CN107491718A - The method that human hand Face Detection is carried out under different lightness environment - Google Patents
The method that human hand Face Detection is carried out under different lightness environment Download PDFInfo
- Publication number
- CN107491718A CN107491718A CN201610420486.3A CN201610420486A CN107491718A CN 107491718 A CN107491718 A CN 107491718A CN 201610420486 A CN201610420486 A CN 201610420486A CN 107491718 A CN107491718 A CN 107491718A
- Authority
- CN
- China
- Prior art keywords
- face detection
- carried out
- skin
- out under
- under different
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/245—Aligning, centring, orientation detection or correction of the image by locating a pattern; Special marks for positioning
-
- 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
- G06V40/107—Static hand or arm
-
- 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
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Image Processing (AREA)
Abstract
The present invention is a kind of method that Face Detection is carried out under different lightness environment, is carried out in accordance with the following steps：Camera device calls default shooting condition according to ambient brightness automatically；Shoot live-pictures during hand disengaging shopping cart；Data processing is carried out to live-pictures using colour of skin model of ellipse and obtains Face Detection figure.The present invention ensures that the view data of capture is authentic and valid by correction before being gathered to camera, and carry out skin detection and skin color probability statistics, the skin color probability of acquisition and the center position of highest skin chunk will be counted compared with system primary photometric central point, to determine final light-metering central point；Its specific aim is stronger, can eliminate the influence of the inhuman hand region such as background, makes light-metering effect more stable and more natural.
Description
Technical field
The present invention relates to a kind of skin color detection method, is specifically progress human hand colour of skin inspection under a kind of different lightness environment
The method of survey, belong to machine vision and technical field of image processing.
Background technology
One major function of supermarket intelligent shopping vehicle be exactly can identify customer hand and its whether hold goods on hand
Thing, existing skin color detection method are mainly the detection method based on face, and to know clearly, guarantor face part is as much as possible
It is comprised in photometry region, it is necessary to increase the size of face frame, it is so more or less to be included in face photometry region
The data of background and hair, because the monochrome information of background changes greatly under different scenes and illumination condition, and add
Hair and eye color influence, cause it is based on the light-metering based on face very unstable, strong influence light-metering
Effect.
The content of the invention
Judge the difference of hand position by identifying hand skin color the technical problem to be solved by the invention is to provide a kind of
The method that Face Detection is carried out under lightness environment.
The present invention solves the technical scheme of above technical problem：
A kind of method that Face Detection is carried out under different lightness environment, is carried out in accordance with the following steps：
（1）Camera device calls default shooting condition according to ambient brightness automatically；
（2）Shoot live-pictures during hand disengaging shopping cart；
（3）Data processing is carried out to live-pictures using colour of skin model of ellipse and obtains Face Detection figure.
The technical scheme that further limits of the present invention as：
Further, step（1）Including it is following specific step by step：
（1.1）It is pre- to clap step, before camera device starts shooting, first voluntarily shoot an environment picture；
（1.2）Calculate this environment picture mean flow rate A；
（1.3）When mean flow rate A and upper limit threshold B relations are A-B ＞ 0, then into step（1.4）, when mean flow rate A and lower limit
Threshold value C relations are A-C ＜ 0, then into step（1.5）, the relation between mean flow rate A and upper limit threshold B, lower threshold C
For C≤A≤B, then into step（1.6）；
（1.4）The light-inletting quantity of camera device is turned down according to presupposed solution while increases the time for exposure, shoots photo；
（1.5）The light-inletting quantity of camera device is heightened according to presupposed solution while increases the time for exposure, shoots photo；
（1.6）According to presupposed solution, photo is directly shot.
Further, step（3）Including it is following specific step by step：
（3.1）Live-pictures are transformed into YCrCb spaces by rgb space, and are divided into tri- passages of Y, Cr, Cb；
（3.2）Chrominance C r, Cb is subjected to nonlinear transformation；
（3.3）The colour of skin is carried out to image for the first time to judge, and image is converted into binary map according to brightness Y；
（3.4）The Face Detection result of the Face Detection result of present frame and background frames is done into additive operation and corrosion, removal is made an uproar
Sound and some small noncoherent boundary points, finally give Face Detection figure.
Further, step（3.3）Specially：More than predetermined luminance threshold value 1, and the Cr after corresponding nonlinear transformation
Point value and Cb point values are set to 255, remaining is set to 0 in FX 1；To less than a certain luminance threshold, further according to judging Cr
Whether point value, Cb point values are to be set to 255, are otherwise set to 0 in FX 2.
