CN109359537A - Human face posture angle detecting method neural network based and system - Google Patents
Human face posture angle detecting method neural network based and system Download PDFInfo
- Publication number
- CN109359537A CN109359537A CN201811073697.XA CN201811073697A CN109359537A CN 109359537 A CN109359537 A CN 109359537A CN 201811073697 A CN201811073697 A CN 201811073697A CN 109359537 A CN109359537 A CN 109359537A
- Authority
- CN
- China
- Prior art keywords
- human face
- posture angle
- key point
- neural network
- face posture
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000001514 detection method Methods 0.000 claims abstract description 63
- 230000001815 facial effect Effects 0.000 claims abstract description 22
- 238000012360 testing method Methods 0.000 claims abstract description 21
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 3
- 230000036544 posture Effects 0.000 description 61
- 238000012549 training Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000004218 nerve net Anatomy 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Geometry (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
Human face posture angle detecting method neural network based of the invention contains the testing image of face to be measured including obtaining；Face datection detects the facial image to be measured containing face characteristic region in testing image；Key point is carried out to facial image to be measured by default key point neural network to position to obtain 68 key points；Key point is normalized to obtain corresponding key point coordinate, key point coordinate is input in default human face posture angle detection neural network, human face posture angle detection neural network is preset and exports human face posture angle value.Human face posture angle detecting method neural network based of the invention carries out crucial point location to facial image to be measured by default key point neural network and obtains 68 key points, key point is detected using default human face posture angle detection neural network to obtain human face posture angle value, whole process testing result is accurate, speed is fast, high to the robustness of various face shapes of face.
Description
Technical field
The present invention relates to human face posture angle detection fields more particularly to human face posture angle neural network based to detect
Method and system.
Background technique
Current includes following two for the detection of human face posture angle: 1. based on face key point between points away from
From the mapping that ratio carries out angle.2. being asked by calculating face 3D point cloud and an angle map relationship of standard faces 3D point cloud
Obtain human face posture angle.Above two method has the following problems: method 1: accuracy rate is not high and can not accomplish wide-angle
Angle estimation fluctuates different faces shape of face bigger；Method 2: detection is very time-consuming, and detection process needs the plenty of time.
Summary of the invention
For overcome the deficiencies in the prior art, one of the objects of the present invention is to provide human face postures neural network based
Angle detecting method can solve the limitation of traditional technique in measuring and the problem that detection is very time-consuming.
The second object of the present invention is to provide human face posture angle detection system neural network based, can solve biography
The very time-consuming problem of the limitation and detection that system method detects.
The present invention provides the first purpose and is implemented with the following technical solutions:
Human face posture angle detecting method neural network based, comprising:
Image obtains, and obtains the testing image for containing face to be measured；
Face datection detects the facial image to be measured containing face characteristic region in the testing image；
Crucial point location carries out key point to the facial image to be measured by default key point neural network and positions to obtain
68 key points；
The detection of human face posture angle, is normalized the key point to obtain corresponding key point coordinate, by institute
It states key point coordinate to be input in default human face posture angle detection neural network, the default human face posture angle detection nerve
Network exports human face posture angle value.
Further, the default human face posture angle detection neural network includes input layer, the first full articulamentum, second
Full articulamentum and output layer.
Further, the dimension of the input layer is 1*136, and the dimension of the first full articulamentum is 136*68, described
The dimension of second full articulamentum is 68*3, and the dimension of the output layer is 1*3.
Further, human face posture angle detection specifically: the key point is normalized to obtain pair
The key point coordinate is entered by input layer, and successively passes through the first full articulamentum and second by the key point coordinate answered
Full articulamentum processing, final output layer export human face posture angle value.
Further, the human face posture angle value includes level angle value, tilt values and pitching angle value.
