CN117392732A - Skin color detection method, device, computer equipment and storage medium - Google Patents
Skin color detection method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117392732A CN117392732A CN202311686460.XA CN202311686460A CN117392732A CN 117392732 A CN117392732 A CN 117392732A CN 202311686460 A CN202311686460 A CN 202311686460A CN 117392732 A CN117392732 A CN 117392732A
- Authority
- CN
- China
- Prior art keywords
- pixel
- original
- color
- face
- original 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 34
- 239000011159 matrix material Substances 0.000 claims abstract description 192
- 239000003086 colorant Substances 0.000 claims abstract description 65
- 238000000034 method Methods 0.000 claims abstract description 24
- 238000005192 partition Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 14
- 210000003491 skin Anatomy 0.000 description 91
- 238000010586 diagram Methods 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 9
- 230000000875 corresponding effect Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- BPYKTIZUTYGOLE-IFADSCNNSA-N Bilirubin Chemical compound N1C(=O)C(C)=C(C=C)\C1=C\C1=C(C)C(CCC(O)=O)=C(CC2=C(C(C)=C(\C=C/3C(=C(C=C)C(=O)N\3)C)N2)CCC(O)=O)N1 BPYKTIZUTYGOLE-IFADSCNNSA-N 0.000 description 2
- XUMBMVFBXHLACL-UHFFFAOYSA-N Melanin Chemical compound O=C1C(=O)C(C2=CNC3=C(C(C(=O)C4=C32)=O)C)=C2C4=CNC2=C1C XUMBMVFBXHLACL-UHFFFAOYSA-N 0.000 description 2
- 210000001061 forehead Anatomy 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 241001156002 Anthonomus pomorum Species 0.000 description 1
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 210000002615 epidermis Anatomy 0.000 description 1
- 238000005755 formation reaction Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000019612 pigmentation Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- -1 protoheme Chemical compound 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 208000017520 skin disease Diseases 0.000 description 1
- 230000005808 skin problem Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/162—Detection; Localisation; Normalisation using pixel segmentation or colour matching
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a skin tone detection method, a skin tone detection device, a computer device and a storage medium. The method comprises the following steps: acquiring an original format color matrix obtained by shooting a human face; respectively determining at least one original pixel group in each original pixel matrix, wherein the original pixel groups comprise at least one original pixel of each basic color, and any original pixel in the original pixel groups is adjacent to at least one other original pixel in the original pixel groups; determining pixel values of the same face pixel in different color channels under an RGB color mode based on pixel values of at least one original pixel of each basic color in each original pixel group, wherein the different color channels respectively represent different basic colors; and determining the skin color of the face according to the pixel values of the face pixels in different color channels in the RGB color mode. The method can improve the accuracy of the detected skin color.
Description
Technical Field
The present application relates to the field of skin detection technologies, and in particular, to a skin color detection method, apparatus, computer device, and storage medium.
Background
With the development of computer technology, skin color detection technology has emerged. Skin color is the skin color reflected by pigmentation of the skin epidermis of human skin, such as melanin, protoheme, and bilirubin. Skin color detection technology can be applied to various fields, such as skin care, face recognition, skin problem judgment, skin disease diagnosis and the like, and skin color detection is used as a pre-processing work applied in the fields, so that the accuracy of skin color detection has a great influence on subsequent processing. In the prior art, a face is usually shot to obtain a face image, and the skin color of the face is detected according to the face image.
However, when detecting the skin color of a face from a face image, there is a problem in that the accuracy of the skin color is low.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, apparatus, computer device, and computer-readable storage medium that can improve skin tone accuracy.
In a first aspect, the present application provides a skin tone detection method, including:
acquiring an original format color matrix obtained by shooting a human face, wherein the original format color matrix comprises a plurality of original pixel matrixes, each original pixel matrix comprises original pixels for representing each basic color in a plurality of basic colors, and each original pixel represents one basic color;
Respectively determining at least one original pixel group in each original pixel matrix, wherein the original pixel groups comprise at least one original pixel of each basic color, and any original pixel in the original pixel groups is adjacent to at least one other original pixel in the original pixel groups;
determining pixel values of the same face pixel in different color channels under an RGB color mode based on pixel values of at least one original pixel of each basic color in each original pixel group, wherein the different color channels respectively represent different basic colors;
and determining the skin color of the face according to the pixel values of the pixels of each face in different color channels in the RGB color mode.
In a second aspect, the present application further provides a skin color detection apparatus, including:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring an original format color matrix obtained by shooting a human face, the original format color matrix comprises a plurality of original pixel matrixes, each original pixel matrix comprises original pixels for representing each basic color in a plurality of basic colors, and each original pixel represents one basic color;
a pixel management module, configured to determine at least one original pixel group in each original pixel matrix, where the original pixel group includes at least one original pixel of each basic color, and any one of the original pixel groups is adjacent to at least another original pixel in the original pixel group; determining pixel values of the same face pixel in different color channels under an RGB color mode based on pixel values of at least one original pixel of each basic color in each original pixel group, wherein the different color channels respectively represent different basic colors;
And the skin color determining module is used for determining the skin color of the face according to the pixel values of the pixels of each face in different color channels in the RGB color mode.
In a third aspect, the present application also provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring an original format color matrix obtained by shooting a human face, wherein the original format color matrix comprises a plurality of original pixel matrixes, each original pixel matrix comprises original pixels for representing each basic color in a plurality of basic colors, and each original pixel represents one basic color;
respectively determining at least one original pixel group in each original pixel matrix, wherein the original pixel groups comprise at least one original pixel of each basic color, and any original pixel in the original pixel groups is adjacent to at least one other original pixel in the original pixel groups;
determining pixel values of the same face pixel in different color channels under an RGB color mode based on pixel values of at least one original pixel of each basic color in each original pixel group, wherein the different color channels respectively represent different basic colors;
And determining the skin color of the face according to the pixel values of the pixels of each face in different color channels in the RGB color mode.
