CN106845365A - For the method for detecting human face of student attendance - Google Patents

For the method for detecting human face of student attendance Download PDF

Info

Publication number
CN106845365A
CN106845365A CN201611239037.5A CN201611239037A CN106845365A CN 106845365 A CN106845365 A CN 106845365A CN 201611239037 A CN201611239037 A CN 201611239037A CN 106845365 A CN106845365 A CN 106845365A
Authority
CN
China
Prior art keywords
facial characteristics
ratio
head
area
student
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
Application number
CN201611239037.5A
Other languages
Chinese (zh)
Inventor
龙珑
邓伟
利基林
陆建波
元昌安
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
GUANGXI TUMOUR RESEARCH INSTITUTE
Guangxi Teachers College
Original Assignee
GUANGXI TUMOUR RESEARCH INSTITUTE
Guangxi Teachers College
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by GUANGXI TUMOUR RESEARCH INSTITUTE, Guangxi Teachers College filed Critical GUANGXI TUMOUR RESEARCH INSTITUTE
Priority to CN201611239037.5A priority Critical patent/CN106845365A/en
Publication of CN106845365A publication Critical patent/CN106845365A/en
Pending legal-status Critical Current

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
    • G06V40/161—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
    • G06V40/16—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
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
    • G07C1/10—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people together with the recording, indicating or registering of other data, e.g. of signs of identity

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Geometry (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses a kind of method for detecting human face for student attendance, comprise the following steps：The front head picture of student is first gathered, and picture is chosen into each facial characteristics region and head zone by setting shape；Calculate each facial characteristics region area of selection and the ratio of head zone area respectively again, and ratio is preserved by each facial characteristics classification of every student；Obtain the raw picture of studying diligently that needs checking, and picture is intercepted into out head portion by face recognition technology, each facial characteristics region area of target student and the ratio of head zone area are calculated again, then contrasted with the data for preserving, if the facial characteristics for having predetermined number coincide, you can judge the student attendance.The present invention has good fault-tolerance, and face can be still detected in the case where the face more than half is occluded.

