CN109190529A - A kind of method for detecting human face and system based on lip positioning - Google Patents
A kind of method for detecting human face and system based on lip positioning Download PDFInfo
- Publication number
- CN109190529A CN109190529A CN201810954300.1A CN201810954300A CN109190529A CN 109190529 A CN109190529 A CN 109190529A CN 201810954300 A CN201810954300 A CN 201810954300A CN 109190529 A CN109190529 A CN 109190529A
- Authority
- CN
- China
- Prior art keywords
- thres
- face
- block
- gmb
- lip
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention proposes a kind of method for detecting human face and system based on lip positioning.The method of the present invention finds the lip-region of current face first, determines the side degree of face gradient and face;Then, the region of search that face is determined according to the gradient of face, side degree, then according to face colour of skin characteristic accurately determined, reasonable tilt angle analyze, on the one hand the accurate face direction of search can be provided for face detection system;On the other hand the calculation amount that full search is carried out to the Face Detection of whole image video can be reduced.
Description
Technical field
The present invention relates to technical field of image processing more particularly to a kind of method for detecting human face positioned based on lip and it is
System.
Background technique
Recognition of face, video U.S. face are two emerging big Video Applications.In practical application, face will not be always at front
Not torticollis.Due to personal habit and the demand of beautification, often there is situations such as side, inclination.If according to normal mode
It is not distinguish, will affect the accuracy of Face datection identification.Face datection inaccuracy, the portrait beauty being just unable to reach naturally
Face effect.
Summary of the invention
The purpose of the embodiment of the present invention is to propose a kind of method for detecting human face based on lip positioning, it is intended to solve existing
The low problem of skill Face datection recognition accuracy.
The embodiments of the present invention are implemented as follows, a kind of method for detecting human face based on lip positioning, which comprises
Step1: lip positioning is carried out to current face;
Step2: in being determined as current face's lip set of blocks, the block column with minimum row number is found, block column are positioned
Intermediate mass, be denoted as gmb (i1, j1);Find the block column with maximum row number, position the intermediate mass of block column, be denoted as gmb (i2,
j2);
Step3: in being determined as current face's lip set of blocks, the block row with minimum line number is found, the block row is positioned
Intermediate mass, be denoted as gmb (i3, j3);Find the block row with maximum line number, position the intermediate mass of the block row, be denoted as gmb (i4,
j4);
Step4: current face side ratio γ is calculated;
Step5: current face's tilt angle theta is calculated;
Step6: according to face tilt angle and face side ratio, current face's area to be tested is determined;
Step7: the colour of skin is carried out to block in current face's area to be tested and is accurately determined, Face datection is completed.
The another object of the embodiment of the present invention is to propose a kind of face detection system based on lip positioning, the system
Include:
Lip positioning device, for carrying out lip positioning to current face;
First intermediate mass searchs and locates module, has minimum for finding in being determined as current face's lip set of blocks
The block of row number arranges, and positions the intermediate mass of block column, is denoted as gmb (i1, j1);The block column with maximum row number are found, the block is positioned
The intermediate mass of column is denoted as gmb (i2, j2);
Second intermediate mass searchs and locates module, has minimum for finding in being determined as current face's lip set of blocks
The block row of line number, positions the intermediate mass of the block row, is denoted as gmb (i3, j3);The block row with maximum line number is found, the block is positioned
Capable intermediate mass is denoted as gmb (i4, j4);
Face side ratio computing module, for calculating current face side ratio γ;
Face tilt angle computing module, for calculating current face's tilt angle theta;
Face area to be tested determining module, for according to face tilt angle and face side ratio, forefathers to be worked as in determination
Face area to be tested;
The accurate determination module of the colour of skin accurately determines for carrying out the colour of skin to block in current face's area to be tested, completes people
Face detection.
Beneficial effects of the present invention
The present invention proposes a kind of method for detecting human face and system based on lip positioning.The method of the present invention is found currently first
The lip-region of face determines the side degree of face gradient and face;Then, according to the gradient of face, side degree
The region of search for determining face is accurately determined then according to the colour of skin characteristic of face.Reasonable tilt angle analysis, a side
Face can provide the accurate face direction of search for face detection system;On the other hand the colour of skin to whole image video can be reduced
Detection carries out the calculation amount of full search.
Detailed description of the invention
Fig. 1 is a kind of method for detecting human face flow chart based on lip positioning of the preferred embodiment of the present invention;
Fig. 2 is a kind of face detection system structure chart based on lip positioning of the preferred embodiment of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, right below in conjunction with drawings and examples
The present invention is further elaborated, and for ease of description, only parts related to embodiments of the present invention are shown.It should manage
Solution, the specific embodiment that this place is described are used only for explaining the present invention, be not intended to limit the invention.
The present invention proposes a kind of method for detecting human face and system based on lip positioning.The method of the present invention is found currently first
The lip-region of face determines the side degree of face gradient and face;Then, according to the gradient of face, side degree
The region of search for determining face is accurately determined then according to the colour of skin characteristic of face.Reasonable tilt angle analysis, a side
Face can provide the accurate face direction of search for face detection system;On the other hand the colour of skin to whole image video can be reduced
Detection carries out the calculation amount of full search.
Embodiment one
Fig. 1 is a kind of method for detecting human face flow chart based on lip positioning of the preferred embodiment of the present invention;The method packet
It includes:
Step1: lip positioning is carried out to current face.
It is described that lip positioning is carried out using disclosed method in the industry to current face;
Step2: in being determined as current face's lip set of blocks, the block column with minimum row number is found, block column are positioned
Intermediate mass, be denoted as gmb (i1, j1);Find the block column with maximum row number, position the intermediate mass of block column, be denoted as gmb (i2,
j2)。
Step3: in being determined as current face's lip set of blocks, the block row with minimum line number is found, the block row is positioned
Intermediate mass, be denoted as gmb (i3, j3);Find the block row with maximum line number, position the intermediate mass of the block row, be denoted as gmb (i4,
j4)。
Step4: calculating current face side ratio γ,
Step5: calculating current face's tilt angle theta,
Step6: according to face tilt angle and face side ratio, current face's area to be tested is determined.
It is specific as follows:
If θ=0, delimiting face area to be tested is
{gmb(i,j)|i3-ThresiU≤i≤i4+ThresiDAnd j1-ThresjL≤j≤j2+ThresjR,
Wherein, Thres < ThresiD< ThresiU/ 3 < 2*Thres, Thres=max (i4-i3, j2-j1),
2*Thres < ThresjR< 6*Thres,Thres、ThresiU、
ThresiD、ThresjL、ThresjRIt is referred to as threshold value, uplink threshold value, downlink threshold value, left column threshold value, right column threshold value;max
Table seeks maximizing;Gmb (i, j) indicates the block for being located at present image the i-th row jth column.
If θ ≠ 0, rectangular area delimited first
{i3-ThresiU≤i≤i4+ThresiDAnd j1-ThresjL≤j≤j2+ThresjR};Then anchor point is found
((i3+i4)/2, (j3+j4)/2), then using above-mentioned anchor point as revolving fixed point, rotates θ for rectangular area;It finally chooses and falls into
Block in the rotation rectangular area is face area to be tested.
Step7: the colour of skin is carried out to block in current face's area to be tested and is accurately determined, Face datection is completed.
It is described that the block progress colour of skin in current face's area to be tested is accurately determined using published method in the industry.
Embodiment two
Fig. 2 is a kind of face detection system structure chart based on lip positioning of the preferred embodiment of the present invention.The system packet
It includes:
Lip positioning device, for carrying out lip positioning to current face.
It is described that lip positioning is carried out using disclosed method in the industry to current face;
First intermediate mass searchs and locates module, has minimum for finding in being determined as current face's lip set of blocks
The block of row number arranges, and positions the intermediate mass of block column, is denoted as gmb (i1, j1);The block column with maximum row number are found, the block is positioned
The intermediate mass of column is denoted as gmb (i2, j2).
Second intermediate mass searchs and locates module, has minimum for finding in being determined as current face's lip set of blocks
The block row of line number, positions the intermediate mass of the block row, is denoted as gmb (i3, j3);The block row with maximum line number is found, the block is positioned
Capable intermediate mass is denoted as gmb (i4, j4).
Face side ratio computing module, for calculating current face side ratio γ,
Face tilt angle computing module, for calculating current face's tilt angle theta,
Face area to be tested determining module, for according to face tilt angle and face side ratio, forefathers to be worked as in determination
Face area to be tested.
It is specific as follows:
If θ=0, delimiting face area to be tested is
{gmb(i,j)|i3-ThresiU≤i≤i4+ThresiDAnd j1-ThresjL≤j≤j2+ThresjR,
Wherein, Thres < ThresiD< ThresiU/ 3 < 2*Thres, Thres=max (i4-i3, j2-j1), 2*
Thres < ThresjR< 6*Thres,Thres、ThresiU、ThresiD、
ThresjL、ThresjRIt is referred to as threshold value, uplink threshold value, downlink threshold value, left column threshold value, right column threshold value;Max table is asked
Maximum value;Gmb (i, j) indicates the block for being located at present image the i-th row jth column.
If θ ≠ 0, rectangular area delimited first
{i3-ThresiU≤i≤i4+ThresiDAnd j1-ThresjL≤j≤j2+ThresjR};Then anchor point is found
((i3+i4)/2, (j3+j4)/2), then using above-mentioned anchor point as revolving fixed point, rotates θ for rectangular area;It finally chooses and falls into
Block in the rotation rectangular area is face area to be tested.
The accurate determination module of the colour of skin accurately determines for carrying out the colour of skin to block in current face's area to be tested, completes people
Face detection.
It is described that the block progress colour of skin in current face's area to be tested is accurately determined using published method in the industry.
It will be understood by those skilled in the art that implement the method for the above embodiments be can
With what is completed by program instruction related hardware, the program be can be stored in a computer readable storage medium,
The storage medium can be ROM, RAM, disk, CD etc..
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (8)
1. a kind of method for detecting human face based on lip positioning, which is characterized in that the described method includes:
Step1: lip positioning is carried out to current face;
Step2: in being determined as current face's lip set of blocks, the block column with minimum row number is found, are positioned in block column
Between block, be denoted as gmb (i1, j1);The block column with maximum row number are found, the intermediate mass of block column is positioned, is denoted as gmb (i2, j2);
Step3: in being determined as current face's lip set of blocks, the block row with minimum line number is found, is positioned in the block row
Between block, be denoted as gmb (i3, j3);The block row with maximum line number is found, the intermediate mass of the block row is positioned, is denoted as gmb (i4, j4);
Step4: current face side ratio γ is calculated;
Step5: current face's tilt angle theta is calculated;
Step6: according to face tilt angle and face side ratio, current face's area to be tested is determined;
Step7: the colour of skin is carried out to block in current face's area to be tested and is accurately determined, Face datection is completed.
2. the method for detecting human face as described in claim 1 based on lip positioning, which is characterized in that the calculating current face
Side ratio γ specifically:
3. the method for detecting human face as claimed in claim 2 based on lip positioning, which is characterized in that the calculating current face
Tilt angle theta specifically:
4. the method for detecting human face as claimed in claim 3 based on lip positioning, which is characterized in that described to be tilted according to face
Angle and face side ratio, determine current face's area to be tested specifically:
If θ=0, delimiting face area to be tested is
{gmb(i,j)|i3-ThresiU≤i≤i4+ThresiDAnd j1-ThresjL≤j≤j2+ThresjR,
Wherein, Thres < ThresiD< ThresiU/ 3 < 2*Thres, Thres=max (i4-i3, j2-j1), 2*Thres <
ThresjR< 6*Thres,Thres、ThresiU、ThresiD、ThresjL、ThresjR
It is referred to as threshold value, uplink threshold value, downlink threshold value, left column threshold value, right column threshold value;Max table seeks maximizing;gmb(i,j)
Indicate the block for being located at present image the i-th row jth column;
If θ ≠ 0, delimitation rectangular area { i3-Thres firstiU≤i≤i4+ThresiDAnd j1-ThresjL≤j≤j2+
ThresjR};Then anchor point ((i3+i4)/2, (j3+j4)/2) is found, then using above-mentioned anchor point as revolving fixed point, by rectangle
Region rotates θ;Finally choosing the block fallen into the rotation rectangular area is face area to be tested.
5. a kind of face detection system based on lip positioning, which is characterized in that the system comprises:
Lip positioning device, for carrying out lip positioning to current face;
First intermediate mass searchs and locates module, has minimum row number for finding in being determined as current face's lip set of blocks
Block column, position the block column intermediate mass, be denoted as gmb (i1, j1);The block column with maximum row number are found, block column are positioned
Intermediate mass is denoted as gmb (i2, j2);
Second intermediate mass searchs and locates module, has minimum line number for finding in being determined as current face's lip set of blocks
Block row, position the intermediate mass of the block row, be denoted as gmb (i3, j3);The block row with maximum line number is found, the block row is positioned
Intermediate mass is denoted as gmb (i4, j4);
Face side ratio computing module, for calculating current face side ratio γ;
Face tilt angle computing module, for calculating current face's tilt angle theta;
Face area to be tested determining module, for determining that current face waits for according to face tilt angle and face side ratio
Detection zone;
The accurate determination module of the colour of skin accurately determines for carrying out the colour of skin to block in current face's area to be tested, completes face inspection
It surveys.
6. the face detection system as claimed in claim 5 based on lip positioning, which is characterized in that
In the ratio computing module of face side, for calculating current face side ratio γ specifically:
7. the face detection system as claimed in claim 6 based on lip positioning, which is characterized in that
In face tilt angle computing module, for calculating current face's tilt angle theta specifically:
8. the face detection system as claimed in claim 7 based on lip positioning, which is characterized in that
In face area to be tested determining module, for determining current face according to face tilt angle and face side ratio
Area to be tested, specific as follows:
If θ=0, delimiting face area to be tested is
{gmb(i,j)|i3-ThresiU≤i≤i4+ThresiDAnd j1-ThresjL≤j≤j2+ThresjR,
Wherein, Thres < ThresiD< ThresiU/ 3 < 2*Thres, Thres=max (i4-i3, j2-j1), 2*Thres <
ThresjR< 6*Thres,Thres、ThresiU、ThresiD、ThresjL、
ThresjRIt is referred to as threshold value, uplink threshold value, downlink threshold value, left column threshold value, right column threshold value;Max table seeks maximizing;
Gmb (i, j) indicates the block for being located at present image the i-th row jth column;
If θ ≠ 0, delimitation rectangular area { i3-Thres firstiU≤i≤i4+ThresiDAnd j1-ThresjL≤j≤j2+
ThresjR};Then anchor point ((i3+i4)/2, (j3+j4)/2) is found, then using above-mentioned anchor point as revolving fixed point, by rectangle
Region rotates θ;Finally choosing the block fallen into the rotation rectangular area is face area to be tested.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810954300.1A CN109190529B (en) | 2018-08-21 | 2018-08-21 | Face detection method and system based on lip positioning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810954300.1A CN109190529B (en) | 2018-08-21 | 2018-08-21 | Face detection method and system based on lip positioning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109190529A true CN109190529A (en) | 2019-01-11 |
CN109190529B CN109190529B (en) | 2022-02-18 |
Family
ID=64919199
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810954300.1A Active CN109190529B (en) | 2018-08-21 | 2018-08-21 | Face detection method and system based on lip positioning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109190529B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110807402A (en) * | 2019-10-29 | 2020-02-18 | 深圳市梦网百科信息技术有限公司 | Facial features positioning method, system and terminal equipment based on skin color detection |
CN111626143A (en) * | 2020-05-06 | 2020-09-04 | 深圳市梦网视讯有限公司 | Reverse face detection method, system and equipment based on eye positioning |
CN111815651A (en) * | 2020-07-08 | 2020-10-23 | 深圳市梦网视讯有限公司 | Method, system and equipment for segmenting face and body skin color area |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102024156A (en) * | 2010-11-16 | 2011-04-20 | 中国人民解放军国防科学技术大学 | Method for positioning lip region in color face image |
CN102324025A (en) * | 2011-09-06 | 2012-01-18 | 北京航空航天大学 | Human face detection and tracking method based on Gaussian skin color model and feature analysis |
CN103632132A (en) * | 2012-12-11 | 2014-03-12 | 广西工学院 | Face detection and recognition method based on skin color segmentation and template matching |
CN107506691A (en) * | 2017-10-19 | 2017-12-22 | 深圳市梦网百科信息技术有限公司 | A kind of lip localization method and system based on Face Detection |
-
2018
- 2018-08-21 CN CN201810954300.1A patent/CN109190529B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102024156A (en) * | 2010-11-16 | 2011-04-20 | 中国人民解放军国防科学技术大学 | Method for positioning lip region in color face image |
CN102324025A (en) * | 2011-09-06 | 2012-01-18 | 北京航空航天大学 | Human face detection and tracking method based on Gaussian skin color model and feature analysis |
CN103632132A (en) * | 2012-12-11 | 2014-03-12 | 广西工学院 | Face detection and recognition method based on skin color segmentation and template matching |
CN107506691A (en) * | 2017-10-19 | 2017-12-22 | 深圳市梦网百科信息技术有限公司 | A kind of lip localization method and system based on Face Detection |
Non-Patent Citations (2)
Title |
---|
李武军 等: ""一种快速而精确的多人脸检测与定位算法"", 《小型微型计算机***》 * |
马艳: ""基于颜色与模板匹配的人脸检测方法"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110807402A (en) * | 2019-10-29 | 2020-02-18 | 深圳市梦网百科信息技术有限公司 | Facial features positioning method, system and terminal equipment based on skin color detection |
CN110807402B (en) * | 2019-10-29 | 2023-08-08 | 深圳市梦网视讯有限公司 | Facial feature positioning method, system and terminal equipment based on skin color detection |
CN111626143A (en) * | 2020-05-06 | 2020-09-04 | 深圳市梦网视讯有限公司 | Reverse face detection method, system and equipment based on eye positioning |
CN111626143B (en) * | 2020-05-06 | 2023-12-08 | 深圳市梦网视讯有限公司 | Reverse face detection method, system and equipment based on eye positioning |
CN111815651A (en) * | 2020-07-08 | 2020-10-23 | 深圳市梦网视讯有限公司 | Method, system and equipment for segmenting face and body skin color area |
CN111815651B (en) * | 2020-07-08 | 2024-01-30 | 深圳市梦网视讯有限公司 | Method, system and equipment for segmenting human face and body skin color region |
Also Published As
Publication number | Publication date |
---|---|
CN109190529B (en) | 2022-02-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109190529A (en) | A kind of method for detecting human face and system based on lip positioning | |
US11170525B2 (en) | Autonomous vehicle based position detection method and apparatus, device and medium | |
US10922794B2 (en) | Image correction method and device | |
WO2020155518A1 (en) | Object detection method and device, computer device and storage medium | |
CN100550039C (en) | A kind of image characteristic points positioning method and device | |
CN111028220B (en) | Automatic detection method for levelness of point cloud rivet | |
US9092697B2 (en) | Image recognition system and method for identifying similarities in different images | |
CN106778737A (en) | A kind of car plate antidote, device and a kind of video acquisition device | |
US20220178129A1 (en) | Smart toilet with automatic urine position detecting system | |
CN109241878A (en) | A kind of facial feature localization method and system based on lip positioning | |
CN101984453B (en) | Human eye recognition system and method | |
CN106407979A (en) | Bill character correction method and device | |
US20100142768A1 (en) | Method, apparatus and computer program product for providing an orientation independent face detector | |
CN104049760A (en) | Obtaining method and system of man-machine interaction instruction | |
CN106447615A (en) | Tilt correction method for scanning document image | |
CN104239843B (en) | Positioning method and device for face feature points | |
CN112669275A (en) | PCB surface defect detection method and device based on YOLOv3 algorithm | |
CN109255307A (en) | A kind of human face analysis method and system based on lip positioning | |
CN104091148A (en) | Facial feature point positioning method and device | |
EP3376468A1 (en) | Object detection device and object detection method | |
WO2020199498A1 (en) | Palmar digital vein comparison method and device, computer apparatus, and storage medium | |
US7916891B2 (en) | Apparatus for measurement of floating body posture of person wearing life jacket | |
CN108037503B (en) | Laser radar-based planar multi-plate positioning method for feeding and discharging of household plates | |
CN116167983A (en) | Rail web alignment method, system and terminal based on minimum DTW distance | |
CN106096597B (en) | A kind of face identification method and device |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 518000 Guangdong city of Shenzhen province Nanshan District Guangdong streets high in the four Longtaili Technology Building Room 325 No. 30 Applicant after: Shenzhen mengwang video Co., Ltd Address before: 518000 Guangdong city of Shenzhen province Nanshan District Guangdong streets high in the four Longtaili Technology Building Room 325 No. 30 Applicant before: SHENZHEN MONTNETS ENCYCLOPEDIA INFORMATION TECHNOLOGY Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |