CN105389570A - Face angle determination method and system - Google Patents
Face angle determination method and system Download PDFInfo
- Publication number
- CN105389570A CN105389570A CN201510799520.8A CN201510799520A CN105389570A CN 105389570 A CN105389570 A CN 105389570A CN 201510799520 A CN201510799520 A CN 201510799520A CN 105389570 A CN105389570 A CN 105389570A
- Authority
- CN
- China
- Prior art keywords
- face
- deflection angle
- module
- characteristic information
- vertical deflection
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a face angle determination method and system. The method comprises the steps of: 1, obtaining a two-dimensional face photograph of a target person, and carrying out pre-processing on the face photograph; 2, extracting face characteristic information after the pre-processing; 3, inputting the face characteristic information extracted in the step 2 into a standard multidimensional face model establishing module, and establishing a multidimensional face photograph; 4, extracting face characteristic information in the multidimensional face photograph, wherein the face characteristic information at least includes coordinate values of a left pupil Le, a right pupil Re, a nose tip point J and a nose saddle point A; 5, calculating a horizontal deflection angle X of a face and a first vertical deflection angle Y and a second vertical deflection angle Z of the face; and 6, displaying the horizontal deflection angle X, the first vertical deflection angle Y and the second vertical deflection angle Z through a display module. The face angle determination method and system have the advantages that the error is small, and the efficiency is high.
Description
Technical field
The present invention relates to face angle judgment technology field, be specifically related to a kind of face angle decision method and system thereof.
Background technology
The domestic and international method to human face modeling has three classes substantially at present: the method based on model, the method based on face outward appearance and the method based on classification.
Method based on model is the geometric model and the unique point that utilize face, between model and image, set up corresponding relation, is then realized the estimation of human face posture by set or other method.First carry out the detection of unique point, generally adopt eyes, nose and mouth; Then set up three-dimensional model to face, constantly project three-dimensional feature point the unique point of approaching on image, and this method exists the shortcomings such as error rate is high at present.
Method based on face outward appearance is that the content of hypothesis human face posture and image exists mutual relation, such as gray scale, gradient etc., then by the sample that training is a large amount of, finds out this corresponding relation, thus carries out the estimation of attitude.Owing to needing a large amount of training sample image, different attitudes, illumination all can have an impact to the confirmation of relation, more complicated.
Method based on classification adopts the positive negative sample of training, obtains a statistical value according to sample, and this value utilized regression algorithm to calculate regression equation, thus the calculating of attitude is converted to the calculating of regression equation, obtains general angle.Although the method based on classification can find the change direction of human face posture easily, estimate human face posture or some difficulty by this parameter.
For this reason, be necessary to improve existing face angle decision method.
Summary of the invention
The object of the present invention is to provide a kind of error is little, efficiency is high face angle decision method and system thereof.
In order to achieve the above object, the technical solution used in the present invention is as follows:
A kind of face angle decision method, comprises the following steps:
The two-dimension human face photo of step 1, acquisition target person, and pre-service is carried out to human face photo;
Step 2, extract pretreated face characteristic information;
Step 3, the face characteristic information extracted in step 2 is inputted a standard multidimensional faceform and sets up in module, set up multidimensional human face photo;
Step 4, the face characteristic information extracted in multidimensional human face photo, this face characteristic information at least comprises the coordinate figure of left pupil Le, right pupil Re, prenasale J and nose saddle point A;
Step 5, calculate the X deflection angle X of face according to the coordinate figure of left pupil Le and right pupil Re, the first vertical deflection angle Y and the second vertical deflection angle Z of face is calculated according to the coordinate figure of prenasale J and nose saddle point A, wherein X is horizontal direction, Y is vertical direction, and Z is the direction outside vertical paper points to;
Step 6, by a display module reveal competence deflection angle X, the first vertical deflection angle Y and the second vertical deflection angle Z.
As a kind of preferred version, the coordinate figure of described left pupil Le and right pupil Re is respectively Le (x1, y1, z1), Re (x2, y2, z2); The account form of described X deflection angle X is: X=arctan ((y2-y1)/(x2-x1));
The coordinate of described prenasale J and nose saddle point A is respectively J (xn, yn, zn), A (xs, ys, zs);
The account form of described first vertical deflection angle Y is: Y=arctan ((xn-xs)/(zn-zs));
The account form of described second vertical deflection angle Z is: Z=arctan ((xn-xs)
2+ (zn-zs)
2/ (yn-ys)).
