CN106981066A - A kind of interior face image dividing method based on the colour of skin - Google Patents
A kind of interior face image dividing method based on the colour of skin Download PDFInfo
- Publication number
- CN106981066A CN106981066A CN201710126258.XA CN201710126258A CN106981066A CN 106981066 A CN106981066 A CN 106981066A CN 201710126258 A CN201710126258 A CN 201710126258A CN 106981066 A CN106981066 A CN 106981066A
- Authority
- CN
- China
- Prior art keywords
- skin
- colour
- region
- mask
- oval
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Abstract
The present invention relates to a kind of interior face image dividing method based on the colour of skin, including:RGB is carried out to the conversion of YCrBr color spaces to positive face picture under white light, while the model of ellipse for constructing colour of skin cluster is filtered to candidate image, colour of skin mask is obtained;The candidate region of face is obtained based on colour of skin mask, makees boundary rectangle, and the preliminary oval cut zone of generation is split to artwork;Construct shrink space and judge mask, and logical operation is carried out with the skin distribution figure in elliptic region, obtain the remaining non-skin pixel number of four direction, and in this, as adaptive shortening coefficient;Oval cut zone is updated according to constriction coefficient;Iteration, until iterations is reached in the range of the upper limit or contraction factor arrival specification error, stops iteration, exports target image.The present invention is real-time independent of any library file, and accuracy of identification is high, shrinks time-consuming few, and interior face region fitting is accurate.
Description
Technical field
The present invention relates to technical field of image processing, specifically a kind of interior face image dividing method based on the colour of skin.
Background technology
At present, there are many skin detection equipment in the market, and facial image definition that it shoots is high, take capacity and
Bandwidth is high, and the resource to system brings very big pressure;Meanwhile, when detecting all kinds of indexs, due to background and face edge picture
The interference of element distortion, the accuracy of detection can be disturbed greatly.
The skin quality detector of part main flow, the VISIA systems in such as U.S. employ and circle Selected Inspection manually are carried out after shooting image
The mode in region is surveyed to shield inactive area, while the intractability of detection algorithm is reduced, but its operation is sufficiently complex,
It is required for carrying out multiple (such as forehead, cheek) regions the positioning regulation of dozens of point every time after shooting, in user or behaviour
Consumer's Experience is significantly reduced from the perspective of work person.
Therefore, in view of the problem of above series of, for the automation of skin quality testing process, the simplification of detection algorithm,
The lightweight that image is propagated and stored, the present invention proposes a kind of interior face image dividing method based on the colour of skin.
The content of the invention
There is provided a kind of interior face image based on the colour of skin point in order to overcome drawbacks described above present in prior art by the present invention
Segmentation method, is carried out the inactive pixels of smooth segmentation, shielding face week and background to face part in face based on area of skin color, reduced
Capacity shared by image, reduces algorithm detection difficulty.
To solve the above problems, the interior face image dividing method proposed by the present invention based on the colour of skin, comprises the following steps:
Step 1: RGB is carried out to the conversion of YCrBr color spaces to positive face picture under white light, while constructing colour of skin cluster
Model of ellipse candidate image is filtered, obtain colour of skin mask;
Step 2: obtaining the candidate region of face based on colour of skin mask, make boundary rectangle, and generate preliminary oval segmentation
Region is split to artwork, by colour of skin mask and the logical operation of oval cut zone, obtains the colour of skin in elliptic region
Distribution map, and calculate the (skin area/area elliptica in skin accounting=elliptic region of the skin accounting in segmentation candidates region
The domain gross area), it regard it as one of end determination flag of iteration;
Step 3: judging to cover in the top of elliptic region, bottom, left part, four placement configurations shrink spaces of right part respectively
Film, and logical operation is carried out with the skin distribution figure in elliptic region, the remaining non-skin pixel number of four direction is obtained, with
The remaining non-skin pixel number of four direction determines the contraction rate of four direction as adaptive shortening coefficient;
Step 4: according to the constriction coefficient of four direction, adjusting oval central point and transverse and longitudinal axle radius, oval point is updated
Cut region;
Step 5: repeat step three and step 4, until iterations reaches the upper limit or the arrival of four direction contraction factor
In the range of specification error, stop iteration, export target image.
In above-mentioned technical proposal, oval central point abscissa is determined by the difference of left and right constriction coefficient in the step 4,
Ordinate is determined by the difference for pushing up bottom constriction coefficient, left and right, top bottom constriction coefficient is tended to be equal respectively after renewal;Oval transverse axis
Radius is determined that longitudinal axis radius is determined by pushing up bottom constriction coefficient average, and transverse and longitudinal axle radius is made after renewal by left and right constriction coefficient average
Shorten, inside face shrinks.
