CN111986151A - Skin color detection method and device - Google Patents
Skin color detection method and device Download PDFInfo
- Publication number
- CN111986151A CN111986151A CN202010693806.9A CN202010693806A CN111986151A CN 111986151 A CN111986151 A CN 111986151A CN 202010693806 A CN202010693806 A CN 202010693806A CN 111986151 A CN111986151 A CN 111986151A
- Authority
- CN
- China
- Prior art keywords
- skin
- color
- skin color
- image
- values
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 39
- 230000003796 beauty Effects 0.000 claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 12
- 239000011159 matrix material Substances 0.000 claims description 80
- 239000003086 colorant Substances 0.000 claims description 14
- 238000012937 correction Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 12
- 238000002835 absorbance Methods 0.000 claims description 11
- 239000002537 cosmetic Substances 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 241000282412 Homo Species 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000036555 skin type Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
-
- G06T5/90—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/10004—Still image; Photographic image
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30088—Skin; Dermal
Abstract
The disclosure provides a skin color detection method and device. The method comprises the following steps: establishing a human skin color card database; r, G, B chromatic value of the skin image is obtained and corrected; converting R, G, B colorimetric values of the corrected skin image into skin color values, and calculating an overall skin color statistical value of the skin color image; and selecting the color number of the human skin color closest to the integral skin color statistic value from the human skin color card database according to the integral skin color statistic value of the skin color image. The method improves the accuracy of the acquired skin image data by correcting the R, G, B chromaticity value of the acquired skin image. On the other hand, a human body skin color card database is established based on a standard human body skin color card to ensure that the color number of the detected skin can be identified more accurately, so that the laser parameters of the beauty medical equipment can be adjusted more accurately according to the color number of the skin color to achieve the best beauty effect.
Description
Technical Field
The disclosure relates to a skin color detection method and a device for realizing the skin color detection method, belonging to the technical field of skin color detection.
Background
With the continuous development of image recognition technology, various products based on the image recognition technology come into operation, which not only brings great convenience to the life of people, but also improves the life quality of people.
The problem of skin complexion confirmation by using an image recognition technology is a problem to be solved urgently in the skin beautifying industry. The problems to be solved by the technology include: how to accurately divide the acquired skin image into the skin and the background, whether the classification accuracy directly influences the next processing, such as the identification of skin color, the ratio of skin color number, and the like.
Therefore, the improvement of the accuracy of skin color detection has important research significance. On the other hand, accurate skin color detection is very difficult, and for example, subtle differences in human skin color, colored lights, shadows, and strong light, CCD color cast, etc., all affect the correct identification of skin color. Especially in complex lighting situations, the detection of skin tones is more challenging.
Disclosure of Invention
The first technical problem to be solved by the present disclosure is to provide a skin color detection method.
Another technical problem to be solved by the present disclosure is to provide an apparatus for implementing the above skin color detection method.
In order to achieve the purpose, the following technical scheme is adopted in the disclosure:
according to a first aspect of the embodiments of the present disclosure, there is provided a skin color detection method, including the steps of:
designing a color card matrix;
establishing a human skin color card database;
r, G, B chromatic value of the skin image is obtained and corrected;
converting R, G, B colorimetric values of the corrected skin image into skin color values, and calculating an overall skin color statistical value of the skin color image;
and selecting the color number of the human skin color closest to the integral skin color statistic value from the human skin color card database according to the integral skin color statistic value of the skin color image.
Preferably, the color card matrix is composed of N × N code elements, N is a positive integer, the color card matrix arbitrarily selects three corner positions to set positioning code elements, a window composed of M × M code elements is arranged at the center position of the color card matrix, M is a positive integer, and black, white, red, green and blue reference colors are respectively added into the color card matrix.
Preferably, the human body skin color card database is composed of skin color values corresponding to each color number in a standard human body skin color card, and the skin color value corresponding to each color number is calculated according to R, G, B chroma values corresponding to each color number in the standard human body skin color card by the following formula.