The present invention provides the second purpose and is implemented with the following technical solutions:
Human face posture angle detection system neural network based, comprising:
Image collection module, described image obtain module and are used to obtain the testing image containing face to be measured；
Face detection module, the face detection module, which is used to detect in the testing image, contains face characteristic region
Facial image to be measured；
Key point locating module, the key point locating module are used for through default key point neural network to described to be measured
Facial image carries out key point and positions to obtain 68 key points；
Human face posture angle detection module, the human face posture angle detection module are used to carry out normalizing to the key point
Change handles to obtain corresponding key point coordinate, and the key point coordinate is input to default human face posture angle and detects neural network
In, the default human face posture angle detection neural network exports human face posture angle value.
Further, the human face posture angle detection module includes normalization unit and detection unit, the normalization
Unit is used to that the key point to be normalized to obtain on corresponding key point coordinate, and the detection unit is used for will be described
Key point coordinate is input in default human face posture angle detection neural network, and the default human face posture angle detects nerve net
Network exports human face posture angle value.
Further, the human face posture angle value includes level angle value, tilt values and pitching angle value.
Compared with prior art, the beneficial effects of the present invention are human face posture angles neural network based of the invention
Detection method contains the testing image of face to be measured including obtaining；Face datection detects in testing image and contains face characteristic
The facial image to be measured in region；Key point is carried out to facial image to be measured by default key point neural network to position to obtain 68
Key point；Key point is normalized to obtain corresponding key point coordinate, key point coordinate is input to default face
Attitude angle detects in neural network, presets human face posture angle detection neural network and exports human face posture angle value.By pre-
If key point neural network carries out crucial point location to facial image to be measured and obtains 68 key points, using default human face posture angle
Degree detection neural network detects key point to obtain human face posture angle value, whole process testing result is accurate, speed is fast,
It is high to the robustness of various face shapes of face.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And can be implemented in accordance with the contents of the specification, the following is a detailed description of the preferred embodiments of the present invention and the accompanying drawings.
A specific embodiment of the invention is shown in detail by following embodiment and its attached drawing.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is the flow diagram of human face posture angle detecting method neural network based of the invention；
Fig. 2 is the module connection diagram of human face posture angle detection system neural network based of the invention.
Specific embodiment
In the following, being described further in conjunction with attached drawing and specific embodiment to the present invention, it should be noted that not
Under the premise of conflicting, new implementation can be formed between various embodiments described below or between each technical characteristic in any combination
Example.
As shown in Figure 1, human face posture angle detecting method neural network based of the invention, comprising:
Image obtains, and obtains the testing image for containing face to be measured；It is obtained using camera to be measured containing face to be measured
Image contains face to be measured and other backgrounds in testing image.
Face datection detects the facial image to be measured containing face characteristic region in testing image；It detects above-mentioned to be measured
Face characteristic region in image and the facial image to be measured for obtaining containing only face to be measured.
Crucial point location carries out key point to facial image to be measured by default key point neural network and positions to obtain 68
Key point；The default key point nerve net that can be used is trained to key point neural network input training set in advance
Network is handled to obtain totally 68 key points to facial image to be measured using default key point neural network.
The detection of human face posture angle, is normalized key point to obtain corresponding key point coordinate, by key point
Coordinate is input in default human face posture angle detection neural network, is preset human face posture angle detection neural network and is exported face
Attitude angle angle value.Human face posture angle detection neural network is trained using original training set in the present embodiment, through excessive
The default human face posture angle that secondary training can be used detects neural network.Specifically: place is normalized to key point
Reason obtains corresponding key point coordinate, i.e., carries out conversion process to the key point in facial image to be measured and finally obtain unified two
Tie up coordinate.Key point coordinate is entered by input layer, and is successively handled by the first full articulamentum and the second full articulamentum,
Final output layer exports human face posture angle value.Human face posture angle value includes level angle value, tilt values and pitch angle
Value；Level angle value is face left-right rotation degree value, and tilt values are the inclined degree value of face, and pitching angle value is people's face
The degree value for raising up or overlooking.In the present embodiment, key point is normalized to obtain corresponding key point coordinate, it will
Key point coordinate is entered by input layer, and successively by the first full articulamentum and the second full articulamentum processing, final output
Layer output human face posture angle value.The dimension of input layer is 1*136 in the present embodiment, and the dimension of the first full articulamentum is 136*
68, the dimension of the second full articulamentum is 68*3, and the dimension of output layer is 1*3.Default human face posture angle detection neural network
Size only has 38k.Human face posture model inspection neural network is preset in the present embodiment when detecting to human face posture angle
Only need 1ms.
As shown in Fig. 2, the present invention also provides human face posture angle detection systems neural network based, comprising:
Image collection module, image collection module are used to obtain the testing image containing face to be measured；
Face detection module, face detection module are used to detect the people to be measured containing face characteristic region in testing image
Face image；
Key point locating module, key point locating module are used for through default key point neural network to facial image to be measured
Key point is carried out to position to obtain 68 key points；
Human face posture angle detection module, human face posture angle detection module is for being normalized key point
To corresponding key point coordinate, key point coordinate is input in default human face posture angle detection neural network, face is preset
Attitude angle detects neural network and exports human face posture angle value.
In the present embodiment, human face posture angle detection module includes normalization unit and detection unit, normalization unit
For key point to be normalized to obtain corresponding key point coordinate, detection unit is for key point coordinate to be input to
In default human face posture angle detection neural network, presets human face posture angle detection neural network and export human face posture angle
Value.Human face posture angle value includes level angle value, tilt values and pitching angle value.
Human face posture angle detecting method neural network based of the invention, it is to be measured containing face to be measured including obtaining
Image；Face datection detects the facial image to be measured containing face characteristic region in testing image；Pass through default key point mind
Facial image progress key point is surveyed through network handles to position to obtain 68 key points；Key point is normalized to obtain pair
Key point coordinate is input in default human face posture angle detection neural network, presets human face posture by the key point coordinate answered
Angle detects neural network and exports human face posture angle value.Facial image to be measured is closed by default key point neural network
Key point location obtains 68 key points, is detected to obtain people to key point using default human face posture angle detection neural network
Face attitude angle angle value, whole process testing result is accurate, speed is fast, high to the robustness of various face shapes of face.
More than, only presently preferred embodiments of the present invention is not intended to limit the present invention in any form；All current rows
The those of ordinary skill of industry can be shown in by specification attached drawing and above and swimmingly implement the present invention；But all to be familiar with sheet special
The technical staff of industry without departing from the scope of the present invention, is made a little using disclosed above technology contents
The equivalent variations of variation, modification and evolution is equivalent embodiment of the invention；Meanwhile all substantial technologicals according to the present invention
The variation, modification and evolution etc. of any equivalent variations to the above embodiments, still fall within technical solution of the present invention
Within protection scope.
Claims (8)
1. human face posture angle detecting method neural network based, characterized by comprising:
Image obtains, and obtains the testing image for containing face to be measured；
Face datection detects the facial image to be measured containing face characteristic region in the testing image；
Crucial point location carries out key point to the facial image to be measured by default key point neural network and positions to obtain 68
Key point；
The detection of human face posture angle, is normalized the key point to obtain corresponding key point coordinate, by the pass
Key point coordinate is input in default human face posture angle detection neural network, and the default human face posture angle detects neural network
Export human face posture angle value.
2. human face posture angle detecting method neural network based as described in claim 1, it is characterised in that: described default
It includes input layer, the first full articulamentum, the second full articulamentum and output layer that human face posture angle, which detects neural network,.
3. human face posture angle detecting method neural network based as claimed in claim 2, it is characterised in that: the input
The dimension of layer is 1*136, and the dimension of the first full articulamentum is 136*68, and the dimension of the second full articulamentum is 68*3,
The dimension of the output layer is 1*3.
4. human face posture angle detecting method neural network based as claimed in claim 2, it is characterised in that: the face
Attitude angle detection specifically: the key point is normalized to obtain corresponding key point coordinate, by the key
Point coordinate is entered by input layer, and successively defeated by the first full articulamentum and the second full articulamentum processing, final output layer
Human face posture angle value out.
