Skin color quantification and management method and system, electronic equipment and storage medium

Abstract

The invention discloses a skin color quantification and management method and system, electronic equipment and a storage medium. The method comprises the following steps: acquiring a skin color picture of a target object; multi-dimensional skin color parameters are obtained based on skin color picture extraction, and target optimization parameters are determined according to reference skin color parameter quantification corresponding to the multi-dimensional skin color parameters; and determining a skin management suggestion of the target object according to the target optimization parameter mapping. The method can accurately realize skin color quantification and management, and can be widely applied to the technical field of data processing.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a skin color quantization and management method, system, electronic device, and storage medium. Background Art

[0002] Currently, the common practice of understanding consumers' desire for the ideal skin color is to conduct carefully designed scientific tests. Such tests can be through subjective consumer perception research, where panelist team members personally evaluate the skin color of selected models, or evaluate color pictures of different volunteers with different skin whiteness levels. It should be noted that when panelists look at models or photos for comparison and selection, even if the best one is found, it may not be the most rational, and may be affected by appearance preferences, subjective emotions, fatigue, etc.

[0003] Skin color can also be obtained by directly clinically measuring the skin color characteristics of the human body, or by using image analysis methods to measure skin color from color pictures, etc. The results are usually recorded through text descriptions, assigning numbers on a simple numerical scale, measuring by biological instruments (such as X-Rite colorimeter or Minolta Tristimulus Chromameter), or measuring by image analysis software (such as Photoshop or MATLAB). The limitation of the colorimeter is that it measures the chromaticity of "a specific site" with a probe. Even when multiple points are measured and averaged during the measurement, it is still difficult to fully present the skin color results of the entire face or the entire area. And the existing image analysis methods have limited dimensions and cannot reflect all the visual dimensions that affect the ideal skin color in detail and depth. Summary of the Invention

[0004] The present invention aims to solve at least to some extent the problems of related technical limitations. For this purpose, the present invention provides a skin color quantization and management method, system, electronic device, and storage medium, which can accurately perform skin color quantization and management.

[0005] On the one hand, an embodiment of the present invention provides a skin color quantization and management method, including the following steps:

[0006] Obtain a skin color picture of a target object;

[0007] Extract multi-dimensional skin color parameters based on the skin color picture, and then quantitatively determine target optimization parameters according to the reference skin color parameters corresponding to the multi-dimensional skin color parameters;

[0008] Map the target optimization parameters to determine skin management suggestions for the target object.

[0009] Optionally, before the step of extracting multi-dimensional skin color parameters based on the skin color picture, the method further includes the following steps:

[0010] Perform color correction on the skin tone picture based on a preset color system.

[0011] Optionally, performing color correction on the skin tone picture based on a preset color system includes the following steps:

[0012] Process the channel images of each color channel of the skin tone picture based on the CIE-LAB color system, and then draw the chip contour of the preset color chip in the skin tone picture according to a preset pixel brightness threshold;

[0013] Read the measurement values in the RGB color system according to each chip contour;

[0014] Obtain a calibration factor by comparing the measurement values with the standard values of the standard color card;

[0015] Perform color correction on the skin tone picture with the calibration factor.

[0016] Optionally, the skin tone picture is determined according to the skin picture of the target improvement area of the target object; when the skin tone picture is the skin picture of the facial area, the method further includes the following steps:

[0017] Perform positioning and cropping of facial features on the skin picture of the facial area, and retain the area of interest of the facial skin of the target object;

[0018] Use the area of interest of the facial skin as the skin tone picture.

[0019] Optionally, performing positioning and cropping of facial features on the skin picture of the facial area to retain the area of interest of the facial skin of the target object includes the following steps:

[0020] Perform color system conversion on the skin picture of the facial area, and then subtract the A* channel image and the B* channel image from the L* channel image to obtain an LBA image;

[0021] Perform picture pixel brightness histogram analysis on the LBA image, and then calculate a threshold according to the analysis result and draw the facial skin contour of the target object;

[0022] Locate the coordinate range of the facial skin contour in the skin picture of the facial area;

[0023] Locate the preliminary measurement area of each facial feature in the skin picture of the facial area based on the coordinate range;

[0024] Perform picture pixel brightness histogram analysis on the preliminary measurement area of each facial feature, and then calculate a threshold according to the analysis result and draw the facial feature contour of each facial feature;

[0025] All facial feature contours are cropped from the skin image of the facial area to obtain the region of interest of the facial skin of the target object.