In a word, the present invention ensures that the view data of capture is authentic and valid by correction before being gathered to camera, and carries out skin
Skin detects and skin color probability statistics, and the center position and system that count the skin color probability obtained and highest skin chunk is original
Light-metering central point is compared, to determine final light-metering central point；Its specific aim is stronger, can eliminate the non-human hand such as background
The influence in region, make light-metering effect more stable and more natural.
Brief description of the drawings
Fig. 1 is Face Detection flow chart.
Fig. 2 is complexion model detection.
Fig. 3 is the broca scale of the nearly colour of skin of background.
Embodiment
Embodiment 1
A kind of method that Face Detection is carried out under different lightness environment, is carried out in accordance with the following steps：
（1）Camera device calls default shooting condition according to ambient brightness automatically；
（1.1）It is pre- to clap step, before camera device starts shooting, first voluntarily shoot an environment picture；
（1.2）Calculate this environment picture mean flow rate A；
（1.3）When mean flow rate A and upper limit threshold B relations are A-B ＞ 0, then into step（1.4）, when mean flow rate A and lower limit
Threshold value C relations are A-C ＜ 0, then into step（1.5）, the relation between mean flow rate A and upper limit threshold B, lower threshold C
For C≤A≤B, then into step（1.6）；
（1.4）The light-inletting quantity of camera device is turned down according to presupposed solution while increases the time for exposure, shoots photo；
（1.5）The light-inletting quantity of camera device is heightened according to presupposed solution while increases the time for exposure, shoots photo；
（1.6）According to presupposed solution, photo is directly shot.
（2）Shoot live-pictures during hand disengaging shopping cart；
（3）Data processing is carried out to live-pictures using colour of skin model of ellipse and obtains Face Detection figure.
（3.1）Live-pictures are transformed into YCrCb spaces by rgb space, and are divided into tri- passages of Y, Cr, Cb；
（3.2）Chrominance C r, Cb is subjected to nonlinear transformation；
（3.3）The colour of skin is carried out to image for the first time to judge, and image is converted into binary map according to brightness Y；More than predetermined luminance threshold
Value 1, and Cr point values after corresponding nonlinear transformation and Cb point values are set to 255, remaining is set to 0 in FX 1；It is right
Less than a certain luminance threshold, further according to judging that Cr point values, Cb point values are to be set to 255, otherwise whether in FX 2
It is set to 0；
（3.4）The Face Detection result of the Face Detection result of present frame and background frames is done into additive operation and corrosion, removal is made an uproar
Sound and some small noncoherent boundary points, finally give Face Detection figure.
Method expense is made further explanation below in conjunction with the accompanying drawings：
1. as shown in figure 1, because ambient brightness is too high, causes hand to have when passing in and out shopping cart visual field and reflective asked than stronger
Topic, to this, our solution method is to reduce the exposure of camera or camera：
(1) mean flow rate of image is first calculated, then to a threshold value 1, if this brightness is more than threshold value, judges that environment is bright
Spend to be too high；
(2) exposure of camera, prolonging exposure time are reduced；
2. as shown in figure 1, because ambient brightness is excessively dark, the colour of skin can not be detected normally when causing normally to do shopping, to this solution method
It is the exposure for heightening camera or camera：
(1) mean flow rate of image is first calculated, a threshold value 2 is then given again, if this brightness is less than threshold value, judges environment
Brightness was dark；
(2) exposure of camera is heightened, reduces the time for exposure；
3. the brightness between threshold value 1 and threshold value 2 is normal；
4. Face Detection
Because the background of shopping cart use environment is complicated and uneven illumination, and to carry out the colour of skin and the back of the body with constant skin tone value
The identification segmentation of scape can not accurately extract hand.Therefore Fig. 2 is shown in based on the colour of skin model of ellipse detection colour of skin, its Face Detection flow chart,
Coloured image is first transformed into YCrCb spaces by rgb space, and is divided into tri- passages of Y, Cr, Cb.Due to the color of area of skin color
With brightness into non-linear relation, chrominance C r, Cb is first subjected to nonlinear transformation, it is first to carry out the colour of skin to image further according to brightness Y
Judge, to the Cr ' Cb ' point values more than a certain luminance threshold, and after corresponding nonlinear transformation in FX 1, be set to
255, remaining is set to 0；To less than a certain luminance threshold, according to judging that Cr ' Cb ' point values are then whether in FX 2
255 are set to, is otherwise set to 0, this is that the secondary colour of skin judges to be converted into binary map.In view of that may have nearly colour of skin object in background,
And only need to detect the colour of skin hand of motion, therefore the Face Detection result of present frame and the Face Detection result of background frames are done into phase
Subtract computing and corrosion, remove noise and some small noncoherent boundary points, its flow such as Fig. 3.