The principle of interior face image dividing method proposed by the present invention based on the colour of skin is as follows:
Segmented shape:In view of the interior face shape of face of people and effective coverage, this method uses ellipse for main segmented shape.It is ellipse
Circular top part is face hair line, and the pad interference below capture apparatus is considered in bottom, segmentation to lower lip and chin lower edge it
Between, particular location is relevant with the illumination brightness of chin, and the right and left occurs without ear and be defined on the inside of two ears.Elliptical shape
Changed by central point and transverse and longitudinal radius, by calculating adjustment elliptic region to optimum range.
Skin cluster:The colour of skin of people can tend to a less region after cluster in different color spaces.There is reality
Test and show, distribution of the colour of skin in YCrBr color spaces is similar to an ellipse, therefore can be with the region threshold in the color space
Value to carry out extraction calculating to the skin area in image.
Shrink at edge:Because the first cut zone for relying on Face Detection and obtaining can not be fitted face edge well,
Exist and do not reject complete background residual, therefore this method adds the shrink space detection of four direction, and carry out adaptive
The contraction iteration of stepping is so that cut zone is fitted interior face edge as far as possible.
The present invention has the advantages that and advantage compared with prior art:
1) model of ellipse based on YCrBr color spaces of the invention carries out Face Detection, independent of any library file, real
Shi Xingqiang, accuracy of identification is high;
2) present invention is fitted interior face cut zone using elliptical shape, and inwardly enters from four direction by successive ignition
Row adaptive shortening, shrinks time-consuming few, and interior face region fitting is accurate.
Embodiment
Below in conjunction with specific embodiment, the present invention is described in further detail:
In the present embodiment, the interior face image dividing method proposed by the present invention based on the colour of skin comprises the following steps:
Step 1: RGB is carried out to the conversion of YCrBr color spaces to positive face picture under white light, while constructing colour of skin cluster
Model of ellipse candidate image is filtered, obtain colour of skin mask, oval top is face hair line, and bottom is considered to shoot
Pad interference below equipment, splits between lower lip and chin lower edge, particular location is relevant with the illumination brightness of chin, left
Right both sides occur without ear and are defined on the inside of two ears;
Step 2: obtaining the candidate region of face based on colour of skin mask, make boundary rectangle, and generate preliminary oval segmentation
Region is split to artwork, by colour of skin mask and the logical operation of oval cut zone, obtains the colour of skin in elliptic region
Distribution map, and calculate the (skin area/area elliptica in skin accounting=elliptic region of the skin accounting in segmentation candidates region
The domain gross area), it regard it as one of end determination flag of iteration;
Step 3: judging to cover in the top of elliptic region, bottom, left part, four placement configurations shrink spaces of right part respectively
Film, and logical operation is carried out with the skin distribution figure in elliptic region, the remaining non-skin pixel number of four direction is obtained, with
The remaining non-skin pixel number of four direction determines the contraction rate of four direction as adaptive shortening coefficient;
Step 4: according to the constriction coefficient of four direction, adjusting oval central point and transverse and longitudinal axle radius, oval point is updated
Cut region, wherein oval central point abscissa is determined by the difference of left and right constriction coefficient, ordinate by top bottom constriction coefficient difference
Determine, left and right, top bottom constriction coefficient is tended to be equal respectively after renewal;Oval transverse axis radius is determined by left and right constriction coefficient average
Fixed, longitudinal axis radius is determined by pushing up bottom constriction coefficient average, shortens transverse and longitudinal axle radius after renewal, and inside face shrinks;
Step 5: repeat step three and step 4, until iterations reaches the upper limit or the arrival of four direction contraction factor
In the range of specification error, stop iteration, export target image.
Finally illustrate, the above embodiments are merely illustrative of the technical solutions of the present invention and it is unrestricted, although with reference to compared with
The present invention is described in detail good embodiment, it will be understood by those within the art that, can be to skill of the invention
Art scheme is modified or equivalent substitution, and without departing from the objective and scope of technical solution of the present invention, it all should cover at this
In the right of invention.