In a fourth aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring an original format color matrix obtained by shooting a human face, wherein the original format color matrix comprises a plurality of original pixel matrixes, each original pixel matrix comprises original pixels for representing each basic color in a plurality of basic colors, and each original pixel represents one basic color;
respectively determining at least one original pixel group in each original pixel matrix, wherein the original pixel groups comprise at least one original pixel of each basic color, and any original pixel in the original pixel groups is adjacent to at least one other original pixel in the original pixel groups;
determining pixel values of the same face pixel in different color channels under an RGB color mode based on pixel values of at least one original pixel of each basic color in each original pixel group, wherein the different color channels respectively represent different basic colors;
and determining the skin color of the face according to the pixel values of the pixels of each face in different color channels in the RGB color mode.
Compared with the traditional technology adopting a color reconstruction face image to determine the skin color, the skin color detection method, device, computer equipment and storage medium have the advantages that the pixel value of at least one original pixel of each basic color in each original pixel group is determined based on the pixel value of the same face pixel in different color channels in the RGB color mode, each pixel in each original pixel group is an original pixel of one basic color, color reconstruction is not needed, the problem of inaccurate color information caused by the color reconstruction is avoided, and moreover, any original pixel in each original pixel group is adjacent to at least one other original pixel in the original pixel group, namely, the original pixel used for determining the pixel value of each color channel of the face pixel is closer in position, so that the accuracy of the face pixel can be improved to a certain extent, and further, the skin color of the face can be accurately determined according to the pixel value of each face pixel in different color channels in the RGB color mode.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for a person having ordinary skill in the art.
FIG. 1 is a flow chart of a skin tone detection method in one embodiment;
FIG. 2 is a schematic diagram of a color arrangement of the original format color matrix in one embodiment;
FIG. 3 is a schematic diagram of another color arrangement of the original format color matrix in one embodiment;
FIG. 4 is a schematic diagram of a color arrangement of 2×2 original pixel groups according to one embodiment;
FIG. 5 is a schematic diagram of another color arrangement of a 2×2 original pixel set according to one embodiment;
FIG. 6 is a schematic diagram of another color arrangement of a 2×2 original pixel group according to one embodiment;
FIG. 7 is a flowchart illustrating a skin tone detection step according to an embodiment;
FIG. 8 is a block diagram of a skin tone detection apparatus in one embodiment;
fig. 9 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
In one embodiment, as shown in fig. 1, a skin color detection method is provided, and the method is applied to computer equipment for illustration, where the computer equipment may be a terminal, a server, a personal computer, a notebook computer, a smart phone, a tablet computer and a mask. It will be appreciated that the method may also be applied to a system comprising a terminal and a server and implemented by interaction of the terminal and the server. The mask may be a dedicated device for skin tone detection, and may be configured with a camera for capturing a person's face. In this embodiment, the method includes the steps of:
Step 102, obtaining an original format color matrix obtained by shooting a human face, wherein the original format color matrix comprises a plurality of original pixel matrixes, each original pixel matrix comprises original pixels for representing each basic color in a plurality of basic colors, and each original pixel represents one basic color.
The original format color matrix is a color matrix under an unprocessed original format which is output after the face is shot by the camera. The original format may specifically be a RAW format. The original pixels are pixels in the original format color matrix. The plurality of basic colors includes red, green and blue.
The original format color matrix may be formed by a plurality of original pixel matrix arrangements. The original pixel matrix is an identity matrix which enables the basic colors represented by the original pixels in the original format color matrix to be repeatedly arranged according to color combinations. The color combination is a combination of the basic color formations represented by each original pixel in the original pixel matrix. Adjacent two original pixels in the original pixel matrix may respectively represent different basic colors. The adjacent two original pixels are two original pixels on the same side. The original pixel matrix may be a square matrix having the same number of rows and columns. The original pixel matrix may specifically be a matrix with a size of 4*4, i.e. the number of rows and columns is 4; a matrix of size 2 x 2, i.e. with a number of rows and columns of 2, is also possible. The original pixel matrix may be referred to as a Bayer array (Bayer array).
In one embodiment, the computer device may be configured with a camera, and when a face is detected, the camera is controlled to shoot the face, and a color matrix in a original format obtained by shooting the face by the camera is obtained.
In one embodiment, the computer device may not be configured with a camera and may be in communication connection with the camera-configured device, and the computer device may obtain the raw format color matrix obtained by photographing the face from the camera-configured device in which the communication connection is established. The device provided with the camera may be other computer devices provided with the camera or may be a digital camera.
Step 104, determining at least one original pixel group in each original pixel matrix respectively, wherein the original pixel groups comprise at least one original pixel of each basic color, and any original pixel in the original pixel groups is adjacent to at least one other original pixel in the original pixel groups.
In one embodiment, the computer device may obtain a preconfigured number of pixels for each of the original pixel groups, determine at least one of the original pixel groups in each of the original pixel matrices, respectively, such that each of the original pixel groups includes at least one original pixel for each of the primary colors, each of the original pixel groups includes the same number of original pixels as the preconfigured number of pixels, and any one of the original pixels in each of the original pixel groups is adjacent to at least another one of the original pixels in the original pixel group.
Wherein the number of the preconfigured pixels is not less than the number of kinds of the plurality of basic colors and is not greater than the number of the original pixels in the original pixel matrix. The preset number may be the same as or less than the number of pixels of the original pixel matrix, which may be a multiple of the preset number. In the case where the number of kinds of the plurality of basic colors is 3, when the original pixel matrix size is 2×2, that is, the number of original pixels of the original pixel matrix is 4, the preconfigured number of pixels may be 3 or 4. In the case where the number of kinds of the plurality of basic colors is 3, when the original pixel matrix size is 4*4, i.e., the number of original pixels of the original pixel matrix is 16, the preconfigured number of pixels may be 3, 4, 8, 12, or 16.
Step 106, determining pixel values of the same face pixel in different color channels in the RGB color mode based on pixel values of at least one original pixel of each basic color in each original pixel group, wherein the different color channels respectively represent different basic colors.