As a kind of preferred version, the pre-service of described human face photo comprises geometric manipulations, illumination compensation and histogram equalization.
As a kind of preferred version, the information shown by the display module in described step 6 comprises the multi-dimensional graphic information of face, and the markup information of X deflection angle X, the first vertical deflection angle Y and the second vertical deflection angle Z.
The present invention also provides a kind of face angle decision-making system, comprising:
Photo acquisition module, for obtaining the two-dimension human face photo of face;
Pretreatment module, for carrying out pre-service to two-dimension human face photo;
First face characteristic information extracting module, for carrying out feature extraction to pretreated two-dimension human face photo;
Standard multidimensional faceform sets up module, sets up multidimensional human face photo according to the face information that the first face characteristic information extracting module is extracted;
Second face characteristic information extraction module, for extracting the face characteristic information in multidimensional human face photo, this face characteristic information at least comprises the coordinate figure of left pupil Le, right pupil Re, prenasale J and nose saddle point A;
Computing module, for calculated level deflection angle X, the first vertical deflection angle Y and the second vertical deflection angle Z;
Display module, for showing face multidimensional picture, and reveal competence deflection angle X, the first vertical deflection angle Y and the second vertical deflection angle Z;
Described photo acquisition module, pretreatment module, the first face characteristic information extracting module, standard multidimensional faceform set up module, the second face characteristic information extraction module, computing module are connected successively with display module.
Compared with prior art, the invention has the advantages that: two-dimension human face photo is converted to multidimensional human face photo by the present invention, by extracting the human face characteristic point on multidimensional human face photo, carry out face angle calculation by the coordinate of unique point, and then draw face angle more accurately.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the process flow diagram of face angle decision method of the present invention.
Fig. 2 is the frame diagram of face angle decision-making system of the present invention.
Embodiment
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are described in detail, can be easier to make advantages and features of the invention be readily appreciated by one skilled in the art, thus more explicit defining is made to protection scope of the present invention.
Consult shown in Fig. 1, the invention provides a kind of face angle decision method, comprise the following steps:
The two-dimension human face photo of step 1, acquisition target person, and pre-service is carried out to human face photo;
Step 2, extract pretreated face characteristic information;
Step 3, the face characteristic information extracted in step 2 is inputted a standard multidimensional faceform and sets up in module, set up multidimensional human face photo;
Step 4, the face characteristic information extracted in multidimensional human face photo, this face characteristic information at least comprises the coordinate figure of left pupil Le, right pupil Re, prenasale J and nose saddle point A;
Step 5, calculate the X deflection angle X of face according to the coordinate figure of left pupil Le and right pupil Re, the first vertical deflection angle Y and the second vertical deflection angle Z of face is calculated according to the coordinate figure of prenasale J and nose saddle point A, wherein X is horizontal direction, Y is vertical direction, and Z is the direction outside vertical paper points to;
Step 6, by a display module reveal competence deflection angle X, the first vertical deflection angle Y and the second vertical deflection angle Z.Information shown by this display module comprises the multi-dimensional graphic information of face, and the markup information of X deflection angle X, the first vertical deflection angle Y and the second vertical deflection angle Z.
Concrete, in the present invention, the coordinate figure of described left pupil Le and right pupil Re is respectively Le (x1, y1, z1), Re (x2, y2, z2).The account form of described X deflection angle X is: X=arctan ((y2-y1)/(x2-x1)).
The coordinate of described prenasale J and nose saddle point A is respectively J (xn, yn, zn), A (xs, ys, zs); The account form of described first vertical deflection angle Y is: Y=arctan ((xn-xs)/(zn-zs)).
The account form of described second vertical deflection angle Z is: Z=arctan ((xn-xs)
2+ (zn-zs)
2/ (yn-ys)).
The pre-service of described human face photo comprises geometric manipulations, illumination compensation and histogram equalization.And the method for available wavelet transformation is decomposed image, filters out high-frequency information, adopt metastable low-frequency molecular to express image information, the fuzzy impact of human face expression and posture.
Consult shown in Fig. 2, the present invention also provides a kind of face angle decision-making system, comprising: photo acquisition module 1, for obtaining the two-dimension human face photo of face; Pretreatment module 2, for carrying out pre-service to two-dimension human face photo; First face characteristic information extracting module 3, for carrying out feature extraction to pretreated two-dimension human face photo; Standard multidimensional faceform sets up module 4, sets up multidimensional human face photo according to the face information that the first face characteristic information extracting module 3 is extracted; Second face characteristic information extraction module 5, for extracting the face characteristic information in multidimensional human face photo, this face characteristic information at least comprises the coordinate figure of left pupil Le, right pupil Re, prenasale J and nose saddle point A; Computing module 6, for calculated level deflection angle X, the first vertical deflection angle Y and the second vertical deflection angle Z; Display module 7, for showing face multidimensional picture, and reveal competence deflection angle X, the first vertical deflection angle Y and the second vertical deflection angle Z.Wherein, described photo acquisition module 1, pretreatment module 2, first face characteristic information extracting module 3, standard multidimensional faceform set up module 4, second face characteristic information extraction module 5, computing module 6 is connected successively with display module 7.Above-mentioned each module adopts the mode of software programming, is formed in computer-internal.
Two-dimension human face photo is converted to multidimensional human face photo by the present invention, by extracting the human face characteristic point on multidimensional human face photo, carries out face angle calculation by the coordinate of unique point, and then draws face angle more accurately.
Although describe embodiments of the present invention by reference to the accompanying drawings; but patent owner can make various distortion or amendment within the scope of the appended claims; as long as be no more than the protection domain described by claim of the present invention, all should within protection scope of the present invention.
Claims (5)
1. a face angle decision method, is characterized in that: comprise the following steps,
The two-dimension human face photo of step 1, acquisition target person, and pre-service is carried out to human face photo;
Step 2, extract pretreated face characteristic information;
Step 3, the face characteristic information extracted in step 2 is inputted a standard multidimensional faceform and sets up in module, set up multidimensional human face photo;
Step 4, the face characteristic information extracted in multidimensional human face photo, this face characteristic information at least comprises the coordinate figure of left pupil Le, right pupil Re, prenasale J and nose saddle point A;
Step 5, calculate the X deflection angle X of face according to the coordinate figure of left pupil Le and right pupil Re, the first vertical deflection angle Y and the second vertical deflection angle Z of face is calculated according to the coordinate figure of prenasale J and nose saddle point A, wherein X is horizontal direction, Y is vertical direction, and Z is the direction outside vertical paper points to;
Step 6, by a display module reveal competence deflection angle X, the first vertical deflection angle Y and the second vertical deflection angle Z.
2. face angle decision method according to claim 1, is characterized in that:
The coordinate figure of described left pupil Le and right pupil Re is respectively Le (x1, y1, z1), Re (x2, y2, z2); The account form of described X deflection angle X is: X=arctan ((y2-y1)/(x2-x1));
The coordinate of described prenasale J and nose saddle point A is respectively J (xn, yn, zn), A (xs, ys, zs);
The account form of described first vertical deflection angle Y is: Y=arctan ((xn-xs)/(zn-zs));
The account form of described second vertical deflection angle Z is: Z=arctan ((xn-xs)
2+ (zn-zs)
2/ (yn-ys)).
3. face angle decision method according to claim 1, is characterized in that: the pre-service of described human face photo comprises geometric manipulations, illumination compensation and histogram equalization.
4. face angle decision method according to claim 1, it is characterized in that: the information shown by the display module in described step 6 comprises the multi-dimensional graphic information of face, and the markup information of X deflection angle X, the first vertical deflection angle Y and the second vertical deflection angle Z.
5. a face angle decision-making system, is characterized in that: comprise
Photo acquisition module (1), for obtaining the two-dimension human face photo of face;
Pretreatment module (2), for carrying out pre-service to two-dimension human face photo;
First face characteristic information extracting module (3), for carrying out feature extraction to pretreated two-dimension human face photo;
Standard multidimensional faceform sets up module (4), sets up multidimensional human face photo according to the face information that the first face characteristic information extracting module (3) is extracted;
Second face characteristic information extraction module (5), for extracting the face characteristic information in multidimensional human face photo, this face characteristic information at least comprises the coordinate figure of left pupil Le, right pupil Re, prenasale J and nose saddle point A;
Computing module (6), for calculated level deflection angle X, the first vertical deflection angle Y and the second vertical deflection angle Z;
Display module (7), for showing face multidimensional picture, and reveal competence deflection angle X, the first vertical deflection angle (Y) and the second vertical deflection angle (Z);
Described photo acquisition module (1), pretreatment module (2), the first face characteristic information extracting module (3), standard multidimensional faceform set up module (4), the second face characteristic information extraction module (5), computing module (6) are connected successively with display module (7).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510799520.8A CN105389570A (en) | 2015-11-19 | 2015-11-19 | Face angle determination method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510799520.8A CN105389570A (en) | 2015-11-19 | 2015-11-19 | Face angle determination method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105389570A true CN105389570A (en) | 2016-03-09 |
Family
ID=55421842
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510799520.8A Pending CN105389570A (en) | 2015-11-19 | 2015-11-19 | Face angle determination method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105389570A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679446A (en) * | 2017-08-17 | 2018-02-09 | 平安科技（深圳）有限公司 | Human face posture detection method, device and storage medium |
| CN107944424A (en) * | 2017-12-08 | 2018-04-20 | 广东金杭科技有限公司 | Front end human image collecting and Multi-angle human are distributed as comparison method |
| CN108052892A (en) * | 2017-12-08 | 2018-05-18 | 广东金杭科技有限公司 | Gather Head switches amount comparison method |
| CN109146962A (en) * | 2018-09-07 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | Detect method, apparatus, storage medium and the terminal device of face's angle |
| WO2019128932A1 (en) * | 2017-12-25 | 2019-07-04 | 北京市商汤科技开发有限公司 | Face pose analysis method and apparatus, device, storage medium, and program |
| CN111914783A (en) * | 2020-08-10 | 2020-11-10 | 深圳市视美泰技术股份有限公司 | Method and device for determining human face deflection angle, computer equipment and medium |
| CN114162138A (en) * | 2020-09-10 | 2022-03-11 | ***通信有限公司研究院 | Automatic driving mode switching method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102034079A (en) * | 2009-09-24 | 2011-04-27 | 汉王科技股份有限公司 | Method and system for identifying faces shaded by eyeglasses |
| WO2013014328A1 (en) * | 2011-07-25 | 2013-01-31 | Nokia Corporation | Methods and apparatuses for facilitating locking and unlocking of secure functionality through object recognition |
| CN103558910A (en) * | 2013-10-17 | 2014-02-05 | 北京理工大学 | Intelligent display system automatically tracking head posture |
| CN103996032A (en) * | 2014-05-27 | 2014-08-20 | 厦门瑞为信息技术有限公司 | Face angle determining method based on cranium image coincidence theory |
-
2015
- 2015-11-19 CN CN201510799520.8A patent/CN105389570A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102034079A (en) * | 2009-09-24 | 2011-04-27 | 汉王科技股份有限公司 | Method and system for identifying faces shaded by eyeglasses |
| WO2013014328A1 (en) * | 2011-07-25 | 2013-01-31 | Nokia Corporation | Methods and apparatuses for facilitating locking and unlocking of secure functionality through object recognition |
| CN103558910A (en) * | 2013-10-17 | 2014-02-05 | 北京理工大学 | Intelligent display system automatically tracking head posture |
| CN103996032A (en) * | 2014-05-27 | 2014-08-20 | 厦门瑞为信息技术有限公司 | Face angle determining method based on cranium image coincidence theory |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679446A (en) * | 2017-08-17 | 2018-02-09 | 平安科技（深圳）有限公司 | Human face posture detection method, device and storage medium |
| WO2019033576A1 (en) * | 2017-08-17 | 2019-02-21 | 平安科技（深圳）有限公司 | Face posture detection method, device, and storage medium |
| CN107944424A (en) * | 2017-12-08 | 2018-04-20 | 广东金杭科技有限公司 | Front end human image collecting and Multi-angle human are distributed as comparison method |
| CN108052892A (en) * | 2017-12-08 | 2018-05-18 | 广东金杭科技有限公司 | Gather Head switches amount comparison method |
| WO2019128932A1 (en) * | 2017-12-25 | 2019-07-04 | 北京市商汤科技开发有限公司 | Face pose analysis method and apparatus, device, storage medium, and program |
| US11341769B2 (en) | 2017-12-25 | 2022-05-24 | Beijing Sensetime Technology Development Co., Ltd. | Face pose analysis method, electronic device, and storage medium |
| CN109146962A (en) * | 2018-09-07 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | Detect method, apparatus, storage medium and the terminal device of face's angle |
| CN111914783A (en) * | 2020-08-10 | 2020-11-10 | 深圳市视美泰技术股份有限公司 | Method and device for determining human face deflection angle, computer equipment and medium |
| CN114162138A (en) * | 2020-09-10 | 2022-03-11 | ***通信有限公司研究院 | Automatic driving mode switching method and device |
| CN114162138B (en) * | 2020-09-10 | 2023-10-27 | ***通信有限公司研究院 | Automatic driving mode switching method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105389570A (en) | Face angle determination method and system | |
| CN108986094B (en) | Automatic data updating method for training image library for face recognition | |
| CN101777116B (en) | Method for analyzing facial expressions on basis of motion tracking | |
| CN103455991B (en) | A kind of multi-focus image fusing method | |
| CN108986801A (en) | A kind of man-machine interaction method, device and human-computer interaction terminal | |
| CN110348496B (en) | Face image fusion method and system | |
| CN110555412B (en) | End-to-end human body gesture recognition method based on combination of RGB and point cloud | |
| CN103218605B (en) | A kind of fast human-eye positioning method based on integral projection and rim detection | |
| CN102567716B (en) | Face synthetic system and implementation method | |
| CN113205040A (en) | Face image processing method and device and electronic equipment | |
| CN103927016A (en) | Real-time three-dimensional double-hand gesture recognition method and system based on binocular vision | |
| CN111414780A (en) | Sitting posture real-time intelligent distinguishing method, system, equipment and storage medium | |
| CN107688391A (en) | A kind of gesture identification method and device based on monocular vision | |
| CN113538486B (en) | Method for improving identification and positioning accuracy of automobile sheet metal workpiece | |
| CN103530599A (en) | Method and system for distinguishing real face and picture face | |
| CN105930795A (en) | Walking state identification method based on space vector between human body skeleton joints | |
| CN103903013A (en) | Optimization algorithm of unmarked flat object recognition | |
| CN111680544B (en) | Face recognition method, device, system, equipment and medium | |
| CN103605964A (en) | Face detection method and system based on image on-line learning | |
| CN104091350B (en) | A kind of object tracking methods of utilization motion blur information | |
| CN104573634A (en) | Three-dimensional face recognition method | |
| CN103745206A (en) | Human face identification method and system | |
| CN106127193B (en) | A kind of facial image recognition method | |
| CN110135277B (en) | Human behavior recognition method based on convolutional neural network | |
| CN104268519A (en) | Image recognition terminal based on mode matching and recognition method of image recognition terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20170621 Address after: 510000 Guangdong city of Guangzhou province Panyu District Dashi street, Village Stone Road No. 13 Room 401 Applicant after: Guangdong golden hang Polytron Technologies Inc Address before: Tianhe District Huaqiang road Guangzhou City, Guangdong province 510000 No. 3 South Tower room 2405 Applicant before: Wu Jianzhong |
|
| TA01 | Transfer of patent application right | ||
| CI01 | Publication of corrected invention patent application |
Correction item: Applicant|Address Correct: Guangdong golden Hang Technology Co., Ltd.|510000 Guangdong city of Guangzhou province Panyu District Dashi street, Village Stone Road No. 13 Room 401 False: Guangdong golden hang Polytron Technologies Inc|510000 Guangdong city of Guangzhou province Panyu District Dashi street, Village Stone Road No. 13 Room 401 Number: 28-01 Volume: 33 |
|
| CI01 | Publication of corrected invention patent application | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160309 |
|
| RJ01 | Rejection of invention patent application after publication |