5. human face posture angle detecting method neural network based as described in claim 1, it is characterised in that: the face
Attitude angle angle value includes level angle value, tilt values and pitching angle value.
6. human face posture angle detection system neural network based, characterized by comprising:
Image collection module, described image obtain module and are used to obtain the testing image containing face to be measured；
Face detection module, the face detection module be used for detect in the testing image containing face characteristic region to
Survey facial image；
Key point locating module, the key point locating module are used for through default key point neural network to the face to be measured
Image carries out key point and positions to obtain 68 key points；
Human face posture angle detection module, the human face posture angle detection module is for being normalized place to the key point
Reason obtains corresponding key point coordinate, and the key point coordinate is input in default human face posture angle detection neural network,
The default human face posture angle detection neural network exports human face posture angle value.
7. such as claim 6 human face posture angle detection system neural network based, it is characterised in that: the human face posture angle
Degree detection module includes normalization unit and detection unit, and the normalization unit is for being normalized place to the key point
Reason obtains corresponding key point coordinate, and the detection unit is used to the key point coordinate being input to default human face posture angle
It detects in neural network, the default human face posture angle detection neural network exports human face posture angle value.
8. such as claim 6 human face posture angle detection system neural network based, it is characterised in that: the human face posture angle
Angle value includes level angle value, tilt values and pitching angle value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811073697.XA CN109359537A (en) | 2018-09-14 | 2018-09-14 | Human face posture angle detecting method neural network based and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811073697.XA CN109359537A (en) | 2018-09-14 | 2018-09-14 | Human face posture angle detecting method neural network based and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109359537A true CN109359537A (en) | 2019-02-19 |
Family
ID=65350760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811073697.XA Pending CN109359537A (en) | 2018-09-14 | 2018-09-14 | Human face posture angle detecting method neural network based and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109359537A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109919077A (en) * | 2019-03-04 | 2019-06-21 | 网易（杭州）网络有限公司 | Gesture recognition method, device, medium and calculating equipment |
| CN110705355A (en) * | 2019-08-30 | 2020-01-17 | 中国科学院自动化研究所南京人工智能芯片创新研究院 | Face pose estimation method based on key point constraint |
| CN111860394A (en) * | 2020-07-28 | 2020-10-30 | 成都新希望金融信息有限公司 | Gesture estimation and gesture detection-based action living body recognition method |
| CN112613447A (en) * | 2020-12-29 | 2021-04-06 | 上海商汤智能科技有限公司 | Key point detection method and device, electronic equipment and storage medium |
| CN112699784A (en) * | 2020-12-29 | 2021-04-23 | 深圳市普渡科技有限公司 | Face orientation estimation method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103824049A (en) * | 2014-02-17 | 2014-05-28 | 北京旷视科技有限公司 | Cascaded neural network-based face key point detection method |
| CN105760836A (en) * | 2016-02-17 | 2016-07-13 | 厦门美图之家科技有限公司 | Multi-angle face alignment method based on deep learning and system thereof and photographing terminal |
| CN107038429A (en) * | 2017-05-03 | 2017-08-11 | 四川云图睿视科技有限公司 | A kind of multitask cascade face alignment method based on deep learning |
| CN107967456A (en) * | 2017-11-27 | 2018-04-27 | 电子科技大学 | A kind of multiple neural network cascade identification face method based on face key point |
| CN108197547A (en) * | 2017-12-26 | 2018-06-22 | 深圳云天励飞技术有限公司 | Face pose estimation, device, terminal and storage medium |
-
2018
