CN104318202A - Method and system for recognizing facial feature points through face photograph - Google Patents
Method and system for recognizing facial feature points through face photograph Download PDFInfo
- Publication number
- CN104318202A CN104318202A CN201410461784.8A CN201410461784A CN104318202A CN 104318202 A CN104318202 A CN 104318202A CN 201410461784 A CN201410461784 A CN 201410461784A CN 104318202 A CN104318202 A CN 104318202A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- point
- determined
- human
- 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
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- 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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a method and a system for recognizing facial feature points through a face photograph. The method comprises the following steps: 1) carrying out face detection to judge whether a face exists in an input image or not, and continuously executing a step 2) if the face is detected; and 2) determining the face feature points of the face in the image. In the step 1), a face image to be determined is matched with a face template, if the face image to be determined is matched with the face template, the face image to be determined is projected into face subspace, and whether the face image to be determined is the face or not is judged through feature sub-face technology. The invention utilizes a computer scientific processing means, can recognize facial feature positions and feature points through a single front face photograph and improves face recognition accuracy.
Description
Technical field
The present invention relates to recognition of face and reduction technique, particularly, relate to the method and system by human face photo identification face point.
Background technology
Society now, such as vision monitoring, long-distance education and human-computer interaction technology and security and various aspects all urgently wish to carry out authentication fast and effectively.Biological characteristic, because the stability of self and otherness, has become the Main Means of authentication.Face is a kind of very complicated changeable object, is also a kind of typical non-rigid object.
The face feature of people is very abundant, except shape and expression, also has the feature distribution of face.By studying the proportionate relationship between these features, the phase Sihe difference degree of different faces can be obtained.Carry out compared with status verifies with human body biological characteristics such as utilizing retina identification and fingerprint recognition, the features such as face recognition technology has intuitively, friendly and convenient, just more and more be subject to international academic community, business circles, government, the attention of public security department and national defense and military department and favor, be with a wide range of applications.
Two stages are roughly had to the research of recognition of face in prior art.First stage, mainly study the facial characteristics required for recognition of face, this stage feature of work is that identifying all depends on operating personnel, obviously can not complete the function automatically identified.Subordinate phase, mainly man-machine interactive cognitive phase, this stage work characteristics is some priori needing to utilize operator, can not break away from the intervention of people.
Therefore, be necessary to design a kind of technical scheme utilizing computer science process means to realize recognition of face, thus improve the accuracy of recognition of face.
Summary of the invention
For defect of the prior art, the object of this invention is to provide a kind of method and system by human face photo identification face point.
According to a kind of method by human face photo identification face point provided by the invention, comprise the steps:
Step 1: Face datection, to judge whether there is face in input picture, if face detected, then continues to perform step 2;
Step 2: the face feature point determining face in image.
Preferably, described step 1 comprises the steps:
Step 1.1: pre-service is carried out to image, comprising: illumination compensation process is carried out to image, and facial image to be determined in image is transformed to the position that presets and by the size scaling of facial image to be determined to the size preset;
Step 1.2: facial image to be determined and face template are carried out template matches, if coupling, then projects to face subspace by from facial image to be determined, determines whether face by the sub-face technology of feature.
Preferably, described step 2 comprises the steps:
Step 2.1: the priori first utilizing human face to construct, the peak valley of face-image intensity profile and frequency characteristic detect roughly the unique point of the point in the approximate region of eyes, nose, mouth, chin and described approximate region on face outline line as key;
Step 2.2: according to the parameter of the unique point of the described key initial parameter as shape template, wherein, the parameter of described shape reflects the variable part of character pair shape, described variable part eventually through the edge of shape and image, peak, paddy and gray-scale watermark dynamically adapt to be revised alternately.
Preferably, eyes are detected as follows:
Step I 1: in the facial image that step 1 detects, estimates the initial position of nose;
Step I 2: define two initial ranging rectangles, respectively to the approximate location growth residing for two, left and right;
Step I 3: the feature being starkly lower than facial gray scale according to human eye gray scale, utilizes search rectangular to find the edge of eye, finally navigates to the center of pupil.
Preferably, in step I 1, utilize the initial position of the ratio estimation nose in five, three front yard.