Description

For the method for detecting human face of student attendance
Technical field
Face datection field is carried out the present invention relates to machine.It is more particularly related to a kind of be used for student attendance Method for detecting human face.
Background technology
In existing Student Attendance System, often because student is crowded, the situation that face is occluded is caused, in such case Under, machine cannot preferably detect face, and then cannot accurately complete work attendance task, meanwhile, some attendance checking systems are not having When photographing the face of completion, work attendance task cannot be also completed, against these problems, urgent need is a kind of to receive the complete of arbitrary size There is the method that the face-image of the different scale of any position in head portrait can carry out Face datection in whole head portrait, so as to reach In the case where student is crowded, also can preferably recognize and success work attendance student.
The content of the invention
It is an object of the invention to solve at least the above, and provide the advantage that at least will be described later.
In order to realize these purposes of the invention and further advantage, there is provided a kind of face inspection for student attendance Survey method, it is characterised in that comprise the following steps：
The front head picture of student is first gathered, and picture is chosen into each facial characteristics region and header area by setting shape Domain.
Calculate each facial characteristics region area of selection and the ratio of head zone area respectively again, and ratio is pressed every Each facial characteristics classification of student is preserved.
The raw picture of studying diligently that needs checking is obtained, and picture is intercepted into out head portion by face recognition technology, then calculated Each facial characteristics region area of target student and the ratio of head zone area, are then contrasted with the data for preserving, if The facial characteristics for having predetermined number coincide, you can judge the student attendance.
Preferably, described setting is shaped as rectangle, then the ratio of facial characteristics region area and head zone area Computational methods be：
Step a, the pixel-matrix that the picture is adjusted to M × M, are set up as the origin of coordinates with a certain angle point of picture and sat Mark system, chooses a certain facial characteristics and head, and boundary point is represented with coordinate value with rectangle；
Step b, the ratios delta w that facial characteristics region area and head zone area are calculated by boundary point coordinate value：
Wherein, ABCD is head zone, and A point coordinates is (xa, ya), B point coordinates is (xb, yb), C point coordinates is (xc, yc), D point coordinates is (xd, yd), EFGH is defined area, and E point coordinates is (xe, ye), F point coordinates is (xf, yf), G point coordinates is (xg, yg), H point coordinates is (xh, yh), λ is correction factor, and its span is between 0-0.25.
Preferably, facial characteristics includes hair, eyes, nose, ear, face and beard part.
Preferably, the mode for obtaining picture is to treat work attendance student with different angles respectively with multiple cameras to be clapped Take the photograph.
Preferably, the shooting interval time of camera be 0.5s, shooting time section for time break with give a course after 15min。
Preferably, the setting height of camera is in 2-2.5m, line and the horizontal plane of camera and farthest shooting point Angle is not less than 25 °.
Preferably, plurality of pictures is shot to same student using multiple cameras, the same facial of plurality of pictures is special Levy and be respectively calculated, and take maximum therein and contrasted with the data for preserving.
Preferably, described setting is shaped as rectangle, circle, ellipse, rhombus and triangle, then facial characteristics region Area is with the computational methods of the ratio of head zone area：
Step one, a certain facial characteristics and head are chosen with rectangle, and boundary point is represented with coordinate value, by boundary point Coordinate value calculates the first ratio of facial characteristics region area and head zone area；
Step 2, a certain facial characteristics and head are chosen with circle, and boundary point is represented with coordinate value, by boundary point Coordinate value calculates the second ratio of facial characteristics region area and head zone area；
Step 3, a certain facial characteristics and head are chosen with ellipse, and boundary point is represented with coordinate value, by border Point coordinates value calculates the 3rd ratio of facial characteristics region area and head zone area；