Claims (2)
1. a kind of interior face image dividing method based on the colour of skin, it is characterised in that comprise the following steps:
Step 1: RGB is carried out to the conversion of YCrBr color spaces to positive face picture under white light, while constructing the ellipse of colour of skin cluster
Circle model is filtered to candidate image, obtains colour of skin mask;
Step 2: obtaining the candidate region of face based on colour of skin mask, make boundary rectangle, and the center according to rectangle and length and width ginseng
The preliminary oval cut zone of number generation is split to artwork, is transported by colour of skin mask and the logical AND of oval cut zone
Calculate, obtain the skin distribution figure in elliptic region, and calculate the skin accounting in segmentation candidates region, be used as algorithm iteration knot
One of beam Judging index, i.e., when skin accounting reaches default threshold value, expression meets segmentation demand, exits algorithm iteration mistake
Skin area/elliptic region gross area in journey, the skin accounting=elliptic region;
Step 3: respectively in the region of top 1/3 of elliptic region, the region of bottom 1/3, the region of left part 1/6, the region four of right part 1/6
Individual placement configurations shrink space judges mask, and carries out logical operation with the skin distribution figure in elliptic region, obtains four sides
To remaining non-skin pixel number, determined using the remaining non-skin pixel number of four direction as adaptive shortening coefficient
The contraction rate of four direction;
Step 4: according to the constriction coefficient of four direction, adjusting oval central point and transverse and longitudinal axle radius, oval cut section is updated
Domain;
Step 5: repeat step three and step 4, until the contraction factor arrival that iterations reaches the upper limit or four direction refers to
Determine in error range, stop iteration, export target image.
2. the interior face image dividing method according to claim 1 based on the colour of skin, it is characterised in that ellipse in the step 4
Round central point abscissa is determined that ordinate is determined by the difference for pushing up bottom constriction coefficient, is made after renewal by the difference of left and right constriction coefficient
Left and right, top bottom constriction coefficient tend to be equal respectively;Oval transverse axis radius determines by left and right constriction coefficient average, longitudinal axis radius by
Push up bottom constriction coefficient average to determine, shorten transverse and longitudinal axle radius after renewal, inside face shrinks.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710126258.XA CN106981066B (en) | 2017-03-06 | 2017-03-06 | A kind of interior face image dividing method based on the colour of skin |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710126258.XA CN106981066B (en) | 2017-03-06 | 2017-03-06 | A kind of interior face image dividing method based on the colour of skin |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106981066A true CN106981066A (en) | 2017-07-25 |
CN106981066B CN106981066B (en) | 2019-07-12 |
Family
ID=59338658
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710126258.XA Active CN106981066B (en) | 2017-03-06 | 2017-03-06 | A kind of interior face image dividing method based on the colour of skin |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106981066B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110378327A (en) * | 2019-07-09 | 2019-10-25 | 浙江大学 | Add the object detecting device and method of complementary notable feature |
CN111259806A (en) * | 2020-01-16 | 2020-06-09 | 广州杰赛科技股份有限公司 | Face region identification method and device and storage medium |
CN111507944A (en) * | 2020-03-31 | 2020-08-07 | 北京百度网讯科技有限公司 | Skin smoothness determination method and device and electronic equipment |
CN112381046A (en) * | 2020-11-30 | 2021-02-19 | 华南理工大学 | Multitask posture-invariant face recognition method, system, device and storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040037460A1 (en) * | 2002-08-22 | 2004-02-26 | Eastman Kodak Company | Method for detecting objects in digital images |
US20040213476A1 (en) * | 2003-04-28 | 2004-10-28 | Huitao Luo | Detecting and correcting red-eye in a digital image |
WO2010082942A9 (en) * | 2008-02-01 | 2011-01-20 | Canfield Scientific, Incorporated | Automatic mask design and registration and feature detection for computer-aided skin analysis |
CN102270303A (en) * | 2011-07-27 | 2011-12-07 | 重庆大学 | Joint detection method for sensitive image |
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 |
CN105205480A (en) * | 2015-10-31 | 2015-12-30 | 潍坊学院 | Complex scene human eye locating method and system |
CN105224917A (en) * | 2015-09-10 | 2016-01-06 | 成都品果科技有限公司 | A kind of method and system utilizing color space to create skin color probability map |
CN105809089A (en) * | 2014-12-29 | 2016-07-27 | 中国科学院深圳先进技术研究院 | Multi-face detection method and device under complex background |
-
2017