According to a kind of system by human face photo identification face point provided by the invention, comprise as lower device:
Human face detection device, for Face datection, to judge whether there is face in input picture, if detect face;
Feature point detection device, for determining the face feature point of face in image.
Preferably, described human face detection device comprises as lower device:
Pretreatment unit, for carrying out pre-service to image, comprising: carry out illumination compensation process to image, and facial image to be determined in image is transformed to the position that presets and by the size scaling of facial image to be determined to the size preset;
Template matches device, for facial image to be determined and face template are carried out template matches, if coupling, then projects to face subspace by from facial image to be determined, determines whether face by the sub-face technology of feature.
Preferably, described feature point detection device comprises the steps:
First treating apparatus, the peak valley of the priori constructed for first utilizing human face, face-image intensity profile and frequency characteristic detect roughly the unique point of the point in the approximate region of eyes, nose, mouth, chin and described approximate region on face outline line as key;
Second treating apparatus, for the parameter of the unique point according to described key as the initial parameter of shape template, wherein, the parameter of described shape reflects the variable part of character pair shape, described variable part eventually through the edge of shape and image, peak, paddy and gray-scale watermark dynamically adapt to be revised alternately.
Preferably, the second treating apparatus comprises eye detection device, and described eye detection device comprises as lower device:
Nose position estimation device, in the facial image that detects in human face detection device, estimates the initial position of nose;
Search rectangular customizing device, for defining two initial ranging rectangles, respectively to the approximate location growth residing for two, left and right;
Searcher, for being starkly lower than the feature of facial gray scale according to human eye gray scale, utilizing search rectangular to find the edge of eye, finally navigates to the center of pupil.
Preferably, described nose position estimation device, utilizes the initial position of the ratio estimation nose in five, three front yard.
Compared with prior art, the present invention has following beneficial effect:
The present invention utilizes computer science process means, can pass through individual face full face identification face position and unique point, improve the accuracy of recognition of face.
Accompanying drawing explanation
By reading the detailed description done non-limiting example with reference to the following drawings, other features, objects and advantages of the present invention will become more obvious:
Fig. 1 is the face features that the search strategy increased based on region obtains;
Fig. 2 is method flow diagram of the present invention.
Embodiment
Below in conjunction with specific embodiment, the present invention is described in detail.Following examples will contribute to those skilled in the art and understand the present invention further, but not limit the present invention in any form.It should be pointed out that to those skilled in the art, without departing from the inventive concept of the premise, some distortion and improvement can also be made.These all belong to protection scope of the present invention.
According to the method by human face photo identification face point provided by the invention, being in order to by individual face full face identification face position and unique point, is realized by the mode of Face datection and facial Feature Localization.
The described method by human face photo identification face point, comprises the steps:
Step 1: Face datection, to judge whether there is face in input picture.
Principle is: identify the feature on face Main Basis face, generally needs to do geometrical normalization algorithm and gray scale normalizing algorithm before carrying out feature extraction and classification to facial image.
Geometrical normalization algorithm face in image is transformed to same position and onesize according to Face detection result, gray scale normalization algorithm refers to and carries out the process such as illumination compensation to image, and illumination compensation can to a certain degree overcome the impact of illumination variation and improve resolution.
Detect in face process, first facial image to be determined and face template are carried out template matches, if coupling, so projected to face subspace, determine whether face by the sub-face technology of feature.
Wherein, template matches, refers to according to face characteristic, facial image is divided into 14 zoness of different, represents this region by the gray-scale statistical value in each region, with the average gray normalization of whole sample, thus obtains the face template that represents by proper vector.By the method for unsupervised learning to training sample cluster, obtain reference template race.The template of test pattern is mated under certain distance measure with reference template, by threshold decision matching degree.