Gray=0.3R+0.59G+0.11B
Preferably, the skin color value corresponding to each color number is respectively enlarged by preset times and then stored.
Preferably, the method comprises the following steps of obtaining R, G, B chroma values of the skin image and correcting the chroma values:
obtaining R, G, B chromatic values of the color card matrix and the skin image in the window;
positioning the color card matrix and the skin image in the window to obtain R, G, B chromatic values of the skin image in the window;
the R, G, B chrominance values of the skin image within the viewing window are corrected.
Preferably, when R, G, B chromaticity values of the skin image in the window are corrected, R, G, B chromaticity values of the skin image in the window are multiplied by corresponding correction coefficients of R, G, B chromaticity values respectively, and the correction coefficient of the R, G, B chromaticity values is a ratio of an original R, G, B chromaticity value to a R, G, B chromaticity value of an actually acquired color card matrix.
Preferably, when the R, G, B colorimetric values of the skin image in the corrected window are converted into skin color values, sampling is performed according to a preset interval, and after skin color values corresponding to the skin image are obtained, the skin color values are added and averaged to obtain an overall skin color statistical value of the skin image.
Preferably, if the skin color value corresponding to the color number in the database of the human skin color card is enlarged by a preset multiple, the overall skin color statistical value of the skin color image is enlarged by the same multiple as the skin color value corresponding to the color number.
According to a second aspect of the embodiments of the present disclosure, there is provided a method for adjusting laser parameters of a cosmetic medical device, which determines the absorbance of a detected skin color by using the skin color detection method; the method for adjusting the laser parameters of the cosmetic medical equipment further comprises the following steps:
and adjusting the laser parameters of the beauty medical equipment according to the absorbance of the detected skin color.
According to a third aspect of the embodiments of the present disclosure, a skin color detection device is provided, which includes a color chip matrix, a closed cover, an image acquisition device, and a processing device, where the color chip matrix is disposed at a detection port of the closed cover, a light source is disposed in the closed cover, and the image acquisition device is connected to the processing device;
the processing device is used for establishing a human body skin color card database, acquiring R, G, B colorimetric values of skin images, correcting the colorimetric values, converting R, G, B colorimetric values of the corrected skin images into skin color values, calculating an overall skin color statistical value of the skin color images, and then selecting a color number of a human body skin color closest to the overall skin color statistical value from the human body skin color card database according to the overall skin color statistical value of the skin color images.
On one hand, the skin color detection method and the skin color detection device realize the correction of R, G, B chromatic values of the acquired skin image by designing a color card matrix so as to improve the accuracy of the acquired skin image data. On the other hand, a human body skin color card database is established based on a standard human body skin color card to ensure that the color number of the detected skin can be identified more accurately, so that the laser parameters of the beauty medical equipment can be adjusted more accurately according to the color number of the skin color to achieve the best beauty effect.
Drawings
Fig. 1 is a flowchart of a skin color detection method provided by an embodiment of the present disclosure;
fig. 2 is a schematic diagram of a certain color chip matrix designed in the skin color detection method according to the embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a skin color detection device according to an embodiment of the present disclosure.
Detailed Description
The technical contents of the present disclosure are further described in detail below with reference to the accompanying drawings and specific embodiments.
In order to improve the accuracy of skin color detection, as shown in fig. 1, an embodiment of the present disclosure provides a skin color detection method, including the following steps:
step S1: and designing a color card matrix.
In the embodiment of the present disclosure, the color chip matrix is composed of N × N symbols in vertical and horizontal directions, where N is a positive integer. Wherein the size of the color chip matrix is determined by the size of the window actually used for acquiring the skin image. For example, as shown in fig. 2, when the skin image to be collected is composed of 50 × 50 pixels, the size of the window for collecting the image is the same as the size of the matrix composed of 50 × 50 pixels, and the designed color card matrix may be composed of 100 × 100 symbols.
In the designed color chip matrix, three corner positions are arbitrarily selected to set positioning code elements 1 (arbitrarily selected positioning code positions shown in fig. 2) for subsequently positioning the collected color chip matrix and the skin image in the window. And a window 2 consisting of M symbols is arranged at the central position of the color card matrix, wherein M is a positive integer. Wherein the size of the viewing window 2 is determined by the size of the skin image to be acquired. And black, white, red, green, blue reference colors are added into the color card matrix, the area of each reference color added into the color card matrix is determined according to the actually acquired skin image, and the reference colors added into the color card matrix are ensured not to be arranged in a staggered way. For example, as shown in fig. 2, black, white, red, green, and blue reference colors respectively added to the color card matrix are arranged in rows, and the black reference colors are arranged in a rectangular area surrounded by the white, red, green, and blue reference colors, and M × M symbols are left in the middle area of the black reference color area to form a window 2; the color card matrix is used for correcting the color card matrix acquired subsequently and the skin image in the window through the black, white, red, green and blue reference colors respectively added on the color card matrix.
Step S2: and establishing a human skin color card database.
And establishing a human body skin color card database based on the standard human body skin color card. In embodiments of the present disclosure, a PANTONE body color card (PANTONE Skintone) is preferably used. The Pan human skin color card collects 110 international standard skin colors, and the color number of the Pan human skin color card is mainly used for expressing the skin color closest to the body by scientifically measuring the reaction of the actual skin color of the human skin type in the whole frequency spectrum. The Pan-through human skin color card is like a comprehensive visual human skin color library and is used as a reference related to skin color. The Pantong human skin color card is the only international available color standard at present, and can be accurately matched with various skin colors.
According to R, G, B chromatic values corresponding to 110 color numbers in the Pantong human skin color card, skin color values (also called gray values) corresponding to each color number are calculated. In one embodiment of the present disclosure, the skin color value corresponding to each color number is calculated according to the following formula:
Gray=0.3R+0.59G+0.11B (1)
taking the R, G, B colorimetric value (200,169,149) corresponding to the skin color number 1Y02 SP of the pantone human body as an example, the skin color value corresponding to the color number 1Y02 SP can be calculated according to the formula (1): gray ═ 0.3 × 200+0.59 × 169+0.11 × 149 ═ 176.1. Similarly, the formula (1) can be used for respectively calculating the skin color values corresponding to 110 color numbers in the pantone human body skin color card. In order to facilitate subsequent comparison with the obtained skin image, the skin color values corresponding to each color number can be respectively expanded by 100 times and then stored to obtain a human body skin color card database. The skin color values corresponding to the enlarged partial color numbers are shown in table 1. It should be noted that the magnification of the skin color value corresponding to each color number may be set as required, as long as the skin color value corresponding to each color number is an integer.
Table 1 skin color values corresponding to skin color numbers of Pantong humans
Skintone | R | G | B | Gray value 100 |
1Y01 | 200 | 172 | 153 | 17831 |
2Y01 | 203 | 171 | 153 | 17862 |
3Y01 | 202 | 171 | 150 | 17799 |
4Y01 | 203 | 172 | 149 | 17877 |
5Y01 | 201 | 173 | 149 | 17876 |
1Y02 | 200 | 169 | 149 | 17610 |
2Y02 | 201 | 169 | 150 | 17651 |
3Y02 | 200 | 169 | 148 | 17599 |
4Y02 | 199 | 169 | 146 | 17547 |
5Y02 | 197 | 169 | 145 | 17476 |
1R02 | 199 | 168 | 150 | 17532 |
1Y03 | 197 | 166 | 145 | 17299 |
Step S3: r, G, B chroma values of the skin image are acquired and corrected for.
The step is realized by the following substeps:
step S31: r, G, B chrominance values of the color chart matrix and the skin image within the window are obtained.
The position of the window 2 of the color card matrix designed in the step S1 is closely attached to the skin, the whole color card matrix is completely in the white light illumination environment of uniform diffuse reflection, and then the image acquisition device acquires the color card matrix and the skin image in the window to acquire R, G, B chromatic values of the color card matrix and the skin image in the window. For example, the position of window 2, shown in fig. 2, where 100 × 100 symbols constitute the color card matrix is attached to the skin, and the color card matrix and the skin image in the window are collected by the image collecting device to obtain R, G, B chromaticity values of the 100 × 100 color card matrices and the skin image in the window.
Step S32: the color chip matrix and the skin image within the window are located to obtain R, G, B chrominance values of the skin image within the window.
And acquiring the boundary of the color card matrix by using the positioning code element 1 in the color card matrix to adjust the placing direction of the color card matrix, so that the placing direction of the color card matrix is accurate. Then, according to the reference colors of black, white, red, green and blue added by the color card matrix designed in advance, R, G, B colorimetric values of the reference colors of black, white, red, green and blue of the color card matrix are extracted from the collected color card matrix and the skin image in the window. The R, G, B chrominance values of the skin image within the window are derived based on the window position in the predesigned color chip matrix. As shown in fig. 2, the boundary of the image illuminating the skin is obtained using the innermost black band of the color card matrix, resulting in R, G, B chromaticity values for the 50 x 50 pixels in the viewing window.
Step S33: the R, G, B chrominance values of the skin image within the viewing window are corrected.
Due to the influence of colored light, shadow, strong light irradiation and color deviation of the image acquisition device, R, G, B chromatic values of the acquired color chart matrix and the skin image in the window have deviation. Correcting the R, G, B chromatic value of the actually obtained color card matrix according to the original R, G, B chromatic value of the color card matrix to respectively obtain correction coefficients of R, G, B chromatic value; the R, G, B chromaticity value correction factor is the ratio of the original R, G, B chromaticity value to the R, G, B chromaticity value of the actually obtained color chart matrix. Namely, the correction coefficient of the R colorimetric value is the ratio of the original R colorimetric value to the R colorimetric value of the actually obtained color card matrix; the correction coefficient of the G colorimetric value is the ratio of the original R colorimetric value to the G colorimetric value of the actually obtained color card matrix; the correction coefficient of the B colorimetric value is the ratio of the original R colorimetric value to the actually acquired B colorimetric value of the color card matrix.
Because the color card matrix and the skin image in the window are synchronously acquired by the image acquisition device, the R, G, B chromatic value of the skin image in the window can be corrected according to the correction coefficient of the R, G, B chromatic value acquired by the color card matrix. That is, the R, G, B colorimetric values of the skin image in the window are multiplied by the corresponding correction coefficients of the R, G, B colorimetric values, respectively, so that the R, G, B colorimetric values of the skin image in the corrected window can be obtained, and the accuracy of the obtained R, G, B colorimetric values of the skin image in the window is improved.
Step S4: the R, G, B colorimetric values of the corrected skin image are converted into skin color values, and then the overall skin color statistical value of the skin color image is calculated.
According to the formula (1), the R, G, B chromatic value of the skin image in the corrected window is converted into a skin color value, so that the skin color value k corresponding to the skin image is obtained1……kn(n is the number of pixels of the acquired skin image). That is, the R, G, B chromaticity values of the corrected 50 × 50 pixels are converted into corresponding skin color values, respectively.
In order to improve the conversion efficiency of the R, G, B chrominance values of the corrected skin image into skin color values, sampling may be performed at preset intervals. For example, after correction, the R, G, B colorimetric values of 50 × 50 pixel points are converted into skin color values at intervals of 25 pixel points by R, G, B colorimetric values of the corresponding pixel points, so that matrix data composed of the skin color values corresponding to 10 × 10 pixel points are obtained.