Step 4, a certain facial characteristics and head are chosen with triangle, and boundary point is represented with coordinate value, by border Point coordinates value calculates the 4th ratio of facial characteristics region area and head zone area；
Step 5, a certain facial characteristics and head are chosen with rhombus, and boundary point is represented with coordinate value, by boundary point Coordinate value calculates the 5th ratio of facial characteristics region area and head zone area；
Ratio=the first ratio * the second ratios of 0.3+ * of step 6, facial characteristics region area and head zone area The ratio * 0.1 of the 3rd the 4th ratio * 0.1+ of ratio * 0.3+ of 0.2+ the 5th.
The present invention at least includes following beneficial effect：
1st, the present invention has good fault-tolerance in work attendance Severe blockage, in the case where the face more than half is occluded Face can still be detected.
2nd, the present invention can also carry out Face datection when needing checking and studying diligently and give birth to and lean to one side to walk about.
Further advantage of the invention, target and feature embody part by following explanation, and part will also be by this The research and practice of invention and be understood by the person skilled in the art.
Specific embodiment
With reference to embodiment, the present invention is described in further detail, to make those skilled in the art with reference to specification Word can be implemented according to this.
Embodiment 1：
The front head picture of a certain student is first gathered, picture is adjusted to 256 × 256 pixel-matrix, with picture Upper left angle point sets up coordinate system for the origin of coordinates, does that transverse axis is positive and the longitudinal axis is positive along the length and cross direction of picture respectively, with setting Fixed rectangular shape chooses eye portion and head, and the rectangle of eye portion is represented with EFGH, wherein E point coordinates for (84, 105), F point coordinates is (171,105), and G point coordinates is (84,118), and H point coordinates is (171,118), and head is represented with ABCD, Wherein A point coordinates is (200,30), and B point coordinates is (55,30), and C point coordinates is (55,250), and D point coordinates is (200,250), The coordinate value of ABCD and EFGH is substituted into formula：
λ=0, the eye areas area of calculating and the ratio 3.9% of head zone area are taken, it is same as stated above to calculate The ratio that hair zones area is obtained with head zone area is 21.4%, and nasal area area is with the ratio of head zone area 11.2%, the ratio of face region area and head zone area is 10.4%, ear region area and head zone area Ratio is 11.4%, and beard region area is 11.4%, also some facial characteristics, such as eye with the ratio of head zone area Mirror, ear nail etc., do not enumerate herein, by these data preserve, and set coincide face number of features be three or three with On, i.e. the life judgement is turned out for work.
Allow the student front to be passed by face of camera arrangement, and lower half of face is covered with object, the picture that then will be photographed is used Face recognition technology intercepts out head portion, and the picture of head portion is adjusted to 256 × 256 pixel-matrix, with picture Upper left angle point sets up coordinate system for the origin of coordinates, does that transverse axis is positive and the longitudinal axis is positive along the length and cross direction of picture respectively, with setting Fixed rectangular shape chooses eye portion and head, due to being that front is passed by, therefore selects eye portion with previous gathered data one Cause, equally, in the case where upper face is exposed, moreover it is possible to obtain the region area and the ratio of head zone area of hair and nose Value is consistent with previous gathered data, has reached the requirement that three facial characteristics match, it is possible to judge the student attendance.
Embodiment 2：
The front head picture of a certain student is first gathered, picture is adjusted to 256 × 256 pixel-matrix, with picture Upper left angle point sets up coordinate system for the origin of coordinates, does that transverse axis is positive and the longitudinal axis is positive along the length and cross direction of picture respectively, with setting Fixed rectangular shape chooses eye portion and head, and the rectangle of eye portion is represented with EFGH, wherein E point coordinates for (84, 105), F point coordinates is (171,105), and G point coordinates is (84,118), and H point coordinates is (171,118), and head is represented with ABCD, Wherein A point coordinates is (200,30), and B point coordinates is (55,30), and C point coordinates is (55,250), and D point coordinates is (200,250), The coordinate value of ABCD and EFGH is substituted into formula：