The basic thought of the sub-face technology of feature is: from the viewpoint of statistics, and find the fundamental element of facial image distribution, namely the proper vector of facial image sample set covariance matrix, characterizes facial image approx with this.These proper vectors are called eigenface (Eigenface).In fact, eigenface reflects the basic thought of the sub-face technology of hidden feature and is: eigenface reflects and lies in the information of face sample set inside and the structural relation of face.The proper vector of the sample set covariance matrix of eyes, cheek, lower jaw is called eigen eyes, feature jaw and feature lip, is referred to as the sub-face of feature.The sub-face of feature opens into subspace in corresponding image space, is called sub-face space.Calculate the projector distance of test pattern window in sub-face space, if video in window meets threshold value comparison condition, then judge that it is face.
Step 2: the face feature point determining face.
A kind of mode uses feature vector method: the method first determines the attribute such as size, position, distance of the image surface face profiles such as an iris, the wing of nose, the corners of the mouth, and then calculate their geometric feature, and these characteristic quantities form the proper vector that describes this image surface.Add people's trained priori engineer's scale relation to key feature point, namely from forehead to eyes, eyes to nostril, nostril is to face and face to the y coordinate proportionate relationship of lower jaw, be platform with embedded system, draw characteristic point position and contour shape.
On the basis of Face datection, facial key feature detection attempts to detect the position of main face feature point on face and the shape information of the major organs such as eyes and face.Gray-level projection tracing analysis, template matches, deformable template, Hough transform, Snake operator, be conventional method based on the Elastic Graph Matching technology of Gabor wavelet conversion, initiatively proterties model and active appearance models.
The main thought of deformable template is the shape information of the priori according to face characteristic to be detected, define the shape that a parameter describes, the parameter of this model reflects the variable part of character pair shape, as position, large low-angle etc., they eventually through the edge of model and image, peak, paddy and gray-scale watermark dynamically adapt to be revised alternately.
Because template deformation make use of the global information of characteristic area, therefore corresponding character shape can be detected preferably.Because deformable template will adopt optimized algorithm to carry out energy function minimization in parameter space, therefore the major defect of algorithm is 2 points:
(1) high to the degree of dependence of initial parameter values, be easy to be absorbed in Local Minimum;
(2) evaluation time is long.
For the problem of these two aspects, we have employed a kind of detection algorithm from coarse to fine:
Step 2.1: the priori first utilizing human face to construct, the peak valley of face-image intensity profile and frequency characteristic detect roughly the approximate region of eyes, nose, mouth, chin and the unique point of some keys, wherein, the unique point of described key refers to the point as face outline line in Fig. 1 obtains.
Step 2.2: then on this basis, gives the initial parameter of good template, thus significantly can improve speed and the precision of algorithm.Wherein, the initial parameter of described good template is exactly the unique point parameter obtained in step 2.1.
Further, eyes are facial most important features, and their accurate location is the key identified.
We also proposed a kind of eyes location technology increased based on region, this technology is on the basis of Face datection, take full advantage of upper left side and this characteristic of top-right gray scale paddy district that eyes are face centers in facial zone, accurately can locate two eye pupil centers fast.
This algorithm have employed the search strategy increased based on region, comprises the steps:
Step I 1: in the roughly face framework that Face detection algorithm provides, estimates the initial position of nose;
Wherein, utilize the initial position of the concept estimation nose in five, three front yard, the rule in described five, three front yard is specially: make a horizontal line by geisoma; Parallel lines are made by wing of nose lower edge.Like this, face is just divided into three deciles by two parallel lines: from hair line to glabella line; Glabella is to wing of nose lower edge; Wing of nose lower edge is to point, and upper, middle and lower respectively accounts for 1/3rd just, calls in it " three front yards ".And " five " refer to that, to homonymy hairline edge, the just length of what a eye outside canthus, between two eyes, be also the length of eyes, opposite side is an eye-length to hairline limit.Here it is " five ".
Step I 2: define two initial ranging rectangles, respectively to the approximate location growth residing for two, left and right.
Step I 3: the feature being starkly lower than facial gray scale according to human eye gray scale, utilizes search rectangular to find the edge of eye, finally navigates to the center of pupil.As shown in Figure 1.That is, the feature of facial gray scale is starkly lower than according to human eye gray scale.Be exactly first determine approximate location according to five, three front yard, then according to color value and search rectangular location.
Above specific embodiments of the invention are described.It is to be appreciated that the present invention is not limited to above-mentioned particular implementation, those skilled in the art can make various distortion or amendment within the scope of the claims, and this does not affect flesh and blood of the present invention.