[0026] Optionally, the multi-dimensional skin color parameters include surface flaw degree, lightness, lightness intensity difference, lightness area, pinkness, pinkness intensity difference, pinkness area, rosiness, and glossiness; extracting multi-dimensional skin color parameters from the skin color image includes the following steps:

[0027] The average intensity difference between the imperfect features and the normal skin area, the entropy of the gray-level co-occurrence matrix texture features, the average major length of the imperfect shapes greater than a preset ratio, the average pixel intensity of the imperfect shapes, the circularity of the imperfect shapes, and the average area percentage of the imperfect shapes are extracted from the skin color image, and then the surface flaw degree is calculated;

[0028] Among them, the expression of the surface flaw degree is:

[0029] In the formula, SVI represents the surface flaw degree; dINT represents the average intensity difference between the imperfect features and the normal skin area; S represents the entropy of the gray-level co-occurrence matrix texture features; L represents the average major length of the imperfect shapes greater than a preset ratio; I represents the average pixel intensity of the imperfect shapes; C represents the circularity of the imperfect shapes; pctA represents the average area percentage of the imperfect shapes;

[0030] The mode value of the skin color distribution curve, the whiteness and redness of the CIE-LAB color system, and the oil spot index are statistically obtained according to the skin color image;

[0031] The lightness is determined according to the white pixels in the skin color image whose whiteness values are between the standard deviations of the preset multiple ranges of the mode value of the skin color distribution curve;

[0032] The lightness intensity difference is determined according to the difference between the intensity of the pixels corresponding to the lightness and the average brightness of the full-face pixels of the skin color image;

[0033] The lightness area is determined according to the proportion of the pixels corresponding to the lightness in the skin color image;

[0034] The pinkness is determined according to the red pixels in the skin color image whose redness values are between the standard deviations of the preset multiple ranges of the mode value of the skin color distribution curve;

[0035] The pinkness intensity difference is determined according to the difference between the intensity of the pixels corresponding to the pinkness and the average redness of the full-face pixels of the skin color image;

[0036] The pinkness area is determined according to the proportion of the pixels corresponding to the pinkness in the skin color image;

[0037] The rosiness is calculated based on the pinkness and the whiteness; among them, the expression of the rosiness is: rosiness = pinkness × whiteness X, X represents a constant parameter;

[0038] The glossiness is calculated based on the lightness and the oil stain index; wherein, the expression of the glossiness is: Glossiness = (Lightness / Oil stain index X ) Y , X and Y represent constant parameters.

[0039] Optionally, determining the target optimization parameter according to the quantization of the reference skin color parameters corresponding to the multi-dimensional skin color parameters includes the following steps:

[0040] Quantitatively analyzing the improvement percentage of each dimension of skin color parameters based on the reference skin color parameters corresponding to the multi-dimensional skin color parameters;

[0041] Sorting and screening based on the improvement percentage to obtain the target optimization parameter.

[0042] Optionally, quantitatively analyzing the improvement percentage of each dimension of skin color parameters based on the reference skin color parameters corresponding to the multi-dimensional skin color parameters includes the following steps:

[0043] Averaging the values of the same skin color parameter in all regions of the skin color picture to obtain the average value of the skin color parameter corresponding to each dimension of the skin color parameter;

[0044] Determining the absolute difference of the parameters according to each dimension of the skin color parameter and its corresponding reference skin color parameter;

[0045] Obtaining the improvement percentage of each dimension of the skin color parameter according to the ratio of the absolute difference of the parameter corresponding to each dimension of the skin color parameter to the average value of the skin color parameter.

[0046] Optionally, sorting and screening based on the improvement percentage to obtain the target optimization parameter includes the following steps:

[0047] Sorting all dimensions of skin color parameters based on the numerical size of the improvement percentage;

[0048] Taking the preset number of skin color parameters with the largest improvement percentage in the sorting result as the target optimization parameter.