λ=0 is taken, it is 3.9% to calculate eye areas area with the ratio of head zone area, as stated above same meter Calculate the ratio of hair zones area and head zone area is 21.4%, the ratio of nasal area area and head zone area It is 11.2%, the ratio of face region area and head zone area is 10.4%, ear region area and head zone area Ratio be 11.4%, the ratio of beard region area and head zone area is 11.4%, also some facial characteristics, such as Glasses, ear nail etc., do not enumerate herein.
The student is allowed to lean to one side 45 ° to be passed by face of camera arrangement, the picture face recognition technology that then will be photographed is intercepted out Head portion, the picture of head portion is adjusted to 256 × 256 pixel-matrix, and the upper left angle point with picture is as the origin of coordinates Coordinate system is set up, transverse axis forward direction is done along the length and cross direction of picture respectively and the longitudinal axis is positive, eye is chosen with the rectangular shape of setting Eyeball part and head, the rectangle of eye portion represents with JKLM, and wherein J point coordinates is (112,107), K point coordinates for (162, 112), L point coordinates be (162,120), M point coordinates be (112,115), head is represented with NOPQ, wherein N point coordinates for (186, 35), O point coordinates is (42,22), and P point coordinates is (42,223), and Q point coordinates is (186,247), by the coordinate of JKLM and NOPQ Value substitutes into above-mentioned formula, takes λ=0.18, and the ratio for calculating eye areas area with head zone area is 3.9%, by above-mentioned The ratio that method equally calculates hair zones area and head zone area is 25.4%, nasal area area and head zone The ratio of area is 9.2%, and the ratio of face region area and head zone area is 10.4%, ear region area and head The ratio of region area is 11.4%, the ratio of beard region area and head zone area is 13.6%, and is above gathered Data Comparison understand, eye areas area, face region area and ear region area respectively with the ratio of head zone area Value all same, has reached the requirement that three facial characteristics match, it is possible to judge the student attendance.
Embodiment 3：
Two cameras at the drift angle setting of classroom doorframe two, the student to coming to class carries out work attendance, and the court of camera enters Door direction set with the angle swing at 45 ° of doorframe plane, door 2.2m high, before giving a course with give a course after 15min unlatching camera, every 0.5s Camera is shot once, and the ratio meter that facial characteristics area accounts for head area is carried out to two pictures that every student shoots simultaneously Calculate, take maximum with the Data Comparison being previously saved.
The known student that once attends class carries out No. 10 machine work attendances respectively for 53 people, and is checked with the mode called the roll, its Result see the table below：
As can be seen from the table, 80%, in 0-3.9%, accuracy rate is than existing for error range for the accuracy rate of machine work attendance Attendance checking system be higher by 10 percentage points, be primarily due to existing attendance checking system when student is crowded, to sheltering from part face The situation in portion can not be recognized and cause the work attendance that cannot succeed, and the present invention preferably resolves this problem, therefore accuracy rate is improved.
Embodiment 4：
To the work attendance stage on the basis of embodiment 2, the calculating that facial characteristics area accounts for the ratio of head area is done and is optimized, Single when being chosen with rectangle, nasal area area is 9.2% with the ratio of head zone area, and the data being previously saved are 11.2%, result of determination fails for pairing.
On the picture shot in work attendance to nasal area and head zone respectively with rectangle, circle, ellipse, rhombus and Triangle is chosen, and the first ratio, the second ratio, the 3rd ratio, the 4th ratio and the 5th ratio are then calculated respectively, point It is not：9.2%, 15.3%, 12.3%, 7.6%, 9.3%, ratio=the first of nasal area area and head zone area is compared The ratio * 0.1=11.2% of the 3rd the 4th ratio * 0.1+ of ratio * 0.3+ of value * 0.3+ the second ratio * 0.2+ the 5th, contrast was previously protected The data deposited are 11.2%, and result of determination is successful matching
From the above results, the computational methods after optimization improve Detection accuracy.
Although embodiment of the present invention is disclosed as above, it is not restricted to listed in specification and implementation method With, it can be applied to various suitable the field of the invention completely, for those skilled in the art, can be easily Other modification is realized, therefore under the universal limited without departing substantially from claim and equivalency range, the present invention is not limited In specific details and shown here as the embodiment with description.

