CN108021893A - It is a kind of to be used to judging that student to attend class the algorithm of focus - Google Patents
It is a kind of to be used to judging that student to attend class the algorithm of focus Download PDFInfo
- Publication number
- CN108021893A CN108021893A CN201711281326.6A CN201711281326A CN108021893A CN 108021893 A CN108021893 A CN 108021893A CN 201711281326 A CN201711281326 A CN 201711281326A CN 108021893 A CN108021893 A CN 108021893A
- Authority
- CN
- China
- Prior art keywords
- student
- focus
- face
- eyes
- algorithm
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
-
- 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
-
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
Abstract
It is used to judging that student to attend class the algorithm of focus the present invention relates to a kind of.The present invention takes image by the common camera in classroom first, and being based on Viola Jones algorithms using existing Matlab carries out Face datection, obtains face features, and human eye is most directly to react student to attend class the facial characteristics of absorbed state.In the present invention, selected nose as auxiliary reference region, allow for two human eyes center and nose position can approximation regard a triangle as.It is into two dimensional surface, so as to more rapidly judge the focus of student face stereoscopic three-dimensional spatial transformation that face features, which are chosen, as object of reference.The finally various states according to existing for attending class student, present invention employs three kinds of modes to judge focus that student attends class, are that the algorithm that judges of student's side face focus, the algorithm of low (lift) the head focus judgement of student, the opening and closing degree of eyes judge the algorithm of the focus of student respectively.
Description
Technical field
The invention belongs to technical field of image processing and software algorithm module, is related to a kind of absorbed for judging that student attends class
The method of degree.
Background technology
In teaching process, the focus attended class of student is an important factor for influencing student performance and teaching efficiency, because
But numerous parent's issues that need special attentions.Overwhelming majority school is attending class specially by teacher naked eyes subjective judgement student at present
The situation of note degree, this mode do not only take up teacher's class period, disperse teacher's notice, and for student, naked eyes
Judgement accuracy rate it is low, the test and appraisal less effective for the effect that causes to attend class.Particularly, can not real-time statistics and analysis attend class student
Focus, so as to produce suitable hysteresis quality.For attending class, process middle school student produced problem cannot be corrected in time, Lao Shisuo
Whether the content said is understood by student, and a series of classroom problem of effect, the focus of student etc. of giving lessons of teacher, this
Invention designs a set of algorithm that can detect student's focus, and real-time tracking and evaluation and test student attend class focus.
There are following defect for the prior art：
A) focus of student of attending class judges that accuracy rate is very low mainly by teacher's naked eyes；
B) statistics of student's focus takes the class period, disperses teacher's notice；
C) judgement of focus and evaluation process are more by teacher's subjective factor；
D) recording process can not in time be corrected and give lessons there are problem, seriously affect quality of instruction there are hysteresis quality.
The content of the invention
Present invention the defects of be directed to the prior art, it is proposed that a kind of for judging that student attends class the algorithm of focus.
Technical solution adopted for solving the technical problem step of the present invention is as follows：
Step 1：Recognition of face, is based on Viola-Jones algorithms using existing Matlab and carries out Face datection, obtain
Face features, recognize the face of detected target, eyes, nose, face.
Step 2 (core content of this patent)：One of eye recognition, face features.Human eye is most direct reactology
The facial characteristics of raw absorbed state of attending class.Human eye has following characteristics：
A) human eye is distributed across face top half；
B) human eye is all to occur in pairs, is distributed in the left and right sides of human face region；
C) two sizes in left and right are almost consistent, essentially identical positioned at the region of face；
D) human eye is the line of centres angle very little of horizontal symmetrical, horizontal plane and two eyes；
E) human eye is in human face region, therefore human eye positioning action carries out in human face region；
F) face size and human eye size are proportional that the ratio of the area size of human eye and the area size of face exists
In one fixed scope；
Can largely avoid the wrong identification to human eye for above human eye feature, but the eyelid of people, eyebrow,
And intermediate zone of eyes and eyebrow etc. also can often disturb the judgement that human eye positions.Therefore this patent introduce one it is new
Auxiliary reference region：Face or nose.
For the image of human face region, nose and face can serve as good auxiliary reference coordinate, this be because
There is apparent characteristics of image and edge feature for nose face, and the position of nose face is relative to face and human eye
Changeless, it is exactly a little that the probability that nose face is blocked is smaller to also have, view data in video than it is more visible just
In identification.
In this patent, nose has been selected as referring to region, and the center and nose position for allowing for two human eyes can
One triangle is regarded as with approximation.