[0049] Optionally, determining the skin management suggestion of the target object according to the mapping of the target optimization parameter includes the following steps:

[0050] Comparing the target optimization parameter with its corresponding skin color parameter threshold;

[0051] According to the comparison result of the target optimization parameter and the skin color parameter threshold, combining the skin color range corresponding to the target optimization parameter to match the skin management suggestion from the preset management suggestion database.

[0052] Optionally, the method further includes the following steps:

[0053] The multi-dimensional skin color parameters obtained by extracting from the expected skin color picture provided by the target object are used as the reference skin color parameters;

[0054] Or, the statistical result of the skin color quantization data within the target area range is used as the reference skin color parameters;

[0055] Or, the preset skin color parameter value is used as the reference skin color parameters.

[0056] On the other hand, an embodiment of the present invention provides a skin color quantization and management system, including:

[0057] The first module is used to obtain the skin color picture of the target object;

[0058] The second module is used to extract multi-dimensional skin color parameters based on the skin color picture, and then quantitatively determine the target optimization parameters according to the reference skin color parameters corresponding to the multi-dimensional skin color parameters;

[0059] The third module is used to map and determine the skin management suggestions of the target object according to the target optimization parameters.

[0060] Optionally, the system further includes:

[0061] The fourth module is used to perform color correction on the skin color picture based on a preset color system.

[0062] Optionally, the skin color picture is determined according to the skin picture of the target improvement area of the target object; the system further includes:

[0063] The fifth module is used to locate and crop the facial features of the skin picture in the facial area, and retain the facial skin region of interest of the target object;

[0064] The sixth module is used to use the facial skin region of interest as the skin color picture.

[0065] Optionally, the system further includes a seventh module, and the seventh module is used for:

[0066] The multi-dimensional skin color parameters obtained by extracting from the expected skin color picture provided by the target object are used as the reference skin color parameters;

[0067] Or, the statistical result of the skin color quantization data within the target area range is used as the reference skin color parameters;

[0068] Or, the preset skin color parameter value is used as the reference skin color parameters.

[0069] On the other hand, an embodiment of the present invention provides an electronic device, including: a processor and a memory; the memory is used to store a program; the processor executes the program to implement the above-mentioned skin color quantization and management method.

[0070] On the other hand, an embodiment of the present invention provides a computer storage medium storing a program executable by a processor, and the program executable by the processor, when executed by the processor, is used to implement the above-mentioned skin color quantization and management method.

[0071] In an embodiment of the present invention, a skin color picture of a target object is obtained; multi-dimensional skin color parameters are extracted based on the skin color picture, and then target optimization parameters are quantized and determined according to the reference skin color parameters corresponding to the multi-dimensional skin color parameters; skin management suggestions for the target object are mapped according to the target optimization parameters. The present invention extracts multi-dimensional skin color parameters based on the skin color picture. Such multi-dimensional analysis can more comprehensively and meticulously reflect the skin color condition of the target object, providing data support for the formulation of subsequent improvement measures. Then, by comparing the extracted skin color parameters with the reference skin color parameters, the target optimization parameters can be quantized and determined. This step enables the effect of skin color improvement to be quantitatively presented through the quantitative application of parameter numerical results, helping the target object to more intuitively understand the improvement space and direction of their own skin color to determine the target optimization parameters. This not only helps to formulate a more targeted skin color management plan, but also can achieve the optimal skin color improvement effect with limited resources, and can achieve personalized skin color management for each person's skin color situation. Finally, based on the selected target optimization parameters, skin management suggestions for the target object can be mapped. The present invention can accurately implement skin color quantization and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] The drawings are used to provide a further understanding of the technical solution of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solution of the present invention, and do not constitute a limitation to the technical solution of the present invention.