In addition to the implementation, the present invention can also have other embodiment.It is all to use equivalent substitution or equivalent transformation shape
Into technical scheme, all fall within the protection domains of application claims.
Claims (4)
1. the method for Face Detection is carried out under a kind of different lightness environment, it is characterised in that：Carry out in accordance with the following steps：
Camera device calls default shooting condition according to ambient brightness automatically；
Shoot live-pictures during hand disengaging shopping cart；
Data processing is carried out to live-pictures using colour of skin model of ellipse and obtains Face Detection figure.
2. the method for Face Detection is carried out under different lightness environment according to claim 1, it is characterised in that：Step（1）
Including it is following specific step by step：
（1.1）It is pre- to clap step, before camera device starts shooting, first voluntarily shoot an environment picture；
（1.2）Calculate this environment picture mean flow rate A；
（1.3）When mean flow rate A and upper limit threshold B relations are A-B ＞ 0, then into step（1.4）, when mean flow rate A and lower limit
Threshold value C relations are A-C ＜ 0, then into step（1.5）, the relation between mean flow rate A and upper limit threshold B, lower threshold C
For C≤A≤B, then into step（1.6）；
（1.4）The light-inletting quantity of camera device is turned down according to presupposed solution while increases the time for exposure, shoots photo；
（1.5）The light-inletting quantity of camera device is heightened according to presupposed solution while increases the time for exposure, shoots photo；
（1.6）According to presupposed solution, photo is directly shot.
3. the method for Face Detection is carried out under different lightness environment according to claim 1, it is characterised in that：Step（3）
Including it is following specific step by step：
（3.1）Live-pictures are transformed into YCrCb spaces by rgb space, and are divided into tri- passages of Y, Cr, Cb；
（3.2）Chrominance C r, Cb is subjected to nonlinear transformation；
（3.3）The colour of skin is carried out to image for the first time to judge, and image is converted into binary map according to brightness Y；
（3.4）The Face Detection result of the Face Detection result of present frame and background frames is done into additive operation and corrosion, removal is made an uproar
Sound and some small noncoherent boundary points, finally give Face Detection figure.
4. the method for Face Detection is carried out under different lightness environment according to claim 3, it is characterised in that：Step
（3.3）Specially：More than predetermined luminance threshold value 1, and Cr point values after corresponding nonlinear transformation and Cb point values are in fixed area
In domain 1,255 are set to, remaining is set to 0；To less than a certain luminance threshold, further according to judging Cr point values, Cb point values whether solid
Determine in region 2, be, be set to 255, be otherwise set to 0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610420486.3A CN107491718A (en) | 2016-06-13 | 2016-06-13 | The method that human hand Face Detection is carried out under different lightness environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610420486.3A CN107491718A (en) | 2016-06-13 | 2016-06-13 | The method that human hand Face Detection is carried out under different lightness environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107491718A true CN107491718A (en) | 2017-12-19 |
Family
ID=60642431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610420486.3A Pending CN107491718A (en) | 2016-06-13 | 2016-06-13 | The method that human hand Face Detection is carried out under different lightness environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107491718A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109102505A (en) * | 2018-08-17 | 2018-12-28 | 湖南超能机器人技术有限公司 | Contactless palm bleb detection system and its detection method based on image |
| CN109635664A (en) * | 2018-11-15 | 2019-04-16 | 珠海研果科技有限公司 | A kind of method for detecting fatigue driving based on illumination detection |
| CN109977734A (en) * | 2017-12-28 | 2019-07-05 | 华为技术有限公司 | Image processing method and device |
| CN113411507A (en) * | 2021-05-10 | 2021-09-17 | 深圳数联天下智能科技有限公司 | Skin measurement image acquisition method, device, equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101267505A (en) * | 2008-04-25 | 2008-09-17 | 北京中星微电子有限公司 | An exposure time adjusting method, device and a camera |
| 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 |
| CN103279750A (en) * | 2013-06-14 | 2013-09-04 | 清华大学 | Detecting method of mobile telephone holding behavior of driver based on skin color range |
| US20140177955A1 (en) * | 2012-12-21 | 2014-06-26 | Sadagopan Srinivasan | System and method for adaptive skin tone detection |