Wherein the pixel value of the original pixel is the luminance value of the original pixel in the basic color. The pixel in the RGB color mode has pixel values of each of an R (Red) channel, a G (Green) channel, and a B (Blue) channel.
In one embodiment, for each original pixel group, from the pixel values of at least one original pixel of a partial type basic color in the original pixel group, determining a pixel value of one original pixel of the partial type basic color, determining an average value of pixel values of original pixels of the residual type basic color in the original pixel group, and determining the pixel value of one original pixel of the partial type basic color and the average value of pixel values of original pixels of the residual type basic color as pixel values of the same face pixel in different color channels in the RGB color mode.
Wherein the remaining kinds of basic colors are basic colors other than the partial kinds of basic colors among the plurality of basic colors. Specifically, part of the basic colors can be one of red, blue and green, and the rest basic colors can be the other two of red, blue and green; the partial basic colors can be two of red, blue and green, and the residual basic colors can be the other one of red, blue and green. The average value may be an arithmetic average value or a weighted average value, and the closer to the center of the original format color matrix, the more weight may be given to the original pixels.
In one embodiment, the plurality of primary colors includes red, green, and blue, and the set of primary pixels includes one primary pixel of red, two primary pixels of green, and one primary pixel of blue. The computer device may count the number of pixel values in each of a plurality of pixel value segments of the original format color matrix green based on the original pixels of the original format color matrix green, determine, for each pixel value segment, a ratio between the number of pixel values in the pixel value segment for which it is intended and the number of original pixels of the original format color matrix green, and determine the ratio as a weight of the pixel value segment for which it is intended; for each original pixel group, determining one original pixel of red and one original pixel of blue, acquiring the pixel value of one original pixel of red and the pixel value of one original pixel of blue, determining the pixel value section to which the pixel values of the two original pixels of green belong, and determining the weighted average pixel value of green according to the pixel values of the two original pixels of green and the weights of the pixel value sections to which the pixel values of the two original pixels of green belong; and determining the pixel value of one original pixel of red, the pixel value of one original pixel of blue and the weighted average pixel value of green as the pixel values of the same face pixel in different color channels in the RGB color mode.
The pixel value section is a section obtained by dividing a pixel value range of an original pixel of green in an original format color matrix according to a segmentation size. The pixel value range is a value range formed by the minimum pixel value of the green original pixel and the maximum pixel value of the green original pixel. The segment size is the size of the segment divided into pixel values. Specifically, the pixel value of the green original pixel may be from 0 to 255, and the pixel value range of the green original pixel may be any range from 0 to 255, and the segment size may be 1, 10, 20, or others.
Step 108, according to the pixel values of the face pixels in different color channels in the RGB color mode, determining the skin color of the face.
The face pixels are pixels used for determining face complexion and have pixel values of different color channels in RGB color mode. The skin tone may be black, brown, yellow, and white, or may be a further skin tone obtained by further grading on the basis of the basic skin tone, for example, brown may include brown, tan, and yellow may include yellow-black, yellow-white, and yellow-white.
In one embodiment, the computer device may convert the pixel values of each face pixel in the RGB color mode in different color channels into the pixel values of each face pixel in the LAB color mode in different channels, and determine the skin color of the face according to the pixel values of each face pixel in the LAB color mode in different channels. The LAB color modes include an L (light) channel, an A (Green-Red Axis, red-Green) channel, and a B (Blue-Yellow Axis, yellow Lan Sedu) channel, among others.
In one embodiment, the computer device may determine representative pixel values of different channels in the LAB color mode according to pixel values of different channels of each face pixel in the LAB color mode, and determine skin color of the face according to the representative pixel values of different channels in the LAB color mode. The representative pixel value of each channel in the LAB color mode is an average value, a mode, a median or other of the pixel values of the face pixels in the corresponding channels in the LAB color mode.
In one embodiment, the computer device may determine a skin color individual type angle (Individule Type Angle, ita°) according to representative pixel values of the L channel and the B channel in the LAB color mode, determine a preset skin color individual type angle range in which the skin color individual type angle is located, and determine a preset skin color corresponding to the preset skin color individual preset type angle range as a skin color of the face. The preset skin color individual preset type angle range is a preset skin color individual preset type angle range, for example, 55 to 90 can be achieved, and the corresponding preset skin color can be white. The representative pixel values of the L channel and the B channel can be subjected to linear operation to obtain a linear operation value, the linear operation value is subjected to arc tangent operation to obtain an arc tangent operation value, and the ratio of 180 to the circumference ratio is subjected to multiplication operation with the arc tangent operation value to obtain the individual skin color type angle. The linear operation is performed on the representative pixel values of the L channel and the B channel, which means that the ratio of the difference value between the representative pixel value of the L channel and 50 to the representative pixel value of the B channel is calculated.
In the skin color detection method, compared with the traditional technology adopting a mode of determining skin colors by adopting a color reconstructed face image, because the pixel value of the same face pixel in different color channels in the RGB color mode is determined based on the pixel value of at least one original pixel in each basic color in each original pixel group, each pixel in each original pixel group is an original pixel of one basic color, the color reconstruction is not needed, the problem of inaccurate color information caused by the color reconstruction is avoided, and moreover, any original pixel in each original pixel group is adjacent to at least another original pixel in the original pixel group, namely, the original pixel used for determining the pixel value of each color channel of the face pixel is closer in position, so that the accuracy of the face pixel can be improved to a certain extent, and further, the skin color of the face can be determined more accurately according to the pixel value of each face pixel in different color channels in the RGB color mode.
In one embodiment, step 106 includes: for each original pixel group, determining a pixel value of one original pixel for each basic color from pixel values of at least one original pixel for each basic color in the original pixel group; and respectively determining the pixel value of an original pixel of each basic color as the pixel values of the same face pixel in different color channels in the RGB color mode.
Wherein, each basic color in the original pixel group is an original pixel, which can be any one of at least one original pixel of each basic color in the original pixel group.