[0073] Figure 1 is a schematic diagram of an implementation environment for skin color quantization and management provided by an embodiment of the present invention;

[0074] Figure 2 is a schematic flowchart of a skin color quantization and management method provided by an embodiment of the present invention;

[0075] Figure 3 is a schematic diagram of an example of face edge detection and contour provided by an embodiment of the present invention;

[0076] Figure 4 is a schematic diagram of an example of detecting the right eye and eyebrow provided by an embodiment of the present invention;

[0077] Figure 5 is a schematic diagram of an example of detecting the left eye and eyebrow provided by an embodiment of the present invention;

[0078] Figure 6 is a schematic diagram of an example of detecting the lips provided by an embodiment of the present invention;

[0079] Figure 7 Schematic diagram of detected nostril examples provided by an embodiment of the present invention;

[0080] Figure 8 Schematic diagram of an example of a cropped full-face ROI provided by an embodiment of the present invention;

[0081] Figure 9 Schematic diagram of a specific implementation process of a skin color quantization and management method provided by an embodiment of the present invention;

[0082] Figure 10 Schematic diagram of an example of the ranking order of skin attributes provided by an embodiment of the present invention;

[0083] Figure 11 Schematic diagram of an example of the change in primary color values expressed in selfies of research participants before and after grooming provided by an embodiment of the present invention;

[0084] Figure 12 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Detailed implementation manner

[0085] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0086] It should be noted that although functional module division is performed in the system schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from the module division in the system or the order in the flowchart. The terms "first / S100", "second / S200", etc. in the description and claims and the above-mentioned drawings are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence.

[0087] Referring to "embodiment" herein means that a specific feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appears in various positions in the description and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0088] It is understandable that the skin color quantification and management method provided by the embodiments of the present invention can be applied to any computer device with data processing and computing capabilities, and this computer device can be various types of terminals or servers. When the computer device in the embodiment is a server, the server is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Optionally, the terminal is a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but it is not limited thereto.

[0089] For the convenience of understanding the technical solutions of the present invention, first, the technical feature proper nouns that may appear in the embodiments of the present invention are explained:

[0090] Ideal skin color: The visual effects related to skin color that meet the aesthetic needs of consumers, and there are comprehensive definitions in multiple dimensions later.

[0091] The expression of skin color parameters in the CIE-Lab color system: L*, a*, b*, ITA, etc. Please refer to the description in Table 1 below or the explanations in any professional literature and books.

[0092] As Figure 1 shown, it is a schematic diagram of an implementation environment provided by the embodiments of the present invention. Referring to Figure 1 , this implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be network-connected wirelessly or wiredly to complete data transmission and exchange.

[0093] The server 101 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0094] In addition, the server 101 can also be a node server in a blockchain network. Among them, the blockchain is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithms.

[0095] The terminal 102 can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal 102 and the server 101 can be directly or indirectly connected through wired or wireless communication means, and the embodiments of the present invention do not limit this here.

[0096] Exemplarily based on Figure 1 the implementation environment shown, an embodiment of the present invention provides a skin color quantization and management method. Taking the application of this skin color quantization and management method to the server 101 as an example for illustration, it can be understood that this skin color quantization and management method can also be applied to the terminal 102.

[0097] Referring to Figure 2 , Figure 2 is a flowchart of the skin color quantization and management method applied to the server provided by the embodiment of the present invention. The execution subject of this skin color quantization and management method can be any of the aforementioned computer devices (including the server or the terminal). Referring to Figure 2 ,the method includes the following steps:

[0098] S100. Obtain a skin color picture of the target object;

[0099] Among them, the skin color picture is determined according to the skin picture of the target improvement area of the target object;

[0100] Exemplarily, the skin color picture can be a front view, a side view, a partial area (such as the forehead, T-zone, cheeks, eye area, etc.) of the face or the skin picture of any body target improvement area. In some specific implementation manners, with the help of laboratory technicians, in the environment of a skin test laboratory, the main camera of a smart phone can be used to take the skin picture of the desired improvement area of the research participant under specified illumination (such as white light).

[0101] S200. Extract multi-dimensional skin color parameters based on the skin color picture, and then quantitatively determine the target optimization parameters according to the reference skin color parameters corresponding to the multi-dimensional skin color parameters;

[0102] It should be noted that in some embodiments, before the step of extracting multi-dimensional skin color parameters based on the skin color picture, the method may further include the following steps: performing color correction on the skin color picture based on a preset color system.