It is that face stereoscopic three-dimensional spatial transformation is simplified patent into two dimensional surface that face features, which are chosen, as object of reference
Calculation amount, the operation efficiency of raising, so as to more rapidly judge the focus of student.
Step 3：The judgement of student's side face focus, this patent distance of left eye to nose on known two dimensional surface are
The length of line segment AC, the distance of right eye to nose are the length of line segment BC.
The optimal threshold of this algorithm student's focus during this patent is realized is obtained by testing detection and data analysis
Value value range is that can judge whether detected student is absorbed in when the ratio of AC/BC is less than 1.24 or more than 0.86,
Above-mentioned threshold value value range needs user to be adjusted according to actual conditions such as video camera setting angle, camera lens visual field parameters.
Assuming that the ratio of the AC/BC drawn by realtime graphic is K, if K is more than 1.24 or less than 0.86 (i.e. AC/
BC<0.86 or AC/BC>1.24) judge to be detected student not to be absorbed in.
Step 4：Student comes back, focus of bowing judges：The method of second of judgement student's focus, is according to student
Come back in class period, the state bowed.Student attend class condition conversion be plane geometry expression be exactly in triangle ABC,
The distance of line segment AC is constant, and the distance of line segment AB and BC can shorten.Another kind expression is exactly that the angle of ∠ C in triangle can become
Greatly, student does not listen to the teacher conscientiously when the number of degrees of ∠ C are more than 66 degree of angles, and focus is inadequate；Same method obtains, when
The angle of ∠ C can also become larger therewith when student comes back, so working as ∠ C>When 66 °, judge that student's focus compares
It is low.
Step 5：The opening and closing degree of eyes judges the focus of student；It is to judge student according to the expansion ratio of student's eyeball
It is no be absorbed in listen to the teacher, be approximately an ellipse the eyes of people, represent the maximum height opened of human eye, the human eye that K is represented is most
Big width, ratio between the two are exactly the opening and closing degree of eyes.
The essence that human eye state judges is to judge the closure and open configuration of the eyes during blink.In order to preferably real
Existing human eye state judges, judges the closure state of eyes, in existing many documents, eye using the opening and closing degree of eyes herein
The opening and closing degree of eyeball is generally obtained using following calculating formula：
ZHD=(G/K) * 100%；
Since human eye opening and closing degree ZHD is a continuous variable, calculated to simplify, this patent is defined as follows conversion formula：
ZHD=(ZHD/ZHDmax) * 100%；
Wherein (0≤ZHD≤1), when the opening and closing degree for being detected target human eye is less than 20%, judges that being detected target is absorbed in
Spend low.By contrast, when the opening and closing degree for being detected target human eye is more than 20%, judge to be detected target focus height.
Beneficial effects of the present invention：
The present invention according to student attend class focus there are the drawbacks of, it is proposed that a kind of new calculation for judging student's focus
Method, more comprehensively, accurately, timely detects the focus that student attends class.The present invention changes traditional teacher's naked eyes identification student
The mode for focus of attending class, saves the hours of instruction of class-teaching of teacher, and feed back in time Parents of Students student attend class it is special
The height of note degree.Present invention employs three kinds of algorithms to judge focus that student attends class, are that student's side face focus is sentenced respectively
Fixed algorithm, algorithm that low (lift) the head focus of student judges, the opening and closing degree of eyes judge the algorithm of the focus of student.This
Three kinds of algorithms more real-time and accurately judge the focus that student attends class, at the same the present invention to improve teacher attend class quality with
And Parents of Students understands the absorbed situation of attending class of oneself child and plays an important role in real time.
Brief description of the drawings
Fig. 1 hardware unit schematic diagrames；
Fig. 2 algorithm main flow charts；
Fig. 3 side face focus decision flowcharts；
Fig. 4 human eye histograms；
Fig. 5 extract facial features；
Fig. 6 simplified plan views；
Fig. 7 comes back, focus of bowing decision flowchart；
Fig. 8 human eye simulation drawings；
Opening and closing degree represents figure under Fig. 9 eyes different conditions；
The opening and closing degree decision flowchart of Figure 10 eyes.
Specific embodiment
In order to simplify calculation amount, arithmetic speed is improved, this patent, which takes, turns the focus three-dimensional image attended class
Change the method for the plane of two dimension.It is the focus that student is judged by three kinds of algorithms in this patent innovative part.It is to learn respectively
Algorithm that raw side face focus judges, the algorithm of low (lift) the head focus judgement of student, the opening and closing degree of eyes judge student's
The algorithm of focus.
A) apparatus structure
As shown in Fig. 1 hardware unit schematic diagrames, the present apparatus images common scene using student classroom of attending class.
B) software algorithm
Software algorithm module is mainly by Image Acquisition, recognition of face and face features identification three parts composition.Wherein
The core of this patent is recognition of face and face features identification.
State that student attends class is determined by face features identification, recycles the invention algorithm of this patent to handle
These data, so as to draw a conclusion.
In order to simplify calculation amount, arithmetic speed is improved, this patent, which takes, turns the focus three-dimensional image attended class
Change the method for the plane of two dimension.It is the focus that student is judged by three kinds of algorithms in this patent innovative part, as Fig. 2 is calculated
Shown in method main flow chart.
C) this patent is based on Viola-Jones algorithms by existing Matlab and carries out Face datection, detects target person
The facial characteristics of face, recognizes face, eyes, nose, the face of detected target, and by rectangle these detected people
Face portion signature identification comes out.So as to obtain the rectangular coordinates of eyes and the length and width of rectangle of people, calculated to simplify,
Efficiency of algorithm is improved, eyes are seen as a pixel in image, with a coordinate representation.Assuming that target person in the picture
The left eye top left co-ordinate (i.e. the top left co-ordinate of rectangle) of thing is (x, y), and the length of rectangle is m, width n, such as Fig. 4 human eyes
Shown in histogram.
Therefore the pixel coordinate that target person left eye is calculated is：
Using same algorithm, the right eye centre coordinate that can obtain student is (x2, y2), and the coordinate of student's nose is
(x3,y3).As shown in Fig. 5 extract facial features.
Obtained after simplification such as Fig. 6 triangle projective planum schematic diagrames.
Defined according to vector, obtain the coordinate points of three points in plane.Assuming that these three coordinate points are A (a, b), B (c,
D), C (e, f), so that vectorial AB=(c-a, d-b) is obtained, vectorial BC=(e-c, f-d), cosB=(vectorial AB* vector BC)/
(∣ AB ∣ * ∣ BC ∣)=(c-a, d- b) * (e-c, f-d)/(∣ (c-a, d-b) ∣ * ∣ (e-c, f-d) ∣)；Or connect these three seats
Punctuate, forms a triangle.Assuming that a in this triangle, b, c is Atria edge lengths, and A, B, C are respectively side a, b, c
Corresponding angle.With the cosine law, obtain：
CosC=(a2+b2-c2)/(2*a*b)
CosB=(a2+c2-b2)/(2*a*c)
CosA=(c2+b2-a2)/(2*b*c)
Further according to known coordinate points in figure, obtained by Fig. 6：
The length that three sides of Fig. 6 triangles ABC can be obtained is respectively：
D) judgement of student's side face focus, its algorithm flow chart are as shown in Figure 3；
E) student comes back, focus of bowing judges, its algorithm flow chart is as shown in Figure 7；
F) listened to the teacher according to the expansion ratio of student's eyeball to judge whether student is absorbed in, as shown in Fig. 8 human eye simulation drawings, people
Eyes be approximately an ellipse.The maximum height that G expression human eyes are opened, the human eye maximum width that K is represented, between the two
Ratio be exactly eyes opening and closing degree.
The essence that human eye state judges is to judge the closure and open configuration of the eyes during blink, in order to preferably real
Existing human eye state judges, judges the closure state of eyes, in existing many documents, eye using the opening and closing degree of eyes herein
The opening and closing degree of eyeball is obtained using following calculating formula more：
ZHD=(G/K) * 100%
The different conditions of the degree of opening of human eye are as shown in Figure 9；
The opening and closing degree of eyes judges that its algorithm flow chart is as shown in Figure 10.
Claims (1)
1. a kind of be used to judging that student to attend class the algorithm of focus, it is characterised in that this method comprises the following steps：
S1) recognition of face, is based on Viola-Jones algorithms using existing Matlab and carries out Face datection, obtain face face
Feature, recognizes face, eyes, nose, the face of detected target；
S2 one of) eye recognition, face features, human eye are most directly to react student to attend class the facial characteristics of absorbed state；
In this patent, selected nose as referring to region, allow for two human eyes center and nose position can approximation see
Work is a triangle, choose face features for object of reference be face stereoscopic three-dimensional spatial transformation into two dimensional surface, it is simple
The calculation amount of patent, the operation efficiency of raising are changed, so as to more rapidly judge the focus of student；
S3) the judgement of student's side face focus, this patent distance of left eye to nose on known two dimensional surface is line segment AC's
Length, the distance of right eye to nose are the length of line segment BC；Obtain realizing in this patent by testing detection and data analysis
The optimal threshold value range of this algorithm student focus is the energy when the ratio of AC/BC is less than 1.24 or more than 0.86 in journey
Judge whether detected student is absorbed in, above-mentioned threshold value value range needs user according to video camera setting angle, camera lens
The actual conditions such as visual field parameter adjust；Assuming that the ratio of the AC/BC drawn by realtime graphic is K, if K be more than 1.24 or
Less than 0.86 (i.e. AC/BC<0.86 or AC/BC>1.24) judge to be detected student not to be absorbed in；
S4) student comes back, focus of bowing judges, is come back according in student's class period, and the state bowed, student attends class shape
The expression that state is converted into plane geometry is exactly in triangle ABC, and the distance of line segment AC is constant, and the distance of line segment AB and BC can become
Short, another kind expression is exactly that the angle of ∠ C in triangle can become larger, and student is not when the number of degrees of ∠ C are more than 66 degree of angles
Have and conscientiously listen to the teacher, focus is inadequate；Same method obtains, and the angle of ∠ C can also become larger therewith when student comes back, institute
With as ∠ C>When 66 °, judge student's focus than relatively low；
S5) opening and closing degree of eyes judges the focus of student；Listened according to the expansion ratio of student's eyeball to judge whether student is absorbed in
Class, is approximately an ellipse the eyes of people, and G represents the maximum height that human eye is opened, the human eye maximum width that K is represented,
Ratio between the two is exactly the opening and closing degree of eyes, and the opening and closing degree of eyes is generally obtained using following calculating formula：
ZHD=(G/K) * 100%；
Since human eye opening and closing degree ZHD is a continuous variable, calculated to simplify, this patent is defined as follows conversion formula：
ZHD=(ZHD/ZHDmax) * 100%；
Wherein (0≤ZHD≤1), when the opening and closing degree for being detected target human eye is less than 20%, judges to be detected target focus
It is low；By contrast, when the opening and closing degree for being detected target human eye is more than 20%, judge to be detected target focus height.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711281326.6A CN108021893A (en) | 2017-12-07 | 2017-12-07 | It is a kind of to be used to judging that student to attend class the algorithm of focus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711281326.6A CN108021893A (en) | 2017-12-07 | 2017-12-07 | It is a kind of to be used to judging that student to attend class the algorithm of focus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108021893A true CN108021893A (en) | 2018-05-11 |
Family
ID=62078760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711281326.6A Pending CN108021893A (en) | 2017-12-07 | 2017-12-07 | It is a kind of to be used to judging that student to attend class the algorithm of focus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108021893A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109522815A (en) * | 2018-10-26 | 2019-03-26 | 深圳博为教育科技有限公司 | A kind of focus appraisal procedure, device and electronic equipment |
| CN109635725A (en) * | 2018-12-11 | 2019-04-16 | 深圳先进技术研究院 | Detect method, computer storage medium and the computer equipment of student's focus |
| CN109670395A (en) * | 2018-10-29 | 2019-04-23 | 四川文轩教育科技有限公司 | A kind of student's focus monitoring method based on artificial intelligence |
| CN110009210A (en) * | 2019-03-26 | 2019-07-12 | 北京师范大学珠海分校 | A kind of student based on attention rate and focus listens to the teacher level comprehensive appraisal procedure |
| CN110135380A (en) * | 2019-05-22 | 2019-08-16 | 东北大学 | A kind of classroom focus knowledge method for distinguishing based on Face datection |
| CN110175501A (en) * | 2019-03-28 | 2019-08-27 | 重庆电政信息科技有限公司 | More people's scene focus recognition methods based on recognition of face |
| CN111242049A (en) * | 2020-01-15 | 2020-06-05 | 武汉科技大学 | Student online class learning state evaluation method and system based on facial recognition |