Claims (8)

1. a kind of method for detecting human face for student attendance, it is characterised in that comprise the following steps：
The front head picture of student is first gathered, and picture is chosen into each facial characteristics region and head zone by setting shape；
Calculate each facial characteristics region area of selection and the ratio of head zone area respectively again, and ratio is pressed into every student Each facial characteristics classification preserve；
The raw picture of studying diligently that needs checking is obtained, and picture is intercepted into out head portion by face recognition technology, then calculate target Each facial characteristics region area of student and the ratio of head zone area, are then contrasted, with the data for preserving if having pre- Fixed number purpose facial characteristics coincide, you can judge the student attendance.
2. the method for detecting human face of student attendance is used for as claimed in claim 1, it is characterised in that described setting is shaped as Rectangle, then facial characteristics region area be with the computational methods of the ratio of head zone area：
Step a, the pixel-matrix that the picture is adjusted to M × M, coordinate is set up by the origin of coordinates of a certain angle point of picture System, chooses a certain facial characteristics and head, and boundary point is represented with coordinate value with rectangle；
Step b, the ratios delta w that facial characteristics region area and head zone area are calculated by boundary point coordinate value：
Δ w = ( x h - x f ) 2 + ( y h - y f ) 2 × ( x e - x f ) 2 + ( y e - ( 1 - λ ) y f ) 2 ( x d - x a ) 2 + ( y d - ( 1 - λ ) y a ) 2 × ( x b - x a ) 2 + ( y b - y a ) 2 ;
Wherein, ABCD is head zone, and A point coordinates is (xa, ya), B point coordinates is (xb, yb), C point coordinates is (xc, yc), D points Coordinate is (xd, yd), EFGH is defined area, and E point coordinates is (xe, ye), F point coordinates is (xf, yf), G point coordinates is (xg, yg), H point coordinates is (xh, yh), λ is correction factor, and its span is between 0-0.25.
3. the method for detecting human face of student attendance is used for as claimed in claim 1, it is characterised in that facial characteristics includes head Hair, eyes, nose, ear, face and beard part.
4. the as claimed in claim 1 method for detecting human face for being used for student attendance, it is characterised in that the mode for obtaining picture is Work attendance student is treated with multiple cameras with different angles respectively to be shot.
5. the method for detecting human face of student attendance is used for as claimed in claim 4, it is characterised in that the shooting interval of camera Time is 0.5s, shooting time section for time break with give a course after 15min.
6. the method for detecting human face of student attendance is used for as claimed in claim 4, it is characterised in that the setting of camera is highly In 2-2.5m, the line of camera and farthest shooting point is not less than 25 ° with the angle of horizontal plane.
7. the method for detecting human face of student attendance is used for as claimed in claim 4, it is characterised in that use multiple cameras pair Same student shoots plurality of pictures, and the same facial feature of plurality of pictures is respectively calculated, and take maximum therein with The data of preservation are contrasted.
8. the method for detecting human face of student attendance is used for as claimed in claim 1, it is characterised in that described setting is shaped as Rectangle, circle, ellipse, rhombus and triangle, then the calculating side of the ratio of facial characteristics region area and head zone area Method is：
Step one, a certain facial characteristics and head are chosen with rectangle, and boundary point is represented with coordinate value, by border point coordinates Value calculates the first ratio of facial characteristics region area and head zone area；
Step 2, a certain facial characteristics and head are chosen with circle, and boundary point is represented with coordinate value, by border point coordinates Value calculates the second ratio of facial characteristics region area and head zone area；
Step 3, a certain facial characteristics and head are chosen with ellipse, and boundary point is represented with coordinate value, sat by boundary point Scale value calculates the 3rd ratio of facial characteristics region area and head zone area；
Step 4, a certain facial characteristics and head are chosen with triangle, and boundary point is represented with coordinate value, sat by boundary point Scale value calculates the 4th ratio of facial characteristics region area and head zone area；
Step 5, a certain facial characteristics and head are chosen with rhombus, and boundary point is represented with coordinate value, by border point coordinates Value calculates the 5th ratio of facial characteristics region area and head zone area；
Ratio=the first ratio * 0.3+ the second ratio * 0.2+ of step 6, facial characteristics region area and head zone area The ratio * 0.1 of three the 4th ratio * 0.1+ of ratio * 0.3+ the 5th.
CN201611239037.5A 2016-12-28 2016-12-28 For the method for detecting human face of student attendance Pending CN106845365A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611239037.5A CN106845365A (en) 2016-12-28 2016-12-28 For the method for detecting human face of student attendance

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611239037.5A CN106845365A (en) 2016-12-28 2016-12-28 For the method for detecting human face of student attendance

Publications (1)

Publication Number Publication Date
CN106845365A true CN106845365A (en) 2017-06-13

Family

ID=59114571

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611239037.5A Pending CN106845365A (en) 2016-12-28 2016-12-28 For the method for detecting human face of student attendance

Country Status (1)

Country Link
CN (1) CN106845365A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109040267A (en) * 2018-08-13 2018-12-18 河南亚视软件技术有限公司 A kind of Education Administration Information System based on video
CN110555353A (en) * 2018-06-04 2019-12-10 北京嘀嘀无限科技发展有限公司 Action recognition method and device
CN111814702A (en) * 2020-07-13 2020-10-23 安徽兰臣信息科技有限公司 Child face recognition method based on adult face and child photo feature space mapping relation
CN112562216A (en) * 2020-12-01 2021-03-26 合肥大多数信息科技有限公司 Intelligent charging machine for electric power business hall
CN113469157A (en) * 2021-09-06 2021-10-01 深圳启程智远网络科技有限公司 Student attendance management system and method based on big data