Claims (10)
1., by a method for human face photo identification face point, it is characterized in that, comprise the steps:
Step 1: Face datection, to judge whether there is face in input picture, if face detected, then continues to perform step 2;
Step 2: the face feature point determining face in image.
2. the method by human face photo identification face point according to claim 1, it is characterized in that, described step 1 comprises the steps:
Step 1.1: pre-service is carried out to image, comprising: illumination compensation process is carried out to image, and facial image to be determined in image is transformed to the position that presets and by the size scaling of facial image to be determined to the size preset;
Step 1.2: facial image to be determined and face template are carried out template matches, if coupling, then projects to face subspace by from facial image to be determined, determines whether face by the sub-face technology of feature.
3. the method by human face photo identification face point according to claim 1, it is characterized in that, described step 2 comprises the steps:
Step 2.1: the priori first utilizing human face to construct, the peak valley of face-image intensity profile and frequency characteristic detect roughly the unique point of the point in the approximate region of eyes, nose, mouth, chin and described approximate region on face outline line as key;
Step 2.2: according to the parameter of the unique point of the described key initial parameter as shape template, wherein, the parameter of described shape reflects the variable part of character pair shape, described variable part eventually through the edge of shape and image, peak, paddy and gray-scale watermark dynamically adapt to be revised alternately.
4. the method by human face photo identification face point according to claim 3, is characterized in that, detect eyes as follows:
Step I 1: in the facial image that step 1 detects, estimates the initial position of nose;
Step I 2: define two initial ranging rectangles, respectively to the approximate location growth residing for two, left and right;
Step I 3: the feature being starkly lower than facial gray scale according to human eye gray scale, utilizes search rectangular to find the edge of eye, finally navigates to the center of pupil.
5. the method by human face photo identification face point according to claim 4, is characterized in that, in step I 1, utilizes the initial position of the ratio estimation nose in five, three front yard.
6. by a system for human face photo identification face point, it is characterized in that, comprise as lower device:
Human face detection device, for Face datection, to judge whether there is face in input picture, if detect face;
Feature point detection device, for determining the face feature point of face in image.
7. the system by human face photo identification face point according to claim 6, it is characterized in that, described human face detection device comprises as lower device:
Pretreatment unit, for carrying out pre-service to image, comprising: carry out illumination compensation process to image, and facial image to be determined in image is transformed to the position that presets and by the size scaling of facial image to be determined to the size preset;
Template matches device, for facial image to be determined and face template are carried out template matches, if coupling, then projects to face subspace by from facial image to be determined, determines whether face by the sub-face technology of feature.
8. the system by human face photo identification face point according to claim 6, is characterized in that, described feature point detection device comprises the steps:
First treating apparatus, the peak valley of the priori constructed for first utilizing human face, face-image intensity profile and frequency characteristic detect roughly the unique point of the point in the approximate region of eyes, nose, mouth, chin and described approximate region on face outline line as key;
Second treating apparatus, for the parameter of the unique point according to described key as the initial parameter of shape template, wherein, the parameter of described shape reflects the variable part of character pair shape, described variable part eventually through the edge of shape and image, peak, paddy and gray-scale watermark dynamically adapt to be revised alternately.
9. the system by human face photo identification face point according to claim 8, it is characterized in that, the second treating apparatus comprises eye detection device, and described eye detection device comprises as lower device:
Nose position estimation device, in the facial image that detects in human face detection device, estimates the initial position of nose;
Search rectangular customizing device, for defining two initial ranging rectangles, respectively to the approximate location growth residing for two, left and right;
Searcher, for being starkly lower than the feature of facial gray scale according to human eye gray scale, utilizing search rectangular to find the edge of eye, finally navigates to the center of pupil.