The skin color value k corresponding to the skin image1……knAnd after addition, averaging is carried out to obtain the overall skin color statistical value of the skin color image. Specifically, the overall skin color statistic of the skin color image is obtained according to the following formula (2). And if the skin color value corresponding to the color number in the database of the human body skin color card is expanded by a preset multiple, expanding the integral skin color statistical value of the skin color image by the same multiple as the skin color value corresponding to the color number.
Step S5: and selecting the color number of the human skin color closest to the integral skin color statistic value from the human skin color card database according to the integral skin color statistic value of the skin color image.
And (4) comparing the overall skin color statistical value of the skin color image obtained in the step (S4) with the skin color value corresponding to the color number in the human body skin color card database, and selecting the color number closest to the overall skin color value as the color number of the detected skin.
In addition, in another embodiment of the present disclosure, a method for adjusting laser parameters of a cosmetic medical device is provided, which determines the absorbance of a detected skin color by using the skin color detection method corresponding to the above-mentioned fig. 1 and fig. 2; the method for adjusting the laser parameters of the cosmetic medical equipment further comprises the following steps:
and adjusting the laser parameters of the beauty medical equipment according to the absorbance of the detected skin color.
Specifically, the absorbance of the detected skin color includes a strong, weak, and medium score.
Adjusting a laser parameter of the cosmetic medical device based on the absorbance of the detected skin color may include:
when the skin color absorbance is detected to be strong, the laser parameters of the beauty medical equipment are adjusted, and the output laser energy is reduced.
When the absorbance of the detected skin color is weak, the laser parameters of the beauty medical equipment are adjusted, and the output laser energy is improved.
And when the absorbance of the skin color is detected to be medium, the laser parameters of the beauty medical equipment are kept, and the laser energy is normally output.
As shown in fig. 3, the embodiment of the present disclosure further provides a skin color detection device, which includes a color chip matrix 10, a light-tight enclosure 20, an image capturing device 30, and a processing device 40. The color card matrix 10 is arranged at the position of a detection port of the light-tight closed cover 20, a light source 50 is arranged in the closed cover, and the image acquisition device 30 is connected with the processing device 40.
The color card matrix 10 is composed of N × N symbols in vertical and horizontal directions, where N is a positive integer. Positioning code elements 1 (the randomly selected positioning code positions shown in fig. 2) are arranged at three corner positions of the randomly selected color card matrix 10, and are used for subsequently positioning the acquired color card matrix and the skin image in the window. A window 2 consisting of M symbols is arranged at the central position of the color card matrix 10, wherein M is a positive integer. In addition, the color card matrix 10 is added with reference colors of black, white, red, green and blue, the area of each reference color added into the color card matrix 10 is determined according to the actually acquired skin image, and the reference colors added into the color card matrix 10 are ensured not to be arranged in a staggered manner.
The light sources provided in the light-tight enclosure 20 may be LED light sources for placing the color chip matrix 10 entirely in a uniformly diffusely reflective white light illumination environment.
The image capturing device 30 may be implemented by a CCD camera or a CMOS camera. The image capturing device 30 is configured to capture the color chart matrix and the skin image in the window, and output R, G, B colorimetric values of the color chart matrix and the skin image in the window to the processing device 40.
Specifically, the position of the window 2 of the color chart matrix 10 of the skin color detection device is closely attached to the skin, and the color chart matrix and the skin image in the window are collected by the image collection device to obtain R, G, B colorimetric values of the color chart matrix and the skin image in the window.
The processing device 40 can be implemented by an industrial personal computer or a single chip microcomputer. The processing device 40 is configured to establish a human body skin color card database, obtain R, G, B chroma values of the skin image, correct the chroma values, convert R, G, B chroma values of the corrected skin image into skin color values, calculate an overall skin color statistic value of the skin color image, and select a similar color number of the human body skin color from the human body skin color card database according to the overall skin color statistic value of the skin color image. The R, G, B colorimetric values of the acquired skin image are processed by the processing device, and finally, the process of determining the color number of the detected skin color of the skin is the same as the steps S3 to S5, which are not described herein again.
On one hand, the skin color detection method and the skin color detection device realize the correction of R, G, B chromatic values of the acquired skin image by designing a color card matrix so as to improve the accuracy of the acquired skin image data. On the other hand, a human body skin color card database is established based on the Pantong human body skin color card to ensure that the color number of the detected skin can be identified more accurately, so that the laser parameters of the beauty medical equipment can be adjusted more accurately according to the color number of the skin color to achieve the best beauty effect.
The skin color detection method and device provided by the present disclosure are described in detail above. It will be apparent to those skilled in the art that various modifications can be made without departing from the spirit of the disclosure, and the scope of the disclosure is to be accorded the full scope of the claims appended hereto.
Claims (10)
1. A skin color detection method is characterized by comprising the following steps:
designing a color card matrix;
establishing a human skin color card database;
r, G, B chromatic value of the skin image is obtained and corrected;
converting R, G, B colorimetric values of the corrected skin image into skin color values, and calculating an overall skin color statistical value of the skin color image;
and selecting the color number of the human skin color closest to the integral skin color statistic value from the human skin color card database according to the integral skin color statistic value of the skin color image.
2. The skin color detection method as defined in claim 1, characterized in that:
the color card matrix is composed of N code elements, N is a positive integer, the color card matrix is provided with positioning code elements at any three selected corner positions, a window composed of M code elements is arranged at the central position of the color card matrix, M is a positive integer, and black, white, red, green and blue reference colors are added into the color card matrix respectively.
3. The skin color detection method as defined in claim 1, characterized in that:
the human body skin color card database consists of skin color values corresponding to each color number in a standard human body skin color card, and the skin color value corresponding to each color number is calculated according to R, G, B chromatic values corresponding to each color number in the standard human body skin color card by the following formula.
Gray=0.3R+0.59G+0.11B 。
4. A skin tone detection method as defined in claim 3, characterized by:
and respectively storing the skin color values corresponding to each color number after the skin color values are enlarged by preset times.
5. The skin color detection method as defined in claim 2, characterized in that:
r, G, B chroma value of the skin image is obtained and corrected, and the method comprises the following steps:
obtaining R, G, B chromatic values of the color card matrix and the skin image in the window;
positioning the color card matrix and the skin image in the window to obtain R, G, B chromatic values of the skin image in the window;
the R, G, B chrominance values of the skin image within the viewing window are corrected.
6. The skin tone detection method as defined in claim 5, wherein:
when R, G, B colorimetric values of the skin image in the window are corrected, R, G, B colorimetric values of the skin image in the window are multiplied by corresponding correction coefficients of R, G, B colorimetric values respectively, and the correction coefficient of the R, G, B colorimetric values is a ratio of original R, G, B colorimetric values to actually acquired R, G, B colorimetric values of the color card matrix.
7. The skin color detection method as defined in claim 1, characterized in that:
when R, G, B chromatic values of the skin image in the corrected window are converted into skin color values, sampling is carried out according to preset intervals, skin color values corresponding to the skin image are obtained, then addition and averaging are carried out, and the integral skin color statistical value of the skin color image is obtained.
8. The skin color detection method according to claim 4 or 7, characterized in that:
and if the skin color value corresponding to the color number in the database of the human body skin color card is expanded by a preset multiple, expanding the integral skin color statistical value of the skin color image by the same multiple as the skin color value corresponding to the color number.
9. A method for adjusting laser parameters of beauty medical equipment is characterized in that the method for detecting skin color according to any one of claims 1-8 is adopted to judge the absorbance of the detected skin color; the method for adjusting the laser parameters of the cosmetic medical equipment further comprises the following steps:
and adjusting the laser parameters of the beauty medical equipment according to the absorbance of the detected skin color.
10. A skin color detection device is characterized by comprising a color chip matrix, a closed cover, an image acquisition device and a processing device, wherein the color chip matrix is arranged at the position of a detection port of the closed cover;
the processing device is used for establishing a human body skin color card database, acquiring R, G, B colorimetric values of skin images, correcting the colorimetric values, converting R, G, B colorimetric values of the corrected skin images into skin color values, calculating an overall skin color statistical value of the skin color images, and then selecting a color number of a human body skin color closest to the overall skin color statistical value from the human body skin color card database according to the overall skin color statistical value of the skin color images.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010693806.9A CN111986151A (en) | 2020-07-17 | 2020-07-17 | Skin color detection method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010693806.9A CN111986151A (en) | 2020-07-17 | 2020-07-17 | Skin color detection method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111986151A true CN111986151A (en) | 2020-11-24 |
Family
ID=73439287
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010693806.9A Pending CN111986151A (en) | 2020-07-17 | 2020-07-17 | Skin color detection method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111986151A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112767257A (en) * | 2020-12-07 | 2021-05-07 | 深圳市福日中诺电子科技有限公司 | Method for improving accuracy of reduction of different skin colors |
-
2020
- 2020-07-17 CN CN202010693806.9A patent/CN111986151A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112767257A (en) * | 2020-12-07 | 2021-05-07 | 深圳市福日中诺电子科技有限公司 | Method for improving accuracy of reduction of different skin colors |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101288103B (en) | Methods and apparatus for image processing, for color classification, and for skin color detection | |
RU2567863C2 (en) | Method and system for image colour definition | |
CN101283604B (en) | Image processing device with automatic white balance | |
US7884980B2 (en) | System for capturing graphical images using hyperspectral illumination | |
CN107862657A (en) | Image processing method, device, computer equipment and computer-readable recording medium | |
CN101933321A (en) | Image sensor apparatus and method for scene illuminant estimation | |
CN110945561A (en) | Hyperspectral imaging spectrophotometer and system | |
CN106504241A (en) | A kind of apparatus and method of checking colors automatically | |
CN109274948A (en) | Image color correction method, apparatus, storage medium and computer equipment | |
CN111986151A (en) | Skin color detection method and device | |
Chen et al. | Dental shade matching method based on hue, saturation, value color model with machine learning and fuzzy decision | |
US7936920B2 (en) | Method and apparatus for multiple data channel analysis using relative strength histograms | |
Kampel et al. | Color classification of archaeological fragments | |
CN115631350A (en) | Method and device for identifying colors of canned image | |
JP4392268B2 (en) | Surface inspection device | |
Berns et al. | Modifications of a sinarback 54 digital camera for spectral and high-accuracy colorimetric imaging: simulations and experiments | |
CN110726536B (en) | Color correction method for color digital reflection microscope | |
CN114397094A (en) | Light source color rendering evaluation method based on spectral reconstruction and color appearance model | |
Zhbanova | Design and investigation of a digital photocolorimeter | |
Beneducci et al. | Dental shade matching assisted by computer vision techniques | |
Paray | LED Selection for Spectral (Multispectral) Imaging | |
CN109819150B (en) | Multi-channel image acquisition device and method for acquiring multi-channel image | |
CN111277806B (en) | Image processing method and device | |
KR102462061B1 (en) | Calibration Method of Image Deviation between Devices Using Gray Reference Panel and Facial Skin Diagnosis Device with this Function | |
Zhang et al. | Memory color assisted illuminant estimation through pixel clustering |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20210203 Address after: 100192 room 106, 1st floor, 03 yongtaizhuang East Road, Haidian District, Beijing Applicant after: Beijing radico Photoelectric Technology Co.,Ltd. Address before: 100085 room 103, building B, yard 1, No.4, East Binhe Road, Qinghe, Haidian District, Beijing Applicant before: Beijing Ruitong Kerui Technology Co.,Ltd. |
|
TA01 | Transfer of patent application right |