| CN111741250A (en) * | 2020-07-07 | 2020-10-02 | 全时云商务服务股份有限公司 | Method, device and equipment for analyzing participation degree of video conversation scene and storage medium |
| CN112183238A (en) * | 2020-09-10 | 2021-01-05 | 广州大学 | Method and system for detecting attention of remote education |
| EP4201041A4 (en) * | 2020-09-14 | 2023-11-01 | Huawei Technologies Co., Ltd. | Methods, systems, and media for context-aware estimation of student attention in online learning |
-
2017
- 2017-12-07 CN CN201711281326.6A patent/CN108021893A/en active Pending
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109522815A (en) * | 2018-10-26 | 2019-03-26 | 深圳博为教育科技有限公司 | A kind of focus appraisal procedure, device and electronic equipment |
| CN109670395A (en) * | 2018-10-29 | 2019-04-23 | 四川文轩教育科技有限公司 | A kind of student's focus monitoring method based on artificial intelligence |
| CN109635725A (en) * | 2018-12-11 | 2019-04-16 | 深圳先进技术研究院 | Detect method, computer storage medium and the computer equipment of student's focus |
| CN109635725B (en) * | 2018-12-11 | 2023-09-12 | 深圳先进技术研究院 | Method for detecting concentration degree of students, computer storage medium and computer equipment |
| CN110009210B (en) * | 2019-03-26 | 2023-05-26 | 北京师范大学珠海分校 | Comprehensive assessment method for student class listening level based on attention degree and concentration degree |
| CN110009210A (en) * | 2019-03-26 | 2019-07-12 | 北京师范大学珠海分校 | A kind of student based on attention rate and focus listens to the teacher level comprehensive appraisal procedure |
| CN110175501A (en) * | 2019-03-28 | 2019-08-27 | 重庆电政信息科技有限公司 | More people's scene focus recognition methods based on recognition of face |
| CN110135380A (en) * | 2019-05-22 | 2019-08-16 | 东北大学 | A kind of classroom focus knowledge method for distinguishing based on Face datection |
| CN110135380B (en) * | 2019-05-22 | 2023-07-11 | 东北大学 | Classroom concentration recognition method based on face detection |
| CN111242049A (en) * | 2020-01-15 | 2020-06-05 | 武汉科技大学 | Student online class learning state evaluation method and system based on facial recognition |
| CN111741250A (en) * | 2020-07-07 | 2020-10-02 | 全时云商务服务股份有限公司 | Method, device and equipment for analyzing participation degree of video conversation scene and storage medium |
| CN112183238A (en) * | 2020-09-10 | 2021-01-05 | 广州大学 | Method and system for detecting attention of remote education |
| CN112183238B (en) * | 2020-09-10 | 2024-01-05 | 广州大学 | Remote education attention detection method and system |
| EP4201041A4 (en) * | 2020-09-14 | 2023-11-01 | Huawei Technologies Co., Ltd. | Methods, systems, and media for context-aware estimation of student attention in online learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108021893A (en) | It is a kind of to be used to judging that student to attend class the algorithm of focus | |
| CN108108684B (en) | Attention detection method integrating sight detection | |
| CN105844252B (en) | A kind of fatigue detection method of face key position | |
| CN101339606B (en) | Human face critical organ contour characteristic points positioning and tracking method and device | |
| CN100561503C (en) | A kind of people's face canthus and corners of the mouth location and method and the device followed the tracks of | |
| CN102930252B (en) | A kind of sight tracing based on the compensation of neutral net head movement | |
| CN105825503B (en) | The image quality evaluating method of view-based access control model conspicuousness | |
| CN104766059B (en) | Quick accurate human-eye positioning method and the gaze estimation method based on human eye positioning | |
| CN104063700B (en) | The method of eye center point location in natural lighting front face image | |
| CN101930543B (en) | Method for adjusting eye image in self-photographed video | |
| CN104318603A (en) | Method and system for generating 3D model by calling picture from mobile phone photo album | |
| CN110287792A (en) | A kind of classroom Middle school students ' learning state real-time analysis method in nature teaching environment | |
| CN111079625A (en) | Control method for camera to automatically rotate along with human face | |
| CN104299011A (en) | Skin type and skin problem identification and detection method based on facial image identification | |
| CN109952594A (en) | Image processing method, device, terminal and storage medium | |
| CN106778676A (en) | A kind of notice appraisal procedure based on recognition of face and image procossing | |
| CN101916370A (en) | Method for processing non-feature regional images in face detection | |
| CN104091155A (en) | Rapid iris positioning method with illumination robustness | |
| CN108491784A (en) | The identification in real time of single feature towards large-scale live scene and automatic screenshot method | |
| CN104794693B (en) | A kind of portrait optimization method of face key area automatic detection masking-out | |
| CN102930278A (en) | Human eye sight estimation method and device | |
| CN104021550B (en) | Automatic positioning and proportion determining method for proportion of human face | |
| Wei et al. | Head pose estimation using gabor eigenspace modeling | |
| CN105205437B (en) | Side face detection method and device based on contouring head verifying | |
| CN106326823A (en) | Method and system for acquiring head image in picture |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180511 |
|
| WD01 | Invention patent application deemed withdrawn after publication |