- 2018-09-14 CN CN201811073697.XA patent/CN109359537A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103824049A (en) * | 2014-02-17 | 2014-05-28 | 北京旷视科技有限公司 | Cascaded neural network-based face key point detection method |
| CN105760836A (en) * | 2016-02-17 | 2016-07-13 | 厦门美图之家科技有限公司 | Multi-angle face alignment method based on deep learning and system thereof and photographing terminal |
| CN107038429A (en) * | 2017-05-03 | 2017-08-11 | 四川云图睿视科技有限公司 | A kind of multitask cascade face alignment method based on deep learning |
| CN107967456A (en) * | 2017-11-27 | 2018-04-27 | 电子科技大学 | A kind of multiple neural network cascade identification face method based on face key point |
| CN108197547A (en) * | 2017-12-26 | 2018-06-22 | 深圳云天励飞技术有限公司 | Face pose estimation, device, terminal and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 刘淼等: "基于椭圆模型和神经网络的人脸姿态估计方法", 《吉林大学学报(理学版)》, vol. 46, no. 4, 31 July 2008 (2008-07-31), pages 687 - 690 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109919077A (en) * | 2019-03-04 | 2019-06-21 | 网易（杭州）网络有限公司 | Gesture recognition method, device, medium and calculating equipment |
| CN110705355A (en) * | 2019-08-30 | 2020-01-17 | 中国科学院自动化研究所南京人工智能芯片创新研究院 | Face pose estimation method based on key point constraint |
| CN111860394A (en) * | 2020-07-28 | 2020-10-30 | 成都新希望金融信息有限公司 | Gesture estimation and gesture detection-based action living body recognition method |
| CN112613447A (en) * | 2020-12-29 | 2021-04-06 | 上海商汤智能科技有限公司 | Key point detection method and device, electronic equipment and storage medium |
| CN112699784A (en) * | 2020-12-29 | 2021-04-23 | 深圳市普渡科技有限公司 | Face orientation estimation method and device, electronic equipment and storage medium |
| WO2022143264A1 (en) * | 2020-12-29 | 2022-07-07 | 深圳市普渡科技有限公司 | Face orientation estimation method and apparatus, electronic device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109359537A (en) | Human face posture angle detecting method neural network based and system | |
| CN108549873B (en) | Three-dimensional face recognition method and three-dimensional face recognition system | |
| CN106127170B (en) | A kind of training method, recognition methods and system merging key feature points | |
| CN109446892A (en) | Human eye notice positioning method and system based on deep neural network | |
| CN102156537B (en) | A kind of head pose checkout equipment and method | |
| CN102589530B (en) | Method for measuring position and gesture of non-cooperative target based on fusion of two dimension camera and three dimension camera | |
| CN105184830B (en) | A kind of symmetrical shaft detection localization method of symmetric graph picture | |
| CN102609684B (en) | Human body posture detection method and device | |
| CN104400265B (en) | A kind of extracting method of the welding robot corner connection characteristics of weld seam of laser vision guiding | |
| CN108910701B (en) | Suspender attitude detection system and method | |
| CN103530599A (en) | Method and system for distinguishing real face and picture face | |
| CN106503643B (en) | Tumble detection method for human body | |
| CN107016697B (en) | A kind of height measurement method and device | |
| CN105913013A (en) | Binocular vision face recognition algorithm | |
| CN104657713B (en) | It is a kind of can anti-posture and expression shape change three-dimensional face calibration method | |
| CN104665836A (en) | length measuring method and length measuring device | |
| CN103902992B (en) | Human face recognition method | |
| CN109978938A (en) | A kind of pillow spring detection method based on machine vision | |
| CN111507306A (en) | Temperature error compensation method based on AI face distance detection | |
| CN110378246A (en) | Ground detection method, apparatus, computer readable storage medium and electronic equipment | |
| CN107631782A (en) | A kind of level testing methods based on Harris Corner Detections | |
| CN103438834A (en) | Hierarchy-type rapid three-dimensional measuring device and method based on structured light projection | |
| CN109443303A (en) | The method and system of detection face and camera distance based on Image Acquisition | |
| CN104850842A (en) | Mobile terminal iris identification man-machine interaction method | |
| CN105631852A (en) | Depth image contour line-based indoor human body detection method |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190219 |