10. the system by human face photo identification face point according to claim 9, is characterized in that, described nose position estimation device, utilizes the initial position of the ratio estimation nose in five, three front yard.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410461784.8A CN104318202A (en) | 2014-09-12 | 2014-09-12 | Method and system for recognizing facial feature points through face photograph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410461784.8A CN104318202A (en) | 2014-09-12 | 2014-09-12 | Method and system for recognizing facial feature points through face photograph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104318202A true CN104318202A (en) | 2015-01-28 |
Family
ID=52373433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410461784.8A Pending CN104318202A (en) | 2014-09-12 | 2014-09-12 | Method and system for recognizing facial feature points through face photograph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104318202A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104899905A (en) * | 2015-06-08 | 2015-09-09 | 深圳市诺比邻科技有限公司 | Face image processing method and apparatus |
| CN105184327A (en) * | 2015-10-30 | 2015-12-23 | 上海海事大学 | Vertex trisection strategy-based remote sensing image feature point matching method |
| CN105205482A (en) * | 2015-11-03 | 2015-12-30 | 北京英梅吉科技有限公司 | Quick facial feature recognition and posture estimation method |
| CN105844727A (en) * | 2016-03-18 | 2016-08-10 | 中兴智能视觉大数据技术（湖北）有限公司 | Intelligent dynamic human face recognition attendance checking record management system |
| CN105892612A (en) * | 2015-11-27 | 2016-08-24 | 乐视致新电子科技（天津）有限公司 | Method and apparatus for powering off terminal |
| CN105893922A (en) * | 2015-08-11 | 2016-08-24 | 乐视体育文化产业发展（北京）有限公司 | Bicycle unlocking method and device and bicycle |
| CN106909880A (en) * | 2017-01-16 | 2017-06-30 | 北京龙杯信息技术有限公司 | Facial image preprocess method in recognition of face |
| CN107169397A (en) * | 2016-03-07 | 2017-09-15 | 佳能株式会社 | Feature point detecting method and device, image processing system and monitoring system |
| CN107305622A (en) * | 2016-04-15 | 2017-10-31 | 北京市商汤科技开发有限公司 | A kind of human face five-sense-organ recognition methods, apparatus and system |
| CN107749062A (en) * | 2017-09-18 | 2018-03-02 | 深圳市朗形网络科技有限公司 | Image processing method and device |
| CN107767325A (en) * | 2017-09-12 | 2018-03-06 | 深圳市朗形网络科技有限公司 | Method for processing video frequency and device |
| CN109859112A (en) * | 2018-12-21 | 2019-06-07 | 航天信息股份有限公司 | A kind of method and system for realizing face completion |
| CN110223220A (en) * | 2019-06-14 | 2019-09-10 | 北京百度网讯科技有限公司 | A kind of method and apparatus handling image |
| CN110427815A (en) * | 2019-06-24 | 2019-11-08 | 特斯联（北京）科技有限公司 | Realize the method for processing video frequency and device of the effective contents interception of gate inhibition |
| CN113591533A (en) * | 2021-04-27 | 2021-11-02 | 浙江工业大学之江学院 | Anti-fatigue driving method, device, equipment and storage medium based on road monitoring |
-
2014
- 2014-09-12 CN CN201410461784.8A patent/CN104318202A/en active Pending
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104899905A (en) * | 2015-06-08 | 2015-09-09 | 深圳市诺比邻科技有限公司 | Face image processing method and apparatus |
| CN104899905B (en) * | 2015-06-08 | 2017-09-29 | 深圳市诺比邻科技有限公司 | Face image processing process and device |
| CN105893922A (en) * | 2015-08-11 | 2016-08-24 | 乐视体育文化产业发展（北京）有限公司 | Bicycle unlocking method and device and bicycle |
| CN105184327A (en) * | 2015-10-30 | 2015-12-23 | 上海海事大学 | Vertex trisection strategy-based remote sensing image feature point matching method |
| CN105184327B (en) * | 2015-10-30 | 2018-10-23 | 上海海事大学 | A kind of Characteristics of The Remote Sensing Images point matching process dividing strategy based on vertex three |
| CN105205482A (en) * | 2015-11-03 | 2015-12-30 | 北京英梅吉科技有限公司 | Quick facial feature recognition and posture estimation method |
| CN105205482B (en) * | 2015-11-03 | 2018-10-26 | 北京英梅吉科技有限公司 | Fast face feature recognition and posture evaluation method |
| CN105892612A (en) * | 2015-11-27 | 2016-08-24 | 乐视致新电子科技（天津）有限公司 | Method and apparatus for powering off terminal |
| CN107169397A (en) * | 2016-03-07 | 2017-09-15 | 佳能株式会社 | Feature point detecting method and device, image processing system and monitoring system |
| CN105844727A (en) * | 2016-03-18 | 2016-08-10 | 中兴智能视觉大数据技术（湖北）有限公司 | Intelligent dynamic human face recognition attendance checking record management system |
| CN107305622A (en) * | 2016-04-15 | 2017-10-31 | 北京市商汤科技开发有限公司 | A kind of human face five-sense-organ recognition methods, apparatus and system |
| CN106909880A (en) * | 2017-01-16 | 2017-06-30 | 北京龙杯信息技术有限公司 | Facial image preprocess method in recognition of face |
| CN107767325A (en) * | 2017-09-12 | 2018-03-06 | 深圳市朗形网络科技有限公司 | Method for processing video frequency and device |
| CN107749062A (en) * | 2017-09-18 | 2018-03-02 | 深圳市朗形网络科技有限公司 | Image processing method and device |
| CN107749062B (en) * | 2017-09-18 | 2020-10-30 | 深圳市朗形网络科技有限公司 | Image processing method and device |
| CN109859112A (en) * | 2018-12-21 | 2019-06-07 | 航天信息股份有限公司 | A kind of method and system for realizing face completion |
| CN109859112B (en) * | 2018-12-21 | 2023-09-26 | 航天信息股份有限公司 | Method and system for realizing face completion |
| CN110223220A (en) * | 2019-06-14 | 2019-09-10 | 北京百度网讯科技有限公司 | A kind of method and apparatus handling image |
| CN110427815A (en) * | 2019-06-24 | 2019-11-08 | 特斯联（北京）科技有限公司 | Realize the method for processing video frequency and device of the effective contents interception of gate inhibition |
| CN113591533A (en) * | 2021-04-27 | 2021-11-02 | 浙江工业大学之江学院 | Anti-fatigue driving method, device, equipment and storage medium based on road monitoring |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104318202A (en) | Method and system for recognizing facial feature points through face photograph | |
| CN108921100B (en) | Face recognition method and system based on visible light image and infrared image fusion | |
| CN103632132B (en) | Face detection and recognition method based on skin color segmentation and template matching | |
| CN104268932A (en) | 3D facial form automatic changing method and system | |
| Puhan et al. | Efficient segmentation technique for noisy frontal view iris images using Fourier spectral density | |
| CN102902986A (en) | Automatic gender identification system and method | |
| Li et al. | Efficient 3D face recognition handling facial expression and hair occlusion | |
| EP3680794A1 (en) | Device and method for user authentication on basis of iris recognition | |
| CN105335719A (en) | Living body detection method and device | |
| Rouhi et al. | A review on feature extraction techniques in face recognition | |
| CN106650574A (en) | Face identification method based on PCANet | |
| Bedre et al. | Comparative study of face recognition techniques: a review | |
| El Maghraby et al. | Detect and analyze face parts information using Viola-Jones and geometric approaches | |
| CN108268814A (en) | A kind of face identification method and device based on the fusion of global and local feature Fuzzy | |
| Duan et al. | Expression of Concern: Ethnic Features extraction and recognition of human faces | |
| CN106599785A (en) | Method and device for building human body 3D feature identity information database | |
| Jana et al. | Age group estimation using face features | |
| CN106611158A (en) | Method and equipment for obtaining human body 3D characteristic information | |
| CN104021384A (en) | Face recognition method and device | |
| CN105844727A (en) | Intelligent dynamic human face recognition attendance checking record management system | |
| CN102495999A (en) | Face recognition method | |
| CN106778491B (en) | The acquisition methods and equipment of face 3D characteristic information | |
| Tin | Perceived gender classification from face images | |
| Alkoot et al. | A review on advances in iris recognition methods | |
| CN105550642A (en) | Gender identification method and system based on multi-scale linear difference characteristic low-rank expression |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150128 |
|
| WD01 | Invention patent application deemed withdrawn after publication |