[0103] Specifically, the color correction can be implemented by a preset color correction algorithm.

[0104] Among them, in some embodiments, color correction of a skin color picture based on a preset color system may include the following steps: processing the skin color picture based on the CIE-LAB color system to obtain channel images of each color channel of the skin color picture, and then delineating the chip contour of a preset color chip in the skin color picture according to a preset pixel brightness threshold; reading the measurement values of the RGB color system according to each chip contour; obtaining a calibration factor by comparing the measurement values with the standard values of a standard color card; and performing color correction on the skin color picture through the calibration factor.

[0105] Exemplarily, in some specific embodiments, an image color correction algorithm may be used to perform color correction on an original selfie according to the known standard color values of embedded color chips. The specific embodiments may be as follows:

[0106] 1. Focus on color measurement of the picture in the lower half of the picture according to the picture size data.

[0107] 2. In the red (a*) channel of the CIE-LAB color system, use the picture pixel brightness histogram analysis method to calculate the threshold value showing the highest pixel brightness in the a* image to delineate the contour of the red color card.

[0108] 3. Then sequentially adjust the color channels, and use the picture pixel brightness histogram analysis method to calculate the threshold value showing the highest pixel brightness to delineate the contours of other color cards such as green, blue, brown, black, white, etc.; among them, at least six preset color chips are delineated in the embodiments of the present invention.

[0109] 4. Read the measurement values of the RGB color system of each color card through image color analysis.

[0110] 5. Compare the measurement values and standard values of the standard color card to obtain the correlation between the two and the calibration factor in the RGB color system.

[0111] 6. Use the calibration factor to correct the measurement values of the image color to obtain the color-corrected image.

[0112] It should be noted that the skin color picture is determined according to the skin picture of the target improvement area of the target object; in some embodiments, when the skin color picture is the skin picture of the facial area, the method may further include the following steps: performing positioning and cropping of facial features on the skin picture of the facial area, and retaining the facial skin region of interest of the target object; using the facial skin region of interest as the skin color picture.

[0113] Among them, in some embodiments, locating and cropping facial features in a skin image of a facial area to retain the facial skin region of interest of the target object may include the following steps: performing a color system conversion on the skin image of the facial area, and then subtracting the A* channel image and the B* channel image from the L* channel image to obtain an LBA image; performing a picture pixel brightness histogram analysis on the LBA image, and then calculating a threshold value based on the analysis result and outlining the facial skin contour of the target object; locating the coordinate range of the facial skin contour in the skin image of the facial area; locating a preliminary measurement area for each facial feature in the skin image of the facial area based on the coordinate range; performing a picture pixel brightness histogram analysis on the preliminary measurement area of each facial feature, and then calculating a threshold value based on the analysis result and outlining the facial feature contour of each facial feature; cropping all facial feature contours from the skin image of the facial area to obtain the facial skin region of interest of the target object. Figure 2 As shown, it should be noted that the image examples of faces in the present invention all use face images regenerated by AI as the face basis.

[0114] For example, in some specific embodiments, in order to measure the color characteristics of facial skin, the present invention crops the entire facial region of interest (ROI) from the original selfie. Through the functions of automatic facial feature detection and built-in manual verification steps, the pixels of the eyes, eyebrows, nostrils and lips can be identified, and the threshold of pixel light intensity is automatically established by calculation in a specific image color channel to exclude these features from the facial skin ROI. Specific embodiments can be:

[0115] 1. In the original selfie that has been color corrected, convert the image from the RGB color system to the CIE-LAB color system, and subtract the a* (also called A* channel, which is the channel from green to red) and b* (also called B channel, which is the channel from blue to yellow) images from the L* channel (the L* channel is the brightness channel, which contains information about black, gray, and white). Name this image LBA.

[0116] 2. Use the image pixel brightness histogram analysis method to calculate the threshold containing the maximum amount of skin pixels in the LBA image to outline the facial skin contour (such as Figure 3 ).

