CN101511267A - Method of measuring blemishes on skin - Google Patents
Method of measuring blemishes on skin Download PDFInfo
- Publication number
- CN101511267A CN101511267A CNA2007800329534A CN200780032953A CN101511267A CN 101511267 A CN101511267 A CN 101511267A CN A2007800329534 A CNA2007800329534 A CN A2007800329534A CN 200780032953 A CN200780032953 A CN 200780032953A CN 101511267 A CN101511267 A CN 101511267A
- Authority
- CN
- China
- Prior art keywords
- skin
- spots
- image
- colour
- pixel
- 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
Images
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
Assessment of the efficacy of compositions to correct imperfections of the skin is an important part of the activity in the development of skin products. One commonly used method for assessment of the blemishes is through use of professional clinical graders. In this method trained clinicians grade the improvement of the skin appearance over extended use of the product. This assessment is subjective and expensive. Thus a method of measuring blemishes on the skin, particularly dark skin, is provided comprising the steps of: (a) acquiring a colour digital image of the skin; (b) selecting either the blue or the green colour channel of the image based on the average colour of the skin; (c) subjecting the selected colour channel to a Gaussian filter operation to obtain an intensity value for each pixel; (d) binarizing the image into pixels of either a black or a white colour using a predetermined threshold intensity value; and (e) counting the number of black pixels.
Description
Technical field
The present invention relates to a kind of method of measuring the spots on the skin, and relate more specifically to a kind of method of measuring and following the tracks of as the people's of the dark skin of Aisan etc. spots.
Background technology
People's skin has many defectives.The part that exposes as skins such as facial, cervical region and hands is more prone to defectiveness owing to exposing to the open air in sunlight and the air stimulation thing as pollutant etc.Defective may be because localised skin pigmentation, and for example sunburn, freckle etc. and cause perhaps may be because long comedo causes local deepening to cause afterwards.
The effect that evaluation is used for the composition of maintenance skin defect is the very important part of skin care item development activities.The method that spots is evaluated in a kind of commonly used being used to is by using the clinical scale personnel (grader) of specialty.In the method, housebroken clinicist will carry out classification through constantly using the improvement of the skin appearance of this product.This evaluation is subjectivity and expensive.Therefore, exist many trials to use image analysis method based on instrument objectively with the skin appearance classification.
EP 516 457 (Unilever, 1992) a kind of equipment that is used to measure the variation of cutaneous pigmentation aspect has been described, it has measured light with two kinds of wavelength by the reflection of skin, and a kind of wavelength is in 800 to 1500nm scopes, and second kind of wavelength is in 600 to 750nm scopes.The prior art requires to use the optical wavelength of an above scope.Need develop simpler method, wherein use the image of the skin of normal illumination condition to can be used for measuring defective on the skin.
US6571003 (Procter﹠amp; Gamble, 2003) a kind of method that is used for determining the position of one or more visible skin defects on the human body has been described, comprising: first digital picture that obtains human body; This first digital picture of this human body of electronic analysis is with the position in the zone of determining to comprise skin defect; Determine to comprise the first numerical value order of severity of the zone association of skin defect with this; And generate fiducial value between this first numerical value order of severity and the threshold definite value relevant with people race.
US 6761697 (L ' Oreal, 2004) differentiation of at least one situation (condition) of a kind of health outer portion that is used to estimate main body has been described, this method comprises: receive first data, wherein the health outer portion of this first data representation object at least one situation in very first time frame; Receive second data, the health outer portion of this second data representation object this at least one situation in second time frame wherein, this second time frame appears at after this very first time frame; The prediction of this at least one situation that generates the health outer portion of this object based on these first data and second data develops; And should predict that differentiation sent this main body to.
Prior art above-mentioned is announced to have described and is used to follow the tracks of the overall beautiful situation of skin and based on the possible sight of this tracking data comparison/expectation.Do not relate to specially in the prior art providing solution about the fractional problem of spots quantity is provided at the image of spots on the analyzing skin and with highly representative and reproducible mode.And still existing and need providing a kind of is to increase or the solution of the problem of minimizing at following the tracks of spots to measure the spots order of severity.This is being that people's the spots of the dark skin of the people etc. in 6 to 9 scopes of scale (10 for the darkest) needs especially for measuring and follow the tracks of the colour of skin in for example Aisan, the particularly South Asia region with 10.
Therefore the object of the invention is to provide a kind of and is used to use the digital picture that obtains under the normal illumination condition to measure the method and system of the spots on the skin.
Another object of the present invention is to provide a kind of and is used to use the digital picture that obtains under the normal illumination condition to follow the tracks of the method and system of the spots development and change in time on the skin.
Further object of the present invention is to provide the method and system of a kind of people's who is specially adapted to measure and follow the tracks of dark skin spots.
Summary of the invention
According to one aspect of the invention, a kind of method that is used to measure the skin spots is provided, may further comprise the steps:
(a) obtain the color digital image of this skin;
(b) select the blueness or the green channel of this image according to the average colour of skin of skin;
(c) make selected Color Channel through Gaussian filter operation to obtain the brightness value of each pixel;
(d) use the predetermined threshold brightness value that this image binaryzation is black or white pixel;
(e) quantity of counting black picture element.
Particularly preferably, this method comprises measures the average colour of skin 10 to be spots on the application on human skin of the dark skin in 6 to 9 scopes of scale, and wherein 10 for the darkest.
According to a further aspect in the invention, provide a kind of system that is used to implement this method of the present invention, comprise the parts of the digital picture that is used to obtain this skin, be connected with the parts that are used to implement Flame Image Process during its work.
Detailed description of the present invention
The present invention be primarily aimed at be used to measure with analyzing skin on the method for spots.This measurement can be primarily aimed at the exposed parts as hand, cervical region and face etc. at any part of this skin.This method relates to uses the simple color digital camera and as the image analysis part of personal computer etc.The invention provides objective measurement to blemish size, shape and growth.Measurement of the present invention is with to analyze the classification with housebroken clinical scale personnel very relevant, the subjectivity that relates to is minimized and reduced cost and the uncertainty of this availability through the trainer.
This purpose of the present invention and other purposes, its advantage and using method are now described by following detailed description and figure.Draw and formed some embodiments of the present invention and only involved for illustration purpose at figure described herein.These should be by as being to limit the present invention by any way, because concerning the reader, clearly many such embodiment are possible and do not depart from scope of the present invention.Given this, for those skilled in that art, will propose variations and modifications, all such changes and modifications are all in spirit of the present invention and protection domain.
Description of drawings
Fig. 1 is the sketch map that is used to measure the process of the spots on the skin.
Fig. 2 has described to have many spots and the average colour of skin is the digital picture of Aisan's face of 7 (are scale with 10);
Fig. 2 a shows the Fig. 2 through process of the present invention, promptly wherein selects green channel to be used for Flame Image Process.
Fig. 2 b shows Fig. 2 of the process beyond the present invention, promptly wherein selects blue channel to be used for Flame Image Process to Aisan's skin type of dark skin.
Fig. 2 c shows Fig. 2 of the process beyond the present invention, promptly wherein selects red channel to be used for Flame Image Process to Aisan's skin type of dark skin.
The specific embodiment
Fig. 1 is the sketch map that is used to quantize the process of spots quantity on the skin.Method of the present invention relates to following key step.
At first obtain the digital picture of skin.This obtains noiseless by use colorful digital camera and the good digital picture of resolution realizes.Adjust the position of camera, make all images of acquisition under the fixed-illumination condition.Image is usually digitized as 2048 * 1536 matrixes, and wherein each pixel in the matrix has the colour brightness value.Preferably data are passed to the parts that are used for graphical analysis, for example personal computer then.Determine the average color of skin image then by the brightness of calculating picture.This can use any canonical algorithm in the image analysis software to finish.
Image mainly is made up of three kinds of Color Channels, redness, green and blue channels.By the extensive experiment of various skin types is determined, when select blue channel to be used for the analysis of the bright colour of skin and when skin is dark the selection green channel, be best for the quantification of spots quantity on the skin.Therefore according to the present embodiment of invention, when the average colour of skin during less than 4 (scale is 1-10, and 10 for the darkest), the selection blue channel.Therefore blue channel mainly is applicable to caucasian skin colours.When the average colour of skin is selected green channel during greater than 5 (scale is 1-10, and 10 for the darkest).Therefore green channel mainly is applicable to Aisan's colour of skin, particularly people from South Asia region colour of skin.
Digital picture is in discrete domain, and wherein each pixel has the brightness value that is associated with it.Brightness value has big discontinuity, particularly in having the zone of spots.In the process of making decision at quantification spots quantitative aspects, be convenient to Flame Image Process calculating and strengthen color contrast simultaneously, have been found that and work as selected Color Channel through Gaussian filter operation, obtained optimum.The following describes this filtering operation.
Suppose image digitization is turned to image with 20 * 20 matrix formats.Gaussian Blur is to be used for the instrument that the fine detail of the digital picture in image optionally is fuzzy basically.This also is based on the filtering of matrix.Therefore, be 3, promptly 3 * 3 gaussian filterings if 20 * 20 image arrays are used radius, then the trickle image primitive in per the 3rd pixel may be by obfuscation in the row and column of 20 * 20 image arrays.Therefore, the radius of employing is big more, and removed fine detail grade is just big more.Low radius value is only removed very fine details, and high radius value can be removed the details than large level.When being applied to two dimension, this has produced its profile is concentrically ringed surface, and these concentric circulars have the Gauss distribution from central point.Wherein this pixel that is distributed as non-zero is used to set up convolution matrix, and this convolution matrix is applied to original image.The value of each pixel is made as the weighted mean of the neighbor of this pixel.The value of original pixels obtains weight limit (having Gauss's value), and neighbor is along with they obtain littler weight from original pixels apart from increase.This Gaussian filter operation produce will be good than other fuzzy filter computings protection border and edge fuzzy.
Gaussian filter operation is unique, wherein except complete circular symmetry, its can be used as two independently one dimension calculate and to be used for two dimensional image.That is, repeat the effect that this process also can obtain to use two-dimensional matrix then in vertical direction by using a series of one-dimensional Gauss matrixes in the horizontal direction.
Observing, is to make poor between the image that original image obtains after the Gaussian filter operation of twice selection when the Gaussian filter operation that makes original image through twice selection has obtained optimum and consequent image.Preferably in the 20-40 scope, more preferably in the scope of 20-30, the best is 25 to the radius that is used for meticulousr filtering operation.The radius that is used for the computing of coarse filtration ripple is in the 20-50 scope, and more preferably in the 20-40 scope, the best is 30.
Therefore according to the present embodiment that is applied to the invention of Aisan's skin type, made two copies of the selected green channel of original image, and called after image 1 and image 2.Image 1 through the fine Gaussian filter operation of r=radius 20 with construction drawing as 1a.Then image 2 through the rough Gaussian filter operation (gross Gausian filter) of radius R=30 with construction drawing as 2a.From image 2a subtracted image 1a with construction drawing as 3.
Then with image 3 binaryzations with construction drawing as 4.This computing relates to selects threshold value colour brightness value.The all pixel of colour brightness value more than selected threshold value are given black and given white with the pixel of colour brightness value below selected threshold value.Then image 4 is last image, and it describes spots with quantitative manner.Spots quantity can be described as the number that obtains by counting black picture element quantity.
Fig. 2 has described the coloured image of Aisan's face.That Fig. 2 a, 2b and 2c have described respectively to use is green, facial image among Fig. 2 of blueness and red channel.The image of Fig. 2 also by housebroken clinicist according to the spots degree by classification.From the data of clinical scale with the most relevant from the data of Fig. 2 a.
The present invention also is suitable for skin spots quantity method over time as a comparison.Method of the present invention also comprises the method for the development and change of following the tracks of specific interested spots.This method may further comprise the steps: interested spots on the digital picture of (i) selecting to obtain; (ii) measure average gray value, maximum gradation value and the minimum gradation value of interested spots; (iii) calculate the standard deviation of spots; And (iv) more in time standard deviation.With the gray level of pixel be defined as function f (x, y) at arbitrary coordinate to (wherein (x y) is the two-dimensional function of presentation video to f for x, the amplitude of y) locating.
The development and change of relatively representing spots of standard deviation value in time.If standard deviation reduces, its expression spots is reducing, and if the standard deviation increase represents that then blemish size is increasing.
The present invention also provides a kind of system that is used to implement the inventive method, and this system comprises the parts of the digital picture that is used to obtain skin, is connected with the parts that are used to implement Flame Image Process during its work.
The present invention also provides a kind of method and system of measuring and follow the tracks of the spots development and change in time on the skin in the digital picture that obtains under the normal illumination condition that is used to use, especially at the people of dark skin.
Claims (9)
1. method that is used to measure the skin spots may further comprise the steps:
(a) color digital image of the described skin of acquisition;
(b) select the blueness or the green channel of described image according to the average colour of skin of described skin;
(c) make selected Color Channel through Gaussian filter operation to obtain the brightness value of each pixel;
(d) use the predetermined threshold brightness value that described image binaryzation is black or white pixel;
(e) quantity of counting black picture element.
2. the method for claim 1 is if the wherein described average colour of skin is lower than the predetermined colour of skin then selects described blue channel, if the described average colour of skin is higher than the described predetermined colour of skin then selects described green channel.
3. method as claimed in claim 2 wherein selects described blueness then to select green channel at Aisan's skin at white people's skin.
4. as the described method of arbitrary claim among the claim 1-3, wherein the brightness value of each pixel is with the difference of described image through the brightness value that gaussian filtering obtained of twice predetermined radii.
5. method that is used to follow the tracks of skin spots quantity in time, it comprises as the method for the described measurement skin of arbitrary claim spots and following additional step among the claim 1-4:
(a) step before repeating constantly after a while; And
(b) compare skin spots quantity over time.
6. method that is used to follow the tracks of the spots development and change, it comprises method and following additional step as the described measurement skin of arbitrary claim spots among the claim 1-5:
(a) interested spots in the digital picture of selecting to be obtained;
(b) average gray value, maximum gradation value and the minimum gradation value of the described interested spots of measurement;
(c) standard deviation of the described spots of calculating; And
(d) standard deviation more in time.
7. system that is used for implementing as the described method of the arbitrary claim of claim 1-6, it comprises the parts of the digital picture that is used to obtain described skin, is connected with the parts that are used to implement Flame Image Process during described parts work.
8. system as claimed in claim 7, the described parts that wherein are used to obtain digital picture are digital camera.
9. one kind as claim 7 or 8 described systems, and the described parts that wherein are used to implement Flame Image Process are personal computer.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| IN1437/MUM/2006 | 2006-09-07 | ||
| IN1437MU2006 | 2006-09-07 | ||
| EP07250851.8 | 2007-03-01 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101511267A true CN101511267A (en) | 2009-08-19 |
Family
ID=41003390
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2007800329534A Pending CN101511267A (en) | 2006-09-07 | 2007-09-03 | Method of measuring blemishes on skin |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101511267A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111160366A (en) * | 2019-12-18 | 2020-05-15 | 山东鹰格信息工程有限公司 | Color image identification method |
| CN111542856A (en) * | 2018-07-16 | 2020-08-14 | 华为技术有限公司 | Skin detection method and electronic equipment |
| CN111836575A (en) * | 2018-06-21 | 2020-10-27 | 松下知识产权经营株式会社 | Skin evaluation device, skin evaluation system, skin evaluation method, and computer-readable recording medium storing program for skin evaluation |
-
2007
- 2007-09-03 CN CNA2007800329534A patent/CN101511267A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111836575A (en) * | 2018-06-21 | 2020-10-27 | 松下知识产权经营株式会社 | Skin evaluation device, skin evaluation system, skin evaluation method, and computer-readable recording medium storing program for skin evaluation |
| CN111542856A (en) * | 2018-07-16 | 2020-08-14 | 华为技术有限公司 | Skin detection method and electronic equipment |
| CN111160366A (en) * | 2019-12-18 | 2020-05-15 | 山东鹰格信息工程有限公司 | Color image identification method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106529429B (en) | A kind of skin of face analysis system based on image recognition | |
| KR101713086B1 (en) | Transparency evaluation device, transparency evaluation method and transparency evaluation program | |
| JP5146667B2 (en) | Evaluation method of skin smoothness | |
| US6885369B2 (en) | Method and apparatus for acquiring luminance information and for evaluating the quality of a display device image | |
| US20080080766A1 (en) | Apparatus and Method for Analyzing Skin Using L*a*b* Colorspace | |
| KR20080016847A (en) | Methods of chromogen separation-based image analysis | |
| JP2012245356A (en) | Method for characterizing tone of skin and integument | |
| US10345100B1 (en) | Apparatus and method for evaluating metal surface texture | |
| CA2604684A1 (en) | Method of estimating a visual evaluation value of beauty of a skin | |
| JP4383352B2 (en) | Histological evaluation of nuclear polymorphism | |
| WO2008028893A1 (en) | Method of measuring blemishes on skin | |
| JPH0938045A (en) | Skin evaluation method | |
| CN109460710A (en) | A kind of color classification recognition methods, device and automated driving system | |
| CN101511267A (en) | Method of measuring blemishes on skin | |
| JP2019058641A (en) | Skin inner structure estimation method, skin inner structure estimation program, and skin inner structure estimation device | |
| CN112488997B (en) | Method for detecting and evaluating color reproduction of ancient painting printed matter based on characteristic interpolation | |
| CN106204523A (en) | A kind of image quality evaluation method and device | |
| CN116612110B (en) | Intelligent quality assessment method for gradual change printing and dyeing effect | |
| US9668653B2 (en) | Quantification of under-eye skin color | |
| JP2009536316A (en) | Method and apparatus for measuring the surface quality of a support layer | |
| JP2944309B2 (en) | Skin surface morphological feature detection method | |
| CN110793472B (en) | Grinding surface roughness detection method based on quaternion singular value entropy index | |
| JPH06222002A (en) | Method and equipment for measuring unevenness of luster and print | |
| JP4001549B2 (en) | Evaluation method of skin condition | |
| US5619319A (en) | Apparatus for acquiring data used to evaluate and reproduce the color of a sample on the basis of the chroma and glossiness of the sample |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20090819 |