| CN104504383A (en) * | 2015-01-14 | 2015-04-08 | 东南大学 | Human face detecting method based on skin colors and AdaBoost algorithm |
| CN104680122A (en) * | 2013-11-29 | 2015-06-03 | 展讯通信(天津)有限公司 | Tracking method and device based on skin color detection |
| CN104715244A (en) * | 2015-04-01 | 2015-06-17 | 华中科技大学 | Multi-viewing-angle face detection method based on skin color segmentation and machine learning |
-
2016
- 2016-06-13 CN CN201610420486.3A patent/CN107491718A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101267505A (en) * | 2008-04-25 | 2008-09-17 | 北京中星微电子有限公司 | An exposure time adjusting method, device and a camera |
| 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 |
| US20140177955A1 (en) * | 2012-12-21 | 2014-06-26 | Sadagopan Srinivasan | System and method for adaptive skin tone detection |
| CN103279750A (en) * | 2013-06-14 | 2013-09-04 | 清华大学 | Detecting method of mobile telephone holding behavior of driver based on skin color range |
| CN104680122A (en) * | 2013-11-29 | 2015-06-03 | 展讯通信(天津)有限公司 | Tracking method and device based on skin color detection |
| CN104504383A (en) * | 2015-01-14 | 2015-04-08 | 东南大学 | Human face detecting method based on skin colors and AdaBoost algorithm |
| CN104715244A (en) * | 2015-04-01 | 2015-06-17 | 华中科技大学 | Multi-viewing-angle face detection method based on skin color segmentation and machine learning |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109977734A (en) * | 2017-12-28 | 2019-07-05 | 华为技术有限公司 | Image processing method and device |
| CN109102505A (en) * | 2018-08-17 | 2018-12-28 | 湖南超能机器人技术有限公司 | Contactless palm bleb detection system and its detection method based on image |
| CN109635664A (en) * | 2018-11-15 | 2019-04-16 | 珠海研果科技有限公司 | A kind of method for detecting fatigue driving based on illumination detection |
| CN113411507A (en) * | 2021-05-10 | 2021-09-17 | 深圳数联天下智能科技有限公司 | Skin measurement image acquisition method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9866748B2 (en) | System and method for controlling a camera based on processing an image captured by other camera | |
| US8811733B2 (en) | Method of chromatic classification of pixels and method of adaptive enhancement of a color image | |
| US20150170389A1 (en) | Automatic selection of optimum algorithms for high dynamic range image processing based on scene classification | |
| US7830418B2 (en) | Perceptually-derived red-eye correction | |
| US11138695B2 (en) | Method and device for video processing, electronic device, and storage medium | |
| CN105243371A (en) | Human face beauty degree detection method and system and shooting terminal | |
| JP2011521521A (en) | Optimal video selection | |
| US8483480B2 (en) | Method and system for factoring an illumination image | |
| US9396411B2 (en) | Method and system for generating intrinsic images using a single reflectance technique | |
| CN107491718A (en) | The method that human hand Face Detection is carried out under different lightness environment | |
| JP6162345B2 (en) | Raw scene recognition that allows scene-dependent image modification before image recording or display | |
| CN109089041A (en) | Recognition methods, device, electronic equipment and the storage medium of photographed scene | |
| CN106210522B (en) | A kind of image processing method, device, mobile terminal and readable storage medium storing program for executing | |
| WO2001071421A1 (en) | Red-eye correction by image processing | |
| WO2016075978A1 (en) | Information processing device, information processing method, and program | |
| CN113128373B (en) | Image processing-based color spot scoring method, color spot scoring device and terminal equipment | |
| KR101854432B1 (en) | Method and apparatus for detecting and compensating back light frame | |
| US20160180148A1 (en) | Method and system for generating intrinsic images using a single reflectance technique | |
| CN111311500A (en) | Method and device for carrying out color restoration on image | |
| CN103226690B (en) | Detect blood-shot eye illness method and device, removal blood-shot eye illness method and device | |
| WO2022111269A1 (en) | Method and device for enhancing video details, mobile terminal, and storage medium | |
| JP2013156676A (en) | Image processing device, method, and program | |
| JP4831344B2 (en) | Eye position detection method | |
| CN112581380A (en) | Image color enhancement method and device and server | |
| WO2019090591A1 (en) | Photography method and photography system based on smart terminal |
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: Room 1101, 31 Guangju Road, Jianye District, Nanjing City, Jiangsu Province Applicant after: NANJING YIMAO INFORMATION TECHNOLOGY Co.,Ltd. Address before: 210000 National Leading Talents Pioneering Park, Qinhuai District, Nanjing City, Jiangsu Province, 19 (in Nanjing Design Center) Applicant before: NANJING YIMAO INFORMATION TECHNOLOGY Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171219 |