[0117] 3. Preliminary positioning of facial feature recognition: from Figure 3 The red facial contour area calculates the coordinate range, including the minimum (X1) and maximum (X2) values of the horizontal axis, and the minimum (Y1) and maximum (Y2) values of the vertical axis.

[0118] 4. Subtract the L* image from the b* channel image. Name this image BL. Establish the second quadrant centered at the coordinates (X1 + X2) / 2, Y1+(Y2 - Y1) / 3*2 in the full-face image as the preliminary measurement area for the right eye and right eyebrow (as shown in Figure 4 ), and at the same time establish the first quadrant centered at the coordinates (X1 + X2) / 2, Y1+(Y2 - Y1) / 3*2 in the full-face image as the preliminary measurement area for the left eye and left eyebrow (as shown in Figure 5 ). Using the method of analyzing the pixel brightness histogram of the picture, calculate the threshold value containing the largest amount of eye or hair color pixels in the BL right-eye and left-eye images and outline the eye or eyebrow contours to determine the precise positioning of the eyes and eyebrows (see Figure 4 and Figure 5 ).

[0119] 5. Subtract the b* image from the a* channel image. Name this image a - b. Establish the lower half of the full-face image with the longitudinal dividing line at the coordinate Y1+(Y2 - Y1) / 3*2 as the preliminary measurement area for the lips (as shown in Figure 6 ). Using the method of analyzing the pixel brightness histogram of the picture, calculate the threshold value containing the largest amount of lip color pixels in the a - b image and outline the lip contours to determine the precise positioning of the lips (as shown in Figure 6 ).

[0120] 6. Establish the image with the longitudinal boundary from the lower eyelid to the lower lip in the full-face image as the preliminary measurement area for the left and right nostrils (as shown in Figure 7 ). Using the method of analyzing the pixel brightness histogram of the picture, calculate the threshold value containing the largest amount of nostril color pixels in the L* image and outline the nostril contours to determine the precise positioning of the nostrils (as shown in Figure 7 ).

[0121] 7. After performing the complete steps, the region of interest of the facial skin can be cropped (as shown in Figure 8 ).

[0122] It should be noted that the multi-dimensional skin color parameters include surface flaw degree, lightness, lightness intensity difference, lightness area, light redness, light red intensity difference, light red area, rosiness and glossiness; in some embodiments, extracting multi-dimensional skin color parameters based on skin color pictures may include the following steps:

[0123] Extract the average intensity difference between the imperfect features and the normal skin area, the entropy of the gray-level co-occurrence matrix texture feature, the average major length of the imperfect shapes greater than a preset ratio, the average pixel intensity of the imperfect shapes, the circularity of the imperfect shapes, and the average area percentage of the imperfect shapes from the skin color picture, and then calculate the surface flaw degree;

[0124] Among them, the expression of the surface flaw degree is:

[0125] In the formula, SVI represents the surface flaw degree; dINT represents the average intensity difference between the imperfect feature and the normal skin area; S represents the entropy of the gray-level co-occurrence matrix texture feature; L represents the average major length of the imperfect shape greater than a preset ratio; I represents the average pixel intensity of the imperfect shape; C represents the circularity of the imperfect shape; pctA represents the average area percentage of the imperfect shape;

[0126] Based on the skin-tone picture statistics, the mode value of the skin-tone distribution curve, the whiteness and redness of the CIE-LAB color system, and the oil spot index are obtained;

[0127] Based on the white pixels in the skin-tone picture whose whiteness values are between the standard deviations of the preset multiple ranges of the mode value of the skin-tone distribution curve, the lightness is determined;

[0128] Based on the difference between the intensity of the pixels corresponding to the lightness and the average brightness of the full-face pixels of the skin-tone picture, the lightness intensity difference is determined;

[0129] Based on the proportion of the pixels corresponding to the lightness in the skin-tone picture, the lightness area is determined;

[0130] Based on the red pixels in the skin-tone picture whose redness values are between the standard deviations of the preset multiple ranges of the mode value of the skin-tone distribution curve, the light redness is determined;

[0131] Based on the difference between the intensity of the pixels corresponding to the light redness and the average redness of the full-face pixels of the skin-tone picture, the light red intensity difference is determined;

[0132] Based on the proportion of the pixels corresponding to the light redness in the skin-tone picture, the light red area is determined;

[0133] Based on the light redness and whiteness, the rosiness is calculated; among them, the expression of the rosiness is: rosiness = light redness × whiteness X , X represents a constant parameter;

[0134] Based on the lightness and the oil spot index, the glossiness is calculated; among them, the expression of the glossiness is: glossiness = (lightness / oil spot index X ) Y , X, Y represent constant parameters.

