig. 1 is flow chart of the invention.
Embodiment
With reference to embodiment, the invention will be further described, but does not constitute any limitation of the invention, any
The modification of the limited number of time made in scope of the invention as claimed, still in scope of the presently claimed invention.
As shown in figure 1, comparing processing method the invention provides a kind of portrait, this method also includes following process step:
Step 1:Processing system receives the original photograph of input and carries out portrait characteristic extraction, shape to original photograph
Adult is as characteristic data set;
Step 2:Effective portrait judgement is carried out to portrait characteristic data set, effective portrait characteristic data set is obtained;
Step 3:Quality verification is carried out to effective portrait characteristic data set, the portrait spy that mass meets sets requirement is extracted
Levy data set;
Step 4:The portrait characteristic data set that sets requirement is met to quality carries out corresponding portrait characteristic extraction simultaneously
And structural data conversion is carried out, so as to generate specific structural data portrait condition code;
Step 5:By the structuring number in above-mentioned specific structural data portrait condition code and existing property data base
Similarity system design is carried out according to portrait condition code and is exported the similarity fractions that draw are compared.
In the present embodiment, processing system is computer, and computer can pass through extraneous camera or human image collecting
Rifle carries out IMAQ, the structuring number that existing property data base there are for institute's certification object to being certified object
According to the database of portrait condition code, and existing property data base is linked with processing system, wherein structural data portrait
Condition code is the binary data that computer can be recognized.
In the present embodiment, processing it is last will compare the similarity fractions that draw carry out output can be effectively anti-
Reflect contrast effect and processing speed so that result is more directly perceived.
In step 1, the two-dimensional coordinate point of each portrait characteristic point is also obtained when extracting portrait characteristic, each portrait is obtained
The process of the two-dimensional coordinate point of characteristic point is as follows:
Picture element scan line by line is first carried out on original image and obtains the characteristic point for all meeting doubtful portrait, is then obtained one by one
Two-dimensional coordinate point of the characteristic point of doubtful portrait on original image must be met, then the two-dimensional coordinate point periphery of acquisition is entered one by one
Row relevant people is as characteristic is scanned so as to be confirmed.
In step 1, portrait characteristic data set includes the two-dimensional coordinate point of portrait characteristic and portrait characteristic point.According to
The portrait feature of different two-dimensional coordinate points, can form independent portrait characteristic data set.
In the present embodiment, portrait characteristic data set can include a portrait characteristic subset or multiple portrait features
Data subset.
In step 2, portrait feature is concentrated to the portrait characteristic of formation according to effective portrait criterion of setting
Data carry out effective portrait judgement one by one, if judging, the portrait characteristic is not effective portrait, is terminated, if judging the portrait
Characteristic is effective portrait, then records, so as to obtain effective portrait characteristic data set.
In step 2, obtain after effective portrait characteristic data set, effective portrait inspection also whether is all completed to portrait feature set
Survey is judged, if finding there is untreated portrait characteristic, continues to judge untreated portrait characteristic
Processing, if no discovery does not have untreated portrait characteristic, carries out step 3.
In step 3, when carrying out quality verification to effective portrait characteristic data set, according to effective portrait integrity degree of setting
Standard concentrates effective portrait characteristic to carry out quality score effective portrait characteristic one by one, so as to draw satisfaction setting 95
Point and the above portrait characteristic data set.
The effective portrait standard set is the definition of the portrait picture of setting, the angular range of the portrait of setting and can see
See eyes.
In the present embodiment, effective portrait is carried out according to effective portrait standard to be judged as that the premise of eyes can be being seen
Under, the angle that definition size and portrait are captured is obtained according to picture pixels, can such as seen in the angular range of eyes, next pair
Picture carries out effective portrait judgement.
In the present embodiment, effective portrait characteristic data set can include an effective portrait characteristic data set or multiple have
Imitate portrait characteristic data set.Effective portrait characteristic data set includes nose for the feature in the middle of the eyes and mouth and both of portrait
With the feature of face, and some characteristic points are obtained, each characteristic point has set up coordinate, e.g., nose or a mole on the face, then
Using the mole is as a characteristic point and sets up coordinate.
In step 4, the structural data portrait condition code of gained is also deposited into existing property data base.So that spy
Levy database more perfect.
The course of work of the present invention:When carrying out portrait certification, processing system receives the original photograph of input, first original
Picture element scan line by line is carried out on picture and obtains the characteristic point for all meeting doubtful portrait, then obtains one by one and meets doubtful portrait
Two-dimensional coordinate point of the characteristic point on original image, then relevant people is carried out one by one as characteristic to the two-dimensional coordinate point periphery of acquisition
According to scanning so as to be confirmed, by whole portrait characteristics and corresponding two-dimensional coordinate point, portrait characteristic data set is formed;It is right
The portrait characteristic data set of formation carries out effective portrait judgement one by one, if judging, the portrait characteristic is not effective portrait,
Terminate, if judging, the portrait characteristic is effective portrait, records effective portrait characteristic, so as to obtain effective people
Judge as after characteristic data set, also whether all completing effective portrait detection to portrait feature set, if finding there is untreated
Portrait characteristic, continues to carry out judgement processing to untreated portrait characteristic, if no discovery does not have untreated portrait
Characteristic, then carry out quality verification to effective portrait characteristic data set, extract the portrait characteristic for meeting quality requirement
Collection;Corresponding portrait characteristic is carried out to the portrait characteristic data set for meeting quality requirement to extract and carry out structural data
Conversion, so as to generate specific structural data portrait condition code, the structural data portrait condition code of gained is also deposited into now
Some property data bases;By the structural data portrait feature in structural data portrait condition code and existing property data base
Code carries out similarity system design and exported the similarity fractions that draw are compared, end process.
Personnel identity identification is carried out by the present invention, the degree of accuracy of the efficiency passed through and identification can be greatly lifted, together
When can also be collected into and be certified people's information.Discrimination and accuracy of identification can be effectively improved.
It the above is only the preferred embodiment of the present invention, it should be pointed out that for those skilled in the art, do not taking off
On the premise of from structure of the present invention, several modifications and improvements can also be made, these effects implemented all without the influence present invention
And practical applicability.
Claims (9)
1. a kind of portrait compares processing method, it is characterised in that this method also includes following process step:
Step 1:Receive the original photograph of input and portrait characteristic extraction is carried out to original photograph, form portrait characteristic
According to collection;
Step 2:Effective portrait judgement is carried out to portrait characteristic data set, effective portrait characteristic data set is obtained;
Step 3:Quality verification is carried out to effective portrait characteristic data set, the portrait characteristic that mass meets sets requirement is extracted
According to collection;
Step 4:The portrait characteristic data set that sets requirement is met to quality carries out corresponding portrait characteristic extraction and entered
Row structural data is changed, so as to generate specific structural data portrait condition code;
Step 5:By the structural data people in above-mentioned specific structural data portrait condition code and existing property data base
As condition code carries out similarity system design and is exported the similarity fractions drawn are compared.
2. a kind of portrait according to claim 1 compares processing method, it is characterised in that:
In step 1, the two-dimensional coordinate point of each portrait characteristic point is also obtained when extracting portrait characteristic, each portrait feature is obtained
The process of the two-dimensional coordinate point of point is as follows:
Picture element scan line by line is first carried out on original image and obtains the characteristic point for all meeting doubtful portrait, is then expired one by one
Two-dimensional coordinate point of the characteristic point of the doubtful portrait of foot on original image, then phase is carried out one by one to the two-dimensional coordinate point periphery of acquisition
The scanning of portrait characteristic is closed to be confirmed.
3. a kind of portrait according to claim 2 compares processing method, it is characterised in that:The characteristic point of the doubtful portrait
Eyes can be seen to meet.
4. a kind of portrait according to claim 1 or 2 compares processing method, it is characterised in that:
In step 1, portrait characteristic data set includes the two-dimensional coordinate point of portrait characteristic and portrait characteristic point.
5. a kind of portrait according to claim 1 compares processing method, it is characterised in that:
In step 2, portrait characteristic is concentrated to the portrait characteristic of formation according to effective portrait criterion of setting
Effective portrait judgement is carried out one by one, the portrait characteristic is not effective portrait if judging, is terminated, if judging the portrait feature
Data are effective portraits, then record, so as to obtain effective portrait characteristic data set.
6. a kind of portrait compares processing method according to claim 1 or 5, it is characterised in that:
In step 2, obtain after effective portrait characteristic data set, also whether portrait feature set is all completed effective portrait detect into
Row judges, if finding there is untreated portrait characteristic, continues to carry out judgement processing to untreated portrait characteristic,
If no discovery does not have untreated portrait characteristic, step 3 is carried out.
7. a kind of portrait compares processing method according to claim 1 or 5, it is characterised in that:
In step 3, when carrying out quality verification to effective portrait characteristic data set, according to effective portrait integrity degree standard of setting
Effective portrait characteristic is concentrated to carry out quality score effective portrait characteristic one by one, so as to draw satisfaction setting quality point
Several portrait characteristic data sets.
8. a kind of portrait according to claim 5 compares processing method, it is characterised in that:Effective portrait mark of the setting
Standard is the definition of the portrait picture of setting, the setting range of the angle of portrait candid photograph and can see eyes.
9. a kind of portrait according to claim 1 compares processing method, it is characterised in that:
In step 4, the structural data portrait condition code of gained is also deposited into existing property data base.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710227879.7A CN106991448A (en) | 2017-04-10 | 2017-04-10 | A kind of portrait compares processing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710227879.7A CN106991448A (en) | 2017-04-10 | 2017-04-10 | A kind of portrait compares processing method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106991448A true CN106991448A (en) | 2017-07-28 |
Family
ID=59415730
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710227879.7A Pending CN106991448A (en) | 2017-04-10 | 2017-04-10 | A kind of portrait compares processing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106991448A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108090420A (en) * | 2017-11-30 | 2018-05-29 | 睿视智觉(深圳)算法技术有限公司 | A kind of face identification method |
CN110706415A (en) * | 2019-10-14 | 2020-01-17 | 重庆国翰能源发展有限公司 | Charging pile control system based on biological recognition and face recognition method thereof |
CN111264951A (en) * | 2020-03-30 | 2020-06-12 | 杭州电子科技大学 | Non-contact cheongsam customized human body three-dimensional size measurement method based on deep learning |
CN113095396A (en) * | 2021-04-07 | 2021-07-09 | 南京了如指掌软件科技有限公司 | Method for digitizing and rapidly comparing picture features |
WO2021238733A1 (en) * | 2020-05-25 | 2021-12-02 | 聚好看科技股份有限公司 | Display device and image recognition result display method |
CN116311383A (en) * | 2023-05-16 | 2023-06-23 | 成都航空职业技术学院 | Intelligent building power consumption management system based on image processing |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102013011A (en) * | 2010-12-16 | 2011-04-13 | 重庆大学 | Front-face-compensation-operator-based multi-pose human face recognition method |
CN103279764A (en) * | 2013-06-27 | 2013-09-04 | 苏州福丰科技有限公司 | Real-name network authentication system based on face identification |
CN105550671A (en) * | 2016-01-28 | 2016-05-04 | 北京麦芯科技有限公司 | Face recognition method and device |
US20170098119A1 (en) * | 2015-10-01 | 2017-04-06 | Intelli-Vision | Methods and systems for extracting feature descriptors for an image |
-
2017
- 2017-04-10 CN CN201710227879.7A patent/CN106991448A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102013011A (en) * | 2010-12-16 | 2011-04-13 | 重庆大学 | Front-face-compensation-operator-based multi-pose human face recognition method |
CN103279764A (en) * | 2013-06-27 | 2013-09-04 | 苏州福丰科技有限公司 | Real-name network authentication system based on face identification |
US20170098119A1 (en) * | 2015-10-01 | 2017-04-06 | Intelli-Vision | Methods and systems for extracting feature descriptors for an image |
CN105550671A (en) * | 2016-01-28 | 2016-05-04 | 北京麦芯科技有限公司 | Face recognition method and device |
Non-Patent Citations (2)
Title |
---|
贾云伟 等: "基于结构的人脸验证", 《天津理工大学学报》 * |
高云飞: "非理想情况下基于SIFT算法的人脸识别研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108090420A (en) * | 2017-11-30 | 2018-05-29 | 睿视智觉(深圳)算法技术有限公司 | A kind of face identification method |
CN108090420B (en) * | 2017-11-30 | 2021-07-23 | 睿视智觉(深圳)算法技术有限公司 | Face recognition method |
CN110706415A (en) * | 2019-10-14 | 2020-01-17 | 重庆国翰能源发展有限公司 | Charging pile control system based on biological recognition and face recognition method thereof |
CN111264951A (en) * | 2020-03-30 | 2020-06-12 | 杭州电子科技大学 | Non-contact cheongsam customized human body three-dimensional size measurement method based on deep learning |
WO2021238733A1 (en) * | 2020-05-25 | 2021-12-02 | 聚好看科技股份有限公司 | Display device and image recognition result display method |
US11863829B2 (en) | 2020-05-25 | 2024-01-02 | Juhaokan Technology Co., Ltd. | Display apparatus and method for displaying image recognition result |
CN113095396A (en) * | 2021-04-07 | 2021-07-09 | 南京了如指掌软件科技有限公司 | Method for digitizing and rapidly comparing picture features |
CN116311383A (en) * | 2023-05-16 | 2023-06-23 | 成都航空职业技术学院 | Intelligent building power consumption management system based on image processing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106991448A (en) | A kind of portrait compares processing method | |
WO2020155939A1 (en) | Image recognition method and device, storage medium and processor | |
WO2021036436A1 (en) | Facial recognition method and apparatus | |
WO2019071664A1 (en) | Human face recognition method and apparatus combined with depth information, and storage medium | |
CN105740780B (en) | Method and device for detecting living human face | |
CN105740779B (en) | Method and device for detecting living human face | |
CN106529414A (en) | Method for realizing result authentication through image comparison | |
KR101781358B1 (en) | Personal Identification System And Method By Face Recognition In Digital Image | |
WO2016084072A1 (en) | Anti-spoofing system and methods useful in conjunction therewith | |
WO2018192448A1 (en) | People-credentials comparison authentication method, system and camera | |
CN108846306A (en) | A kind of identity card Compare System and method based on deep learning recognition of face | |
Kose et al. | Shape and texture based countermeasure to protect face recognition systems against mask attacks | |
CN107944416A (en) | A kind of method that true man's verification is carried out by video | |
CN111582118A (en) | Face recognition method and device | |
CN105844638A (en) | Method and system for discriminating genuine or counterfeit photos through camera noise | |
WO2013075295A1 (en) | Clothing identification method and system for low-resolution video | |
CN109492509A (en) | Personal identification method, device, computer-readable medium and system | |
CN106203322A (en) | A kind of identity authorization system based on hand back vein and palmmprint fusion image and method | |
CN107944395A (en) | A kind of method and system based on neutral net verification testimony of a witness unification | |
CN110348366B (en) | Automatic optimal face searching method and device | |
JP2013218605A (en) | Image recognition device, image recognition method, and program | |
CN107025435A (en) | A kind of face recognition processing method and system | |
JP2003178304A (en) | Face image retrieving device, face image retrieving method and program for executing method on computer | |
WO2023028947A1 (en) | Palm vein non-contact three-dimensional modeling method and apparatus, and authentication method | |
CN107133586A (en) | A kind of authentication method of calligraphy class historical relic |
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: 20170728 |