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101329722A (en) * 2007-06-21 2008-12-24 上海北控智能科技有限公司 Human face recognition method for performing recognition algorithm based on neural network
CN101344914A (en) * 2007-07-09 2009-01-14 上海耀明仪表控制有限公司 Human face recognition method based on characteristic point
CN102722698A (en) * 2012-05-17 2012-10-10 上海中原电子技术工程有限公司 Method and system for detecting and tracking multi-pose face

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101329722A (en) * 2007-06-21 2008-12-24 上海北控智能科技有限公司 Human face recognition method for performing recognition algorithm based on neural network
CN101344914A (en) * 2007-07-09 2009-01-14 上海耀明仪表控制有限公司 Human face recognition method based on characteristic point
CN102722698A (en) * 2012-05-17 2012-10-10 上海中原电子技术工程有限公司 Method and system for detecting and tracking multi-pose face

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110555353A (en) * 2018-06-04 2019-12-10 北京嘀嘀无限科技发展有限公司 Action recognition method and device
CN110555353B (en) * 2018-06-04 2022-11-15 北京嘀嘀无限科技发展有限公司 Action recognition method and device
CN109040267A (en) * 2018-08-13 2018-12-18 河南亚视软件技术有限公司 A kind of Education Administration Information System based on video
CN111814702A (en) * 2020-07-13 2020-10-23 安徽兰臣信息科技有限公司 Child face recognition method based on adult face and child photo feature space mapping relation
CN112562216A (en) * 2020-12-01 2021-03-26 合肥大多数信息科技有限公司 Intelligent charging machine for electric power business hall
CN112562216B (en) * 2020-12-01 2022-06-14 合肥大多数信息科技有限公司 Intelligent charging machine for electric power business hall
CN113469157A (en) * 2021-09-06 2021-10-01 深圳启程智远网络科技有限公司 Student attendance management system and method based on big data
CN113469157B (en) * 2021-09-06 2021-12-17 深圳启程智远网络科技有限公司 Student attendance management system and method based on big data
WO2023029355A1 (en) * 2021-09-06 2023-03-09 深圳启程智远网络科技有限公司 Big data-based student attendance management system and method

Similar Documents

Publication Publication Date Title
CN106845365A (en) For the method for detecting human face of student attendance
CN104574321B (en) Image correcting method, image correcting apparatus and video system
TWI662433B (en) Living body detection method and device, and identity authentication method and device
CN101458763B (en) Automatic human face identification method based on image weighting average
WO2018040307A1 (en) Vivo detection method and device based on infrared visible binocular image
Juhong et al. Face recognition based on facial landmark detection
CN107609383A (en) 3D face identity authentications and device
CN107633165A (en) 3D face identity authentications and device
CN107748869A (en) 3D face identity authentications and device
CN105759971A (en) Method and system for automatically prompting distance from human eyes to screen
CN108304819B (en) Gesture recognition system and method, and storage medium
CN109073385A (en) A kind of localization method and aircraft of view-based access control model
CN109766785A (en) A kind of biopsy method and device of face
CN105205438A (en) Method of using infrared eyeball to track and control distance of eyes and screen and system thereof
CN108986094A (en) For the recognition of face data automatic update method in training image library
US11610437B2 (en) Face liveness detection systems and methods
CN105678251B (en) Face image processing process and device
TWI691937B (en) Method and device for filtering light spot, computer readable storage medium, processor, gaze tracking equipment
CN106937532B (en) System and method for detecting actual user
CN106203284B (en) Method for detecting human face based on convolutional neural networks and condition random field
CN105258680B (en) A kind of object pose measuring method and device
CN116311549A (en) Living body object identification method, apparatus, and computer-readable storage medium
US11132531B2 (en) Method for determining pose and for identifying a three-dimensional view of a face
CN105844227A (en) Driver identity authentication method for school bus safety
CN109815810A (en) A kind of biopsy method based on single camera

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

Application publication date: 20170613

RJ01 Rejection of invention patent application after publication