In this embodiment, the pixel value of an original pixel of each basic color in the original pixel group is directly determined as the pixel value of the same face pixel in different color channels in the RGB color mode, and although the number of the finally generated pixels is smaller than that of the pixels generated in the color reconstruction and is not used for representing as an image, in the process of processing the original pixels in the original format color matrix obtained by shooting the face, the determined face pixels can determine the skin color, and the color information represented by the pixel values of the different color channels is more accurate, so that the accuracy of the detected skin color can be improved.
In one embodiment, the plurality of primary colors includes red, green, and blue, and the set of primary pixels includes at least one primary pixel of red, at least one primary pixel of green, and at least one primary pixel of blue. The step of determining, for each of the original pixel groups, a pixel value of one original pixel for each of the basic colors from among pixel values of at least one original pixel for each of the basic colors in the original pixel group includes: the computer device may determine, for each of the groups of original pixels, one original pixel of red, one original pixel of green, and one original pixel of blue from at least one original pixel of red, at least one original pixel of green, and at least one original pixel of blue; the pixel value of one original pixel of red, the pixel value of one original pixel of green, and the pixel value of one original pixel of blue are acquired.
In one embodiment, the plurality of primary colors includes red, green, and blue, and the set of primary pixels includes one primary pixel of red, one primary pixel of green, and one primary pixel of blue. The step of determining, for each of the original pixel groups, a pixel value of one original pixel for each of the basic colors from among pixel values of at least one original pixel for each of the basic colors in the original pixel group includes: the computer device may obtain, for each of the original pixel groups, a pixel value of one original pixel of red, a pixel value of one original pixel of green, and a pixel value of one original pixel of blue.
In one embodiment, the plurality of primary colors includes red, green, and blue, and the set of primary pixels includes one primary pixel of red, two primary pixels of green, and one primary pixel of blue; for each original pixel group, determining the pixel value of one original pixel per base color from the pixel values of at least one original pixel per base color in the original pixel group comprises: for each original pixel group, determining one original pixel of red, one original pixel of green and one original pixel of blue from one original pixel of red, two original pixels of green and one original pixel of blue; the pixel value of one original pixel of red, the pixel value of one original pixel of green, and the pixel value of one original pixel of blue are acquired.
The green original pixel may be any one of two green original pixels, or one of the two green original pixels near the center of the original format color matrix, or one of the two green original pixels adjacent to one of the red original pixel and one of the blue original pixel.
In this embodiment, since each pixel position in the color matrix of the original format only represents one basic color, when the conventional technology performs color reconstruction, two other basic colors need to be reconstructed for each pixel position, so that two thirds of color information in the face image subjected to color reconstruction is subjected to reconstruction processing, in the conventional technology, the problem of inaccuracy exists in determining the face skin color according to the face image subjected to color reconstruction, while each original pixel group includes one original pixel of red, two original pixels of green and one original pixel of blue, and when the pixel value of the same face pixel in different color channels in the RGB color mode is determined, the respective pixel values of one original pixel of red, one original pixel of blue and one original pixel of green in the original pixel group are directly adopted, and the pixel value change of the original pixel does not exist, so that the face skin color determined by combining the subsequent steps is more accurate.
In one embodiment, when the original pixels in the original pixel group are arranged in a row or a column, one original pixel of green is adjacent to one original pixel of red and one original pixel of blue, respectively.
In this embodiment, when the original pixels in the original pixel group are arranged in a row or a column, one original pixel of green determined from the original pixel group is adjacent to one original pixel of red and one original pixel of blue respectively, so that the face pixels determined in the subsequent step are more accurate, and the accuracy of the determined face complexion is further improved.
In one embodiment, when the original pixels in the original pixel group are arranged in a row or a column, the original pixels in the original pixel group may be arranged adjacently in sequence of red (R), green (G), blue (B), green, or adjacently in sequence of green, red, green, blue, or adjacently in sequence of blue, green, red, green, or adjacently in sequence of green, blue, green, red.
In one embodiment, as shown in a color arrangement schematic diagram of the original format color matrix of fig. 2, in the original format color matrix, colors represented by the original pixels are repeatedly arranged according to color combinations in the original pixel matrix; the original pixel matrix is a 4*4 matrix, each row has 4 original pixels, each row in the original pixel matrix can be an original pixel group, the original pixel groups in the first row can be sequentially arranged according to red, green, blue and green, the original pixel groups in the second row can be sequentially arranged according to green, red, green and blue, the original pixel groups in the third row can be sequentially arranged according to blue, green, red and green, and the original pixel groups in the fourth row can be sequentially arranged according to green, blue, green and red.
In one embodiment, as shown in another color arrangement schematic diagram of the original format color matrix in fig. 3, the original pixel matrix may be a 2×2 matrix, one original pixel matrix includes one original pixel group, and the original pixel group has the same size as the original pixel matrix, the original pixels in the original pixel group may be arranged in two rows and two columns, and the color arrangement in the original pixel group may be: the first row of the original pixel group may be sequentially arranged in green and red, and the second row may be sequentially arranged in blue and green.
In one embodiment, when the original pixel matrix is a 2×2 matrix, as shown in fig. 4, a color arrangement diagram of the 2×2 original pixel group, where the color arrangement in the original pixel group may further be: the first row of the original pixel group may be sequentially arranged in green and blue, and the second row may be sequentially arranged in red and green.
In one embodiment, when the original pixel matrix is a 2×2 matrix, as shown in another color arrangement diagram of the 2×2 original pixel set in fig. 5, the color arrangement in the original pixel set may further be: the first row of the original pixel group may be arranged in sequence according to blue and green, and the second row may be arranged in sequence according to green and red.
In one embodiment, when the original pixel matrix is a 2×2 matrix, as shown in fig. 6, the color arrangement of the 2×2 original pixel group may be: the first row of the original pixel group may be sequentially arranged in red and green, and the second row may be sequentially arranged in green and blue.
In one embodiment, the skin color detection method further includes the following steps: performing color reconstruction on the original format color matrix to obtain a reconstructed face matrix in an RGB color mode; the reconstructed face matrix consists of reconstructed pixels in an RGB color mode; according to the reconstructed face matrix, determining face partition pixel areas matched with different parts in the face in the reconstructed face matrix; step 108 includes: determining a face partition pixel area to which each face pixel belongs in a pixel position of each face pixel in an RGB color mode; and determining the skin color of the face according to the pixel values of the face pixels in different color channels in the RGB color mode and the weight pre-configured for the face partition pixel area to which the pixel positions are respectively located.
Wherein color reconstruction is the process of reconstructing the base color not characterized by each pixel location in the original format color matrix. In some scenarios, color reconstruction may also be referred to as demosaicing or demosaicing. The reconstructed face matrix is an image matrix representing the face generated through color reconstruction. The size of the reconstructed face matrix is the same as the original format color matrix.
The different parts of the human face can be cheek, mouth, forehead, nose and eyes. The face partition pixel region is a pixel region of a part representing a face in the reconstructed face matrix. For example, the face-partitioned pixel area may include a cheek pixel area, a mouth pixel area, a forehead pixel area, a nose pixel area, and an eye pixel area. The pre-configured weights of the different face partition pixel areas can be positively correlated with the occupied area of the face partition pixel areas in the reconstructed face matrix, namely the larger the occupied area of the face partition pixel areas in the reconstructed face matrix is, the larger the weight is.
Each face pixel in the RGB color mode may form a face pixel matrix for determining skin color, and the size of the face pixel matrix may be the same as the size of the original format color matrix. The face pixel matrix comprises face pixels and null pixels, the pixel positions of the face pixels in the face pixel matrix can be the same as the pixel positions of any one of the original pixels of each basic color used for determining the face pixels in the original format color matrix, and because the face pixel matrix is the same as the reconstructed face pixel matrix, the reconstructed pixel positions which are the same as the pixel positions of the face pixels can be determined in the reconstructed face pixel matrix, so that the face partition pixel areas which the pixel positions of the face pixels belong to can be determined.
In this embodiment, color reconstruction is performed on the original format color matrix, so that a reconstructed face matrix representing a face can be obtained, compared with the original format color matrix, structural information of the face is restored by the reconstructed face matrix, different parts in the face are convenient to identify, so that face subarea pixel areas matched with different parts in the face can be determined, weights are distributed to the different face subarea pixel areas, further, according to pixel values of each face pixel in different color channels in an RGB color mode and weights preconfigured for the face subarea pixel areas to which the pixel positions belong, skin colors of the face are determined, the influence of the pixel values of the face pixels of key areas on the skin colors of the face is greater, the pixel values of the face pixels are not subjected to color reconstruction, and the skin colors of the face can be more accurately determined.
In one embodiment, the computer device may convert pixel values of each face pixel in the RGB color mode in different color channels into pixel values of each face pixel in the LAB color mode in different channels, and for each channel in the LAB color mode, calculate a weighted average value according to the pixel values of each face pixel in the LAB color mode in the corresponding channel and weights preconfigured in the pixel areas of the face partition to which the pixel positions of each face pixel belong, obtain representative pixel values of the corresponding channel in the LAB color mode, obtain representative pixel values of the different channels in the LAB color mode, and determine skin color of the face.
In one embodiment, the computer device may determine, for each face pixel in the LAB color mode, a skin tone individual type angle corresponding to the face pixel in the LAB color mode according to pixel values of the face pixel in the L channel and the B channel, obtain a unit skin tone individual type angle of the face pixel, determine, according to the respective unit skin tone individual type angle of each face pixel and a weight preconfigured in a face partition pixel region to which each face pixel belongs, a representative skin tone individual type angle, and determine a skin tone of the face according to the representative skin tone individual type angle.
In one embodiment, the step of performing color reconstruction on the original format color matrix to obtain a reconstructed face matrix in RGB color mode includes: for each pixel position in the original format color matrix, determining a reconstructed pixel of the pixel position in an RGB color mode according to the pixel value of the original pixel at the pixel position and the pixel value of the original pixel which is different from the basic color represented by the original pixel at the pixel position and in the neighborhood of the pixel position; and generating a reconstructed face matrix in the RGB color mode according to the reconstructed pixels in the RGB color mode at each pixel position.
Where the neighborhood is the pixel location around the pixel location targeted in the original format color matrix. The neighborhood may be a four neighborhood, an eight neighborhood. The four neighbors are four pixel locations that are co-lateral to the pixel location being addressed. An eight neighborhood is eight pixel locations that are co-sided or co-vertex with the pixel location being addressed.
In this embodiment, since the original pixel at each pixel position in the original format color matrix represents only one basic color, color reconstruction is performed through the pixel values of other basic colors in the neighborhood, so that the reconstructed pixel position can represent three basic colors, and a reconstructed face matrix in an RGB color mode is generated, so that the face structural features can be conveniently identified, and more accurate face skin color creation conditions are formed for the subsequent combination of face pixels which are not determined through color reconstruction.
In one embodiment, for each pixel position in the original format color matrix, determining other basic colors different from the basic colors represented by the original pixels at the pixel position, determining the represented pixel values of the other basic colors at the pixel position according to the pixel values of the original pixels of the other basic colors in the neighborhood at the pixel position, determining the pixel values of the original pixels at the pixel position and the represented pixel values of the other basic colors as the pixel values of the reconstructed pixels in the RGB color mode at the pixel position, and obtaining the reconstructed pixels. Wherein the other basic colors may include two basic colors. The representative pixel values of the other base colors may be an average of the respective pixel values of each of the other base colors within the neighborhood of pixel locations for which it is intended.
In one embodiment, the skin color detection method further includes the following steps: determining the definition of a reconstructed face matrix; when the definition does not reach the preset definition, acquiring an original format color matrix obtained by re-shooting the face, performing color reconstruction on the original format color matrix, obtaining a reconstructed face matrix in an RGB color mode until the definition reaches the preset definition, determining face partition pixel areas matched with different parts in the face in the reconstructed face matrix according to the reconstructed face matrix, and determining at least one original pixel group in each original pixel matrix respectively.
The definition is the definition degree of each detail shadow of the image matrix and the boundary thereof. The sharpness of the reconstructed face matrix may be determined by a Brenner gradient function (a function of summing squares of pixel gray differences of two adjacent pixels among all pixels of the matrix), an energy gradient function (Energy of Gradient, taking the sum of squares of gray values of adjacent pixels in the horizontal direction and the vertical direction in the matrix as a gradient value of each pixel point, and accumulating the gradient values of all pixels as a sharpness evaluation function value), or other evaluation functions. The preset definition is a preset function value under an evaluation function adopted in evaluating the definition.
In this embodiment, when the original format color matrix is obtained, the reconstructed face matrix of the original format color matrix is determined, and then the definition of the reconstructed face matrix is determined, when the definition does not reach the preset definition, it is explained that interference conditions such as jitter may exist when the face is shot, so that the shot and acquired information is inaccurate, the face is shot again to obtain the original format color matrix, so that the reconstructed face matrix with higher definition can be obtained after the subsequent color reconstruction, different parts of the face can be conveniently identified, and the original format color matrix with higher accuracy according to the re-acquired color information can be obtained, so that the finally obtained face skin color is more accurate.
In one embodiment, the computer device may determine the definition of the reconstructed face matrix, obtain the original format color matrix obtained by re-shooting the face when the definition does not reach the preset definition, perform the step of performing color reconstruction on the original format color matrix to obtain the reconstructed face matrix in the RGB color mode until the definition reaches the preset definition, perform the step of determining the face partition pixel areas in the reconstructed face matrix, which are matched with different parts in the face, according to the reconstructed face matrix, and perform steps 104 to 108.
In one embodiment, as shown in the flow chart of the skin tone detection step in fig. 7, the skin tone detection method specifically includes the following steps.
The computer equipment can acquire the original format color matrix obtained by shooting the face by the camera and store the original format color matrix. Wherein the raw format color matrix comprises a plurality of raw pixel matrices, each raw pixel matrix comprising raw pixels characterizing each of a plurality of base colors, and each raw pixel characterizing one of the base colors. The plurality of basic colors includes red, green and blue.
The computer equipment can reconstruct colors of the original format color matrix to obtain a reconstructed face matrix in an RGB color mode, specifically, for each pixel position in the original format color matrix, determining a reconstructed pixel in the RGB color mode for the pixel position according to the pixel value of the original pixel at the pixel position and the pixel value of the original pixel which is different from the basic color represented by the original pixel at the pixel position and is in the neighborhood of the pixel position; and generating a reconstructed face matrix in the RGB color mode according to the reconstructed pixels in the RGB color mode at each pixel position.
The computer equipment can determine the definition of the reconstructed face matrix, acquire the original format color matrix obtained by re-shooting the face when the definition does not reach the preset definition, delete the original format color matrix obtained by historical shooting, and store the original format color matrix obtained by re-shooting.
When the definition of the reconstructed face matrix determined according to the re-photographed original format color matrix reaches the preset definition, the computer equipment can determine the face partition pixel areas matched with different parts in the face in the reconstructed face matrix according to the reconstructed face matrix.
When the definition of the reconstructed face matrix determined according to the re-photographed original format color matrix reaches a preset definition, the computer device may determine at least one original pixel group in each original pixel matrix, respectively. Wherein each original pixel group includes one original pixel of red, two original pixels of green, and one original pixel of blue.
The computer device may determine, for each of the original pixel groups, one original pixel of red, one original pixel of green, and one original pixel of blue from among the one original pixel of red, the two original pixels of green, and the one original pixel of blue, and cause the one original pixel of green to be adjacent to the one original pixel of red and the one original pixel of blue, respectively, to acquire a pixel value of the one original pixel of red, a pixel value of the one original pixel of green, and a pixel value of the one original pixel of blue.
The computer device may determine pixel values of the same face pixel in different color channels in the RGB color mode based on pixel values of one original pixel of each basic color in each original pixel group, the different color channels respectively representing different basic colors.
The computer equipment can convert the pixel values of the face pixels in the RGB color mode in different color channels into the pixel values of the face pixels in the LAB color mode in different channels; for each face pixel in the LAB color mode, determining a skin color individual type angle corresponding to the face pixel in the LAB color mode according to the pixel values of the face pixel in the L channel and the B channel in the LAB color mode, obtaining a unit skin color individual type angle of the face pixel, determining a representative skin color individual type angle according to the respective unit skin color individual type angle of each face pixel and the preconfigured weight of the face partition pixel area to which each face pixel belongs, and determining the skin color of the face according to the representative skin color individual type angle.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a skin color detection device for realizing the skin color detection method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of one or more skin tone detection devices provided below may be referred to the limitation of the skin tone detection method hereinabove, and will not be repeated here.
In one embodiment, as shown in fig. 8, there is provided a skin tone detection apparatus 800 comprising: an acquisition module 810, a pixel management module 820, and a skin tone determination module 830, wherein:
the obtaining module 810 is configured to obtain an original format color matrix obtained by photographing a face, where the original format color matrix includes a plurality of original pixel matrices, each original pixel matrix includes original pixels that represent each of a plurality of basic colors, and each original pixel represents one of the basic colors.
A pixel management module 820, configured to determine at least one original pixel group in each original pixel matrix, where the original pixel group includes at least one original pixel of each basic color, and any one of the original pixel groups is adjacent to at least another original pixel in the original pixel group; and determining the pixel values of the same face pixel in different color channels under the RGB color mode based on the pixel value of at least one original pixel of each basic color in each original pixel group, wherein the different color channels respectively represent different basic colors.
The skin color determining module 830 is configured to determine the skin color of the face according to the pixel values of the pixels of the face in the different color channels in the RGB color mode.
In one embodiment, the pixel management module 820 is further configured to determine, for each original pixel group, a pixel value of one original pixel for each base color from the pixel values of at least one original pixel for each base color in the original pixel group; and respectively determining the pixel value of an original pixel of each basic color as the pixel values of the same face pixel in different color channels in the RGB color mode.
In one embodiment, the plurality of primary colors includes red, green, and blue, and the set of primary pixels includes one primary pixel of red, two primary pixels of green, and one primary pixel of blue; the pixel management module 820 is further configured to determine, for each of the original pixel groups, one original pixel of red, one original pixel of green, and one original pixel of blue from among one original pixel of red, two original pixels of green, and one original pixel of blue; the pixel value of one original pixel of red, the pixel value of one original pixel of green, and the pixel value of one original pixel of blue are acquired.
In one embodiment, when the original pixels in the original pixel group are arranged in a row or a column, one original pixel of green is adjacent to one original pixel of red and one original pixel of blue, respectively.
In one embodiment, the skin color detection apparatus 800 further includes a color reconstruction module, where the color reconstruction module is configured to perform color reconstruction on the original format color matrix to obtain a reconstructed face matrix in the RGB color mode; the reconstructed face matrix consists of reconstructed pixels in an RGB color mode; and determining a face partition pixel area matched with different parts in the face in the reconstructed face matrix according to the reconstructed face matrix. The skin color determining module 830 is further configured to determine a face partition pixel area to which a pixel position where each face pixel is located in the RGB color mode belongs; and determining the skin color of the face according to the pixel values of the face pixels in different color channels in the RGB color mode and the weight pre-configured for the face partition pixel area to which the pixel positions are respectively located.
In one embodiment, the color reconstruction module is further configured to determine, for each pixel location in the original format color matrix, a reconstructed pixel for which the pixel location is in RGB color mode based on a pixel value of the original pixel at the pixel location and a pixel value of an original pixel within the neighborhood of the pixel location that is different from the base color represented by the original pixel at the pixel location; and generating a reconstructed face matrix in the RGB color mode according to the reconstructed pixels in the RGB color mode at each pixel position.
In one embodiment, the skin color detection apparatus 800 is further configured to determine sharpness of the reconstructed face matrix; when the definition does not reach the preset definition, acquiring an original format color matrix obtained by re-shooting the face, performing color reconstruction on the original format color matrix, obtaining a reconstructed face matrix in an RGB color mode until the definition reaches the preset definition, determining face partition pixel areas matched with different parts in the face in the reconstructed face matrix according to the reconstructed face matrix, and determining at least one original pixel group in each original pixel matrix respectively.
The various modules in the skin tone detection apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure thereof may be as shown in fig. 9. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a skin tone detection method. The display unit of the computer device is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 9 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application applies, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use, and processing of the related data are required to meet the related regulations.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A method of skin tone detection, the method comprising:
acquiring an original format color matrix obtained by shooting a human face, wherein the original format color matrix comprises a plurality of original pixel matrixes, each original pixel matrix comprises original pixels for representing each basic color in a plurality of basic colors, and each original pixel represents one basic color;
Respectively determining at least one original pixel group in each original pixel matrix, wherein the original pixel groups comprise at least one original pixel of each basic color, and any original pixel in the original pixel groups is adjacent to at least one other original pixel in the original pixel groups;
determining pixel values of the same face pixel in different color channels under an RGB color mode based on pixel values of at least one original pixel of each basic color in each original pixel group, wherein the different color channels respectively represent different basic colors;
and determining the skin color of the face according to the pixel values of the pixels of each face in different color channels in the RGB color mode.
2. The method according to claim 1, wherein determining the pixel values of the same face pixel in the RGB color mode in different color channels based on the pixel values of at least one original pixel of each basic color in each original pixel group comprises:
for each original pixel group, determining a pixel value of one original pixel for each basic color from pixel values of at least one original pixel for each basic color in the original pixel group;
and respectively determining the pixel value of an original pixel of each basic color as the pixel values of the same face pixel in different color channels in the RGB color mode.
3. The method of claim 2, wherein the plurality of primary colors includes red, green, and blue, and the set of primary pixels includes one primary pixel of red, two primary pixels of green, and one primary pixel of blue; the determining, for each original pixel group, a pixel value of one original pixel for each basic color from pixel values of at least one original pixel for each basic color in the original pixel group includes:
for each original pixel group, determining one original pixel of red, one original pixel of green and one original pixel of blue from one original pixel of red, two original pixels of green and one original pixel of blue;
a pixel value of one original pixel of the red color, a pixel value of one original pixel of the green color, and a pixel value of one original pixel of the blue color are acquired.
4. A method according to claim 3, wherein when the original pixels in the original pixel group are arranged in a row or a column, one original pixel of the green color is adjacent to one original pixel of the red color and one original pixel of the blue color, respectively.
5. The method according to any one of claims 1 to 4, further comprising:
performing color reconstruction on the original format color matrix to obtain a reconstructed face matrix in an RGB color mode; the reconstructed face matrix consists of reconstructed pixels in an RGB color mode;
according to the reconstructed face matrix, determining face partition pixel areas matched with different parts in the face in the reconstructed face matrix;
the determining the skin color of the face according to the pixel values of each face pixel in different color channels in the RGB color mode comprises the following steps:
determining a face partition pixel area to which each face pixel belongs in a pixel position of each face pixel in an RGB color mode;
and determining the skin color of the face according to the pixel values of the face pixels in different color channels in the RGB color mode and the weight pre-configured for the face partition pixel area to which the pixel positions are respectively located.
6. The method of claim 5, wherein performing color reconstruction on the original format color matrix to obtain a reconstructed face matrix in RGB color mode, comprises:
for each pixel position in the original format color matrix, determining a reconstructed pixel in an RGB color mode at the pixel position according to the pixel value of the original pixel at the pixel position and the pixel value of the original pixel which is different from the basic color represented by the original pixel at the pixel position and is in the neighborhood of the pixel position;
And generating a reconstructed face matrix in the RGB color mode according to the reconstructed pixels in the RGB color mode at each pixel position.