- 2017-03-06 CN CN201710126258.XA patent/CN106981066B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040037460A1 (en) * | 2002-08-22 | 2004-02-26 | Eastman Kodak Company | Method for detecting objects in digital images |
JP2010102725A (en) * | 2002-08-22 | 2010-05-06 | Eastman Kodak Co | Method for detecting object in digital image |
EP1394723A3 (en) * | 2002-08-22 | 2011-04-13 | Eastman Kodak Company | Method for detecting red-eye effect in digital images |
US20040213476A1 (en) * | 2003-04-28 | 2004-10-28 | Huitao Luo | Detecting and correcting red-eye in a digital image |
WO2010082942A9 (en) * | 2008-02-01 | 2011-01-20 | Canfield Scientific, Incorporated | Automatic mask design and registration and feature detection for computer-aided skin analysis |
CN102270303A (en) * | 2011-07-27 | 2011-12-07 | 重庆大学 | Joint detection method for sensitive image |
CN105809089A (en) * | 2014-12-29 | 2016-07-27 | 中国科学院深圳先进技术研究院 | Multi-face detection method and device under complex background |
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 |
CN105224917A (en) * | 2015-09-10 | 2016-01-06 | 成都品果科技有限公司 | A kind of method and system utilizing color space to create skin color probability map |
CN105205480A (en) * | 2015-10-31 | 2015-12-30 | 潍坊学院 | Complex scene human eye locating method and system |
Non-Patent Citations (4)
Title |
---|
MOHD. ZAMRI OSMAN等: "Improved Skin Detection based on Dynamic Threshold using Multi-Colour Space", 《IEEE》 * |
PAN NG等: "Skin Segmentation Based on Human Face Illumination Feature", 《ACM》 * |
俞王新等: "一种基于肤色模型和眼睛定位的人脸检测方法", 《计算机工程与应用》 * |
黄禹馨等: "基于肤色和器官定位的实时人脸检测", 《计算机工程与科学》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110378327A (en) * | 2019-07-09 | 2019-10-25 | 浙江大学 | Add the object detecting device and method of complementary notable feature |
CN110378327B (en) * | 2019-07-09 | 2021-05-18 | 浙江大学 | Target detection device and method with auxiliary significant features added |
CN111259806A (en) * | 2020-01-16 | 2020-06-09 | 广州杰赛科技股份有限公司 | Face region identification method and device and storage medium |
CN111259806B (en) * | 2020-01-16 | 2023-11-14 | 广州杰赛科技股份有限公司 | Face area identification method, device and storage medium |
CN111507944A (en) * | 2020-03-31 | 2020-08-07 | 北京百度网讯科技有限公司 | Skin smoothness determination method and device and electronic equipment |
CN111507944B (en) * | 2020-03-31 | 2023-07-04 | 北京百度网讯科技有限公司 | Determination method and device for skin smoothness and electronic equipment |
CN112381046A (en) * | 2020-11-30 | 2021-02-19 | 华南理工大学 | Multitask posture-invariant face recognition method, system, device and storage medium |
CN112381046B (en) * | 2020-11-30 | 2023-02-14 | 华南理工大学 | Multitask posture-invariant face recognition method, system, device and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN106981066B (en) | 2019-07-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106981066A (en) | A kind of interior face image dividing method based on the colour of skin | |
CN109636732A (en) | A kind of empty restorative procedure and image processing apparatus of depth image | |
CN107730444A (en) | Image processing method, device, readable storage medium storing program for executing and computer equipment | |
CN109711268B (en) | Face image screening method and device | |
CN110022463A (en) | Video interested region intelligent coding method and system are realized under dynamic scene | |
CN107230207A (en) | The detection method and system of tire | |
CN106815575A (en) | The optimum decision system and its method of Face datection result set | |
CN115409745B (en) | CT image enhancement method applied to radiotherapy preparation | |
CN109657615A (en) | A kind of training method of target detection, device and terminal device | |
CN102982524B (en) | Splicing method for corn ear order images | |
CN109857255A (en) | A kind of display parameter regulation method, device and wear display equipment | |
CN109146845A (en) | Head image sign point detecting method based on convolutional neural networks | |
CN110458142A (en) | A kind of face identification method and system merging 2D and 3D | |
CN101510255A (en) | Method for identifying and positioning human face, apparatus and video processing chip | |
CN113947732B (en) | Aerial visual angle crowd counting method based on reinforcement learning image brightness adjustment | |
CN110390657A (en) | A kind of image interfusion method | |
CN104598914A (en) | Skin color detecting method and device | |
CN104282013B (en) | A kind of image processing method and device for foreground target detection | |
JPH08122944A (en) | Exposure deciding method | |
CN105809085B (en) | Human-eye positioning method and device | |
CN109145865A (en) | Face standard level calculating method and device | |
CN103578121B (en) | Method for testing motion based on shared Gauss model under disturbed motion environment | |
CN110648336B (en) | Method and device for dividing tongue texture and tongue coating | |
CN108416304A (en) | A kind of three classification method for detecting human face using contextual information | |
CN107123103A (en) | Double exposure fusion method based on local energy gradient operator |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |