CN105184238A - Human face recognition method and system - Google Patents
Human face recognition method and system Download PDFInfo
- Publication number
- CN105184238A CN105184238A CN201510530932.1A CN201510530932A CN105184238A CN 105184238 A CN105184238 A CN 105184238A CN 201510530932 A CN201510530932 A CN 201510530932A CN 105184238 A CN105184238 A CN 105184238A
- Authority
- CN
- China
- Prior art keywords
- picture
- similarity
- face
- module
- database
- 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
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention relates to a human face recognition method and a system. The method comprises the steps of inputting a to-be-recognized human face image; intercepting the human face image to obtain an image containing a face region; conducting the feature searching and matching operation for the image containing the face region with human face images stored in a database one by one, calculating the similarity of each human face image stored in the database with the image containing the face region, comparing the obtained similarity with a similarity threshold, and adding the human face image in a sequence of to-be-matched images on the condition that the similarity of above human face image is larger than the similarity threshold; selecting one human face image of the maximum similarity out of all to-be-matched images as a matched target. According to the technical scheme of the invention, based on the above method and the above system, a human face can be quickly and accurately recognized and the recognition resolution is high.
Description
Technical field
The present invention relates to technical field of face recognition, be specifically related to a kind of face identification method and system.
Background technology
Recognition of face is a kind of biological identification technology carrying out identification based on the face feature information of people.Image or the video flowing of face is contained with video camera or camera collection, and automatic detection and tracking face in the picture, and then the face detected is carried out to a series of correlation techniques of face, be usually also called Identification of Images, face recognition.Face identification system mainly comprises four ingredients, is respectively: man face image acquiring and detection, facial image pre-service, facial image feature extraction and matching and recognition.In these processes, image characteristics extraction plays key effect for whole identifying, at present, all complete coupling by extracting SIFT feature, this feature extraction mode is more single, the information that the picture that is beyond expression out enriches more, and then causes resolution low.
Summary of the invention
Technical matters to be solved by this invention is to provide a kind of face identification method and system, fast and accurately can identify face, and resolution is high.
The technical scheme that the present invention solves the problems of the technologies described above is as follows: a kind of face identification method, comprises the following steps:
Step 1, inputs facial image to be identified;
Step 2, carries out sectional drawing to described facial image to be identified, obtains the picture comprising human face region;
Step 3, the described picture including human face region is carried out signature search one by one with the face picture of preserving in database mate, calculate each width face picture and the described similarity including the picture of human face region in the middle of described database, and described similarity and similarity threshold are compared, if the similarity of the face picture in described database is greater than similarity threshold, then this picture is added sequence of pictures to be matched;
Step 4, selects the maximum face picture of similarity as coupling target from picture to be matched.
The invention has the beneficial effects as follows: by extracting the ColorSIFT characteristic information of picture, make relative to traditional feature extraction comparatively, adopt color characteristic and textural characteristics when feature extraction simultaneously, the information that picture enriches more can be given expression to, for recognition of face, resolution is higher.
On the basis of technique scheme, the present invention can also do following improvement:
Further, according to ColorSIFT feature, the described picture including human face region is carried out signature search one by one with the face picture of preserving in database in described step 3 to mate.
Further, Pasteur's distance is adopted to calculate the similarity of two width images in described step 4.
A kind of face identification system, comprises load module, pretreatment module, characteristic extracting module, matching module, identification module and database; Described load module is connected with pretreatment module, characteristic extracting module, matching module, identification module successively, described matching module and DataBase combining;
Load module, for inputting facial image to be identified;
Described pretreatment module, for carrying out sectional drawing to described facial image to be identified, obtaining the picture comprising human face region, and sending to characteristic extracting module;
Described characteristic extracting module, for extracting the feature comprising human face region picture, and sends to described matching module;
Described characteristic matching module, mate for the described picture including human face region is carried out signature search one by one with the face picture of preserving in database, calculate each width face picture and the described similarity including the picture of human face region in the middle of described database, and described similarity and similarity threshold are compared, if the similarity of the face picture in described database is greater than similarity threshold, then using this picture as sequence of pictures to be matched;
Described identification module, for selecting the maximum face picture of similarity as coupling target from picture to be matched.
Described database, for storing several face picture.
On the basis of technique scheme, the present invention can also do following improvement:
Further, described characteristic extracting module is for extracting ColorSIFT feature.
Further, described characteristic matching module is mated for the described picture including human face region being carried out signature search one by one with the face picture of preserving in database according to ColorSIFT feature.
Further, described characteristic matching module adopts Pasteur's distance to calculate the similarity of two width images.
The invention has the beneficial effects as follows: by extracting the ColorSIFT characteristic information of picture, make relative to traditional feature extraction comparatively, adopt color characteristic and textural characteristics when feature extraction simultaneously, the information that picture enriches more can be given expression to, for recognition of face, resolution is higher.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of a kind of face identification method of the present invention;
Fig. 2 is the structural representation of a kind of face identification system of the present invention;
Embodiment
Be described principle of the present invention and feature below in conjunction with accompanying drawing, example, only for explaining the present invention, is not intended to limit scope of the present invention.
As shown in Figure 1, a kind of face identification method, comprises the following steps:
Step 1, inputs facial image to be identified;
Step 2, carries out sectional drawing to described facial image to be identified, obtains the picture comprising human face region;
Step 3, the described picture including human face region is carried out signature search one by one with the face picture of preserving in database mate, calculate each width face picture and the described similarity including the picture of human face region in the middle of described database, and described similarity and similarity threshold are compared, if the similarity of the face picture in described database is greater than similarity threshold, then this picture is added sequence of pictures to be matched; According to ColorSIFT feature, the described picture including human face region is carried out signature search one by one with the face picture of preserving in database in described step 3 to mate.
Step 4, selects the maximum face picture of similarity as coupling target from picture to be matched, adopts Pasteur's distance to calculate the similarity of two width images in described step 4.
As shown in Figure 2, a kind of face identification system, comprises load module, pretreatment module, characteristic extracting module, matching module, identification module and database; Described load module is connected with pretreatment module, characteristic extracting module, matching module, identification module successively, described matching module and DataBase combining;
Load module, for inputting facial image to be identified;
Described pretreatment module, for carrying out sectional drawing to described facial image to be identified, obtaining the picture comprising human face region, and sending to characteristic extracting module;
Described characteristic extracting module, for extracting the feature comprising human face region picture, and sends to described matching module;
Described characteristic matching module, mate for the described picture including human face region is carried out signature search one by one with the face picture of preserving in database, calculate each width face picture and the described similarity including the picture of human face region in the middle of described database, and described similarity and similarity threshold are compared, if the similarity of the face picture in described database is greater than similarity threshold, then using this picture as sequence of pictures to be matched; Described characteristic extracting module is for extracting ColorSIFT feature.Described characteristic matching module is used for, according to ColorSIFT feature, the described picture including human face region is carried out signature search one by one with the face picture of preserving in database and mates.Described characteristic matching module adopts Pasteur's distance to calculate the similarity of two width images.
Described identification module, for selecting the maximum face picture of similarity as coupling target from picture to be matched.
Described database, for storing several face picture.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (7)
1. a face identification method, is characterized in that, comprises the following steps:
Step 1, inputs facial image to be identified;
Step 2, carries out sectional drawing to described facial image to be identified, obtains the picture comprising human face region;
Step 3, the described picture including human face region is carried out signature search one by one with the face picture of preserving in database mate, calculate each width face picture and the described similarity including the picture of human face region in the middle of described database, and described similarity and similarity threshold are compared, if the similarity of the face picture in described database is greater than similarity threshold, then this picture is added sequence of pictures to be matched;
Step 4, selects the maximum face picture of similarity as coupling target from picture to be matched.
2. a kind of face identification method according to claim 1, is characterized in that, according to ColorSIFT feature, the described picture including human face region is carried out signature search one by one with the face picture of preserving in database and mate in described step 3.
3. a kind of face identification method according to claim 1, is characterized in that, adopts Pasteur's distance to calculate the similarity of two width images in described step 4.
4. a face identification system, is characterized in that, comprises load module, pretreatment module, characteristic extracting module, matching module, identification module and database; Described load module is connected with pretreatment module, characteristic extracting module, matching module, identification module successively, described matching module and DataBase combining;
Load module, for inputting facial image to be identified;
Described pretreatment module, for carrying out sectional drawing to described facial image to be identified, obtaining the picture comprising human face region, and sending to characteristic extracting module;
Described characteristic extracting module, for extracting the feature comprising human face region picture, and sends to described matching module;
Described characteristic matching module, mate for the described picture including human face region is carried out signature search one by one with the face picture of preserving in database, calculate each width face picture and the described similarity including the picture of human face region in the middle of described database, and described similarity and similarity threshold are compared, if the similarity of the face picture in described database is greater than similarity threshold, then using this picture as sequence of pictures to be matched;
Described identification module, for selecting the maximum face picture of similarity as coupling target from picture to be matched;
Described database, for storing several face picture.
5. a kind of face identification system according to claim 4, it is characterized in that, described characteristic extracting module is for extracting ColorSIFT feature.
6. a kind of face identification system according to claim 4, is characterized in that, described characteristic matching module is used for, according to ColorSIFT feature, the described picture including human face region is carried out signature search one by one with the face picture of preserving in database and mates.
7. a kind of face identification system according to claim 4, is characterized in that, described characteristic matching module adopts Pasteur's distance to calculate the similarity of two width images.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510530932.1A CN105184238A (en) | 2015-08-26 | 2015-08-26 | Human face recognition method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510530932.1A CN105184238A (en) | 2015-08-26 | 2015-08-26 | Human face recognition method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105184238A true CN105184238A (en) | 2015-12-23 |
Family
ID=54906307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510530932.1A Pending CN105184238A (en) | 2015-08-26 | 2015-08-26 | Human face recognition method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105184238A (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295571A (en) * | 2016-08-11 | 2017-01-04 | 深圳市赛为智能股份有限公司 | The face identification method of illumination adaptive and system |
| CN106384445A (en) * | 2016-11-25 | 2017-02-08 | 钦州市高新技术产业服务中心 | Shopping mall object storage cabinet control system with fingerprint identification function |
| CN106408778A (en) * | 2016-11-25 | 2017-02-15 | 钦州市高新技术产业服务中心 | Face-identification control system of emporium object storing cabinet |
| CN106412674A (en) * | 2016-10-08 | 2017-02-15 | 广州华多网络科技有限公司 | Screenshot method and device for dynamic video |
| CN106886746A (en) * | 2016-12-27 | 2017-06-23 | 浙江宇视科技有限公司 | A kind of recognition methods and back-end server |
| WO2017162076A1 (en) * | 2016-03-24 | 2017-09-28 | 北京握奇数据股份有限公司 | Face identification method and system |
| CN107264469A (en) * | 2017-06-15 | 2017-10-20 | 深圳森阳环保材料科技有限公司 | A kind of VATS Vehicle Anti-Theft System based on recognition of face |
| CN107798308A (en) * | 2017-11-09 | 2018-03-13 | 石数字技术成都有限公司 | A kind of face identification method based on short-sighted frequency coaching method |
| CN107944427A (en) * | 2017-12-14 | 2018-04-20 | 厦门市美亚柏科信息股份有限公司 | Dynamic human face recognition methods and computer-readable recording medium |
| CN108052879A (en) * | 2017-11-29 | 2018-05-18 | 厦门瑞为信息技术有限公司 | A kind of method for reducing recognition of face misclassification rate |
| CN108429619A (en) * | 2018-01-18 | 2018-08-21 | 北京捷通华声科技股份有限公司 | Identity identifying method and system |
| CN108875654A (en) * | 2018-06-25 | 2018-11-23 | 深圳云天励飞技术有限公司 | A kind of face characteristic acquisition method and device |
| CN109117808A (en) * | 2018-08-24 | 2019-01-01 | 深圳前海达闼云端智能科技有限公司 | Face recognition method and device, electronic equipment and computer readable medium |
| CN109426769A (en) * | 2017-08-24 | 2019-03-05 | 合肥虹慧达科技有限公司 | The iris identification method and iris authentication system of face auxiliary |
| CN109508685A (en) * | 2018-11-23 | 2019-03-22 | 赵雷 | Power communication dispatching method based on face recognition technology |
| CN109753924A (en) * | 2018-12-29 | 2019-05-14 | 上海乂学教育科技有限公司 | It is a kind of for the face identification system of online education, method and application |
| CN109815845A (en) * | 2018-12-29 | 2019-05-28 | 深圳前海达闼云端智能科技有限公司 | Face recognition method and device and storage medium |
| CN109902644A (en) * | 2019-03-07 | 2019-06-18 | 北京海益同展信息科技有限公司 | Face identification method, device, equipment and computer-readable medium |
| CN109993039A (en) * | 2018-01-02 | 2019-07-09 | 上海银晨智能识别科技有限公司 | Portrait identification method and device, computer readable storage medium |
| CN111241930A (en) * | 2019-12-30 | 2020-06-05 | 航天信息股份有限公司 | Method and system for face recognition |
| CN111382604A (en) * | 2018-12-27 | 2020-07-07 | 深圳光启空间技术有限公司 | Face recognition method and system |
| CN111881322A (en) * | 2020-09-28 | 2020-11-03 | 成都睿沿科技有限公司 | Target searching method and device, electronic equipment and storage medium |
| CN112115785A (en) * | 2020-08-13 | 2020-12-22 | 力引万物(深圳)科技有限公司 | Picture face splitting identification method and identification system thereof |
-
2015
- 2015-08-26 CN CN201510530932.1A patent/CN105184238A/en active Pending
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017162076A1 (en) * | 2016-03-24 | 2017-09-28 | 北京握奇数据股份有限公司 | Face identification method and system |
| CN106295571A (en) * | 2016-08-11 | 2017-01-04 | 深圳市赛为智能股份有限公司 | The face identification method of illumination adaptive and system |
| CN106412674B (en) * | 2016-10-08 | 2019-04-23 | 广州华多网络科技有限公司 | The screenshot method and its device of dynamic video |
| CN106412674A (en) * | 2016-10-08 | 2017-02-15 | 广州华多网络科技有限公司 | Screenshot method and device for dynamic video |
| CN106408778A (en) * | 2016-11-25 | 2017-02-15 | 钦州市高新技术产业服务中心 | Face-identification control system of emporium object storing cabinet |
| CN106384445A (en) * | 2016-11-25 | 2017-02-08 | 钦州市高新技术产业服务中心 | Shopping mall object storage cabinet control system with fingerprint identification function |
| CN106886746A (en) * | 2016-12-27 | 2017-06-23 | 浙江宇视科技有限公司 | A kind of recognition methods and back-end server |
| CN106886746B (en) * | 2016-12-27 | 2020-07-28 | 浙江宇视科技有限公司 | Identification method and back-end server |
| CN107264469A (en) * | 2017-06-15 | 2017-10-20 | 深圳森阳环保材料科技有限公司 | A kind of VATS Vehicle Anti-Theft System based on recognition of face |
| CN109426769A (en) * | 2017-08-24 | 2019-03-05 | 合肥虹慧达科技有限公司 | The iris identification method and iris authentication system of face auxiliary |
| CN107798308A (en) * | 2017-11-09 | 2018-03-13 | 石数字技术成都有限公司 | A kind of face identification method based on short-sighted frequency coaching method |
| CN107798308B (en) * | 2017-11-09 | 2020-09-22 | 一石数字技术成都有限公司 | Face recognition method based on short video training method |
| CN108052879A (en) * | 2017-11-29 | 2018-05-18 | 厦门瑞为信息技术有限公司 | A kind of method for reducing recognition of face misclassification rate |
| CN107944427A (en) * | 2017-12-14 | 2018-04-20 | 厦门市美亚柏科信息股份有限公司 | Dynamic human face recognition methods and computer-readable recording medium |
| CN107944427B (en) * | 2017-12-14 | 2020-11-06 | 厦门市美亚柏科信息股份有限公司 | Dynamic face recognition method and computer readable storage medium |
| CN109993039A (en) * | 2018-01-02 | 2019-07-09 | 上海银晨智能识别科技有限公司 | Portrait identification method and device, computer readable storage medium |
| CN108429619A (en) * | 2018-01-18 | 2018-08-21 | 北京捷通华声科技股份有限公司 | Identity identifying method and system |
| CN108875654A (en) * | 2018-06-25 | 2018-11-23 | 深圳云天励飞技术有限公司 | A kind of face characteristic acquisition method and device |
| CN108875654B (en) * | 2018-06-25 | 2021-03-05 | 深圳云天励飞技术有限公司 | Face feature acquisition method and device |
| CN109117808A (en) * | 2018-08-24 | 2019-01-01 | 深圳前海达闼云端智能科技有限公司 | Face recognition method and device, electronic equipment and computer readable medium |
| CN109117808B (en) * | 2018-08-24 | 2020-11-03 | 深圳前海达闼云端智能科技有限公司 | Face recognition method and device, electronic equipment and computer readable medium |
| CN109508685A (en) * | 2018-11-23 | 2019-03-22 | 赵雷 | Power communication dispatching method based on face recognition technology |
| CN111382604A (en) * | 2018-12-27 | 2020-07-07 | 深圳光启空间技术有限公司 | Face recognition method and system |
| CN109815845A (en) * | 2018-12-29 | 2019-05-28 | 深圳前海达闼云端智能科技有限公司 | Face recognition method and device and storage medium |
| CN109753924A (en) * | 2018-12-29 | 2019-05-14 | 上海乂学教育科技有限公司 | It is a kind of for the face identification system of online education, method and application |
| CN109815845B (en) * | 2018-12-29 | 2022-03-29 | 达闼机器人有限公司 | Face recognition method and device and storage medium |
| CN109902644A (en) * | 2019-03-07 | 2019-06-18 | 北京海益同展信息科技有限公司 | Face identification method, device, equipment and computer-readable medium |
| CN111241930A (en) * | 2019-12-30 | 2020-06-05 | 航天信息股份有限公司 | Method and system for face recognition |
| CN112115785A (en) * | 2020-08-13 | 2020-12-22 | 力引万物(深圳)科技有限公司 | Picture face splitting identification method and identification system thereof |
| CN111881322A (en) * | 2020-09-28 | 2020-11-03 | 成都睿沿科技有限公司 | Target searching method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105184238A (en) | Human face recognition method and system | |
| CN103207898B (en) | A kind of similar face method for quickly retrieving based on local sensitivity Hash | |
| WO2019071664A1 (en) | Human face recognition method and apparatus combined with depth information, and storage medium | |
| US9508151B2 (en) | Systems, methods, and devices for image matching and object recognition in images using image regions | |
| CN100580691C (en) | Interactive human face identificiating system and method of comprehensive utilizing human face and humanbody auxiliary information | |
| CN109635686B (en) | Two-stage pedestrian searching method combining human face and appearance | |
| CN104731964A (en) | Face abstracting method and video abstracting method based on face recognition and devices thereof | |
| CN106991370B (en) | Pedestrian retrieval method based on color and depth | |
| CN103793697A (en) | Identity labeling method of face images and face identity recognition method of face images | |
| CN103679147A (en) | Method and device for identifying model of mobile phone | |
| CN106557728B (en) | Query image processing and image search method and device and monitoring system | |
| CN103577818A (en) | Method and device for recognizing image characters | |
| Khan et al. | Automatic target recognition in infrared imagery using dense hog features and relevance grouping of vocabulary | |
| US20180232400A1 (en) | Sketch-based image searching system using cell-orientation histograms and outline extraction based on medium-level features | |
| CN104951440B (en) | Image processing method and electronic equipment | |
| Galiyawala et al. | Person retrieval in surveillance using textual query: a review | |
| Bai et al. | A fast stroke-based method for text detection in video | |
| US9286707B1 (en) | Removing transient objects to synthesize an unobstructed image | |
| Hu et al. | Fast face detection based on skin color segmentation using single chrominance Cr | |
| CN104598876A (en) | Embedded face recognition system | |
| CN104199950B (en) | A kind of scientific paper searching method based on image similarity Rapid matching | |
| Huo et al. | Person re-identification based on multi-directional saliency metric learning | |
| Patravali et al. | Skin segmentation using YCBCR and RGB color models | |
| CN104050455A (en) | Skin color detection method and system | |
| CN103955708B (en) | Face photo library fast-reduction method for face synthesis portrait recognition |
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: 20151223 |
|
| RJ01 | Rejection of invention patent application after publication |