7. The method of claim 5, wherein the method further comprises:
determining the definition of the reconstructed face matrix;
and when the definition does not reach the preset definition, acquiring an original format color matrix obtained by re-shooting the human face, executing the step of carrying out color reconstruction on the original format color matrix to obtain a reconstructed human face matrix in an RGB color mode until the definition reaches the preset definition, executing the step of determining human face subarea pixel areas matched with different parts in the human face in the reconstructed human face matrix according to the reconstructed human face matrix, and respectively determining at least one original pixel group in each original pixel matrix.
8. A skin tone detection apparatus, the apparatus comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring an original format color matrix obtained by shooting a human face, the original format color matrix comprises a plurality of original pixel matrixes, each original pixel matrix comprises original pixels for representing each basic color in a plurality of basic colors, and each original pixel represents one basic color;
A pixel management module, configured to determine at least one original pixel group in each original pixel matrix, where the original pixel group includes at least one original pixel of each basic color, and any one of the original pixel groups is adjacent to at least another original pixel in the original pixel group; determining pixel values of the same face pixel in different color channels under an RGB color mode based on pixel values of at least one original pixel of each basic color in each original pixel group, wherein the different color channels respectively represent different basic colors;
and the skin color determining module is used for determining the skin color of the face according to the pixel values of the pixels of each face in different color channels in the RGB color mode.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311686460.XA CN117392732B (en) | 2023-12-11 | 2023-12-11 | Skin color detection method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311686460.XA CN117392732B (en) | 2023-12-11 | 2023-12-11 | Skin color detection method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117392732A true CN117392732A (en) | 2024-01-12 |
| CN117392732B CN117392732B (en) | 2024-03-22 |
Family
ID=89466978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311686460.XA Active CN117392732B (en) | 2023-12-11 | 2023-12-11 | Skin color detection method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117392732B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105516585A (en) * | 2015-11-30 | 2016-04-20 | 努比亚技术有限公司 | Apparatus and method for automatically regulating skin colors |
| CN105678813A (en) * | 2015-11-26 | 2016-06-15 | 乐视致新电子科技（天津）有限公司 | Skin color detection method and device |
| US20190130169A1 (en) * | 2017-10-31 | 2019-05-02 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Image processing method and device, readable storage medium and electronic device |
| CN111355936A (en) * | 2018-12-20 | 2020-06-30 | 杭州凝眸智能科技有限公司 | Method and system for acquiring and processing image data for artificial intelligence |
| CN115601244A (en) * | 2021-07-07 | 2023-01-13 | 荣耀终端有限公司（Cn） | Image processing method and device and electronic equipment |
-
2023
- 2023-12-11 CN CN202311686460.XA patent/CN117392732B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678813A (en) * | 2015-11-26 | 2016-06-15 | 乐视致新电子科技（天津）有限公司 | Skin color detection method and device |
| CN105516585A (en) * | 2015-11-30 | 2016-04-20 | 努比亚技术有限公司 | Apparatus and method for automatically regulating skin colors |
| US20190130169A1 (en) * | 2017-10-31 | 2019-05-02 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Image processing method and device, readable storage medium and electronic device |
| CN111355936A (en) * | 2018-12-20 | 2020-06-30 | 杭州凝眸智能科技有限公司 | Method and system for acquiring and processing image data for artificial intelligence |
| CN115601244A (en) * | 2021-07-07 | 2023-01-13 | 荣耀终端有限公司（Cn） | Image processing method and device and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 欧阳星辰: "一种基于拜耳插值算法的图像设计与实现", 《中国优秀硕士学位论文全文数据库信息科辑》, pages 135 - 4896 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117392732B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109829930B (en) | Face image processing method and device, computer equipment and readable storage medium | |
| WO2021109876A1 (en) | Image processing method, apparatus and device, and storage medium | |
| CN111445410A (en) | Texture enhancement method, device and equipment based on texture image and storage medium | |
| CN101675454A (en) | Adopt the edge mapping of panchromatic pixels | |
| CN112241933A (en) | Face image processing method and device, storage medium and electronic equipment | |
| CN112101294B (en) | Enhanced training method and device for image recognition model | |
| Losson et al. | Color texture analysis using CFA chromatic co-occurrence matrices | |
| CN109919029A (en) | Black eye kind identification method, device, computer equipment and storage medium | |
| CN113034358A (en) | Super-resolution image processing method and related device | |
| CN107480615A (en) | U.S. face processing method, device and mobile device | |
| CN109727196B (en) | Image interpolation processing method | |
| EP4131065A1 (en) | Skin color detection method and apparatus, terminal and storage medium | |
| CN117392732B (en) | Skin color detection method, device, computer equipment and storage medium | |
| Lin et al. | An investigation on worst‐case spectral reconstruction from RGB images via Radiance Mondrian World assumption | |
| CN113780519A (en) | Method and device for generating confrontation network training, computer equipment and storage medium | |
| Zhao et al. | Saliency map-aided generative adversarial network for raw to rgb mapping | |
| CN116843566A (en) | Tone mapping method, tone mapping device, display device and storage medium | |
| CN109658360B (en) | Image processing method and device, electronic equipment and computer storage medium | |
| CN114723723A (en) | Medical image processing method, computer device and storage medium | |
| CN110766079B (en) | Training data generation method and device for screen abnormal picture detection | |
| CN109410302B (en) | Texture mapping method, texture mapping device, computer equipment and storage medium | |
| CN115205613A (en) | Image identification method and device, electronic equipment and storage medium | |
| CN113744221A (en) | Shot object counting method and device, computer equipment and storage medium | |
| CN116797510A (en) | Image processing method, device, computer equipment and storage medium | |
| Liu et al. | CNN-Enhanced graph attention network for hyperspectral image super-resolution using non-local self-similarity |
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 |