[0135] Exemplarily, in some specific embodiments, multiple skin-tone parameters can be measured from the above ROI to describe the color attributes of the facial skin before and after selfie retouching. The present invention has developed a proprietary algorithm to measure the skin-tone attributes that consumers can visually perceive. These attributes include, but are not limited to, the following parameters: surface flaw degree, lightness, lightness intensity difference, lightness area, light redness, light red intensity difference, light red area, rosiness, and glossiness. In some specific application scenarios, the complete version of the skin-tone parameters can refer to the detailed description in Table 1.

[0136] Table 1

[0137]

[0138]

[0139]

[0140] It should be noted that in some embodiments, the target optimization parameters can be determined by quantifying the reference skin color parameters corresponding to the multi-dimensional skin color parameters, and the following steps can be included: analyzing the improvement percentage of the skin color parameters in each dimension by quantifying the reference skin color parameters corresponding to the multi-dimensional skin color parameters; sorting and screening according to the improvement percentage to obtain the target optimization parameters.

[0141] Among them, in some embodiments, the improvement percentage of the skin color parameters in each dimension can be obtained by quantifying the reference skin color parameters corresponding to the multi-dimensional skin color parameters, and the following steps can be included: averaging the values of the same skin color parameter in all regions of the skin color picture to obtain the average value of the skin color parameter corresponding to each dimension; determining the absolute difference of the parameters according to each dimension skin color parameter and its corresponding reference skin color parameter; obtaining the improvement percentage of the skin color parameter in each dimension according to the ratio of the absolute difference of the parameter corresponding to each dimension skin color parameter to the average value of the skin color parameter.

[0142] Exemplarily, in some specific embodiments, the improvement percentage of each attribute of the ideal skin color can be calculated (%IMP X = to identify the core parameters that most effectively affect the skin color condition. In this equation, %IMP X is the improvement percentage, the subscript X represents any skin parameter, and ΔX is the absolute difference between the skin parameter values in the original image and the ideal skin color picture. is the average value of this skin parameter in the original image.

[0143] Among them, in some embodiments, the target optimization parameters can be obtained by sorting and screening according to the improvement percentage, and the following steps can be included: sorting the skin color parameters in all dimensions based on the numerical size of the improvement percentage; using the preset number of skin color parameters with the largest improvement percentage in the sorting result as the target optimization parameters.

[0144] Exemplarily, in some specific embodiments, the top 5 (or any top 3-10) skin parameters can be selected to determine the target optimization parameters. At the same time, the measurement results of each parameter can also be matched with the results of the expert clinical score to determine the target optimization parameters.

[0145] It should also be noted that in some embodiments, the method may further include the following steps: using the multi-dimensional skin color parameters extracted from the expected skin color picture provided according to the target object as the reference skin color parameters; or, using the statistical result of the skin color quantization data within the target area range as the reference skin color parameters; or, using the preset skin color parameter value as the reference skin color parameters.

[0146] Exemplarily, in some specific embodiments, the reference skin color parameters can be obtained through processes such as positioning and cropping of facial features and extraction of multi-dimensional skin color parameters from the retouched selfie obtained after beautifying (photo editing) the front full-face photo of the target object, that is, the reference skin color parameters can be obtained through the aforementioned skin color parameter quantization and extraction processes based on the photo corresponding to the expected skin color state of the target object. In addition, the reference skin color parameters can also be obtained by quantifying the data statistics of a large range of skin color quantization data, or directly obtained by quantifying based on the manually set parameter values. In the embodiments of the present invention, the expected skin color situation of the target object is specifically used as the quantization standard for the reference skin color parameters. In some alternative embodiments, the reference skin color parameters can also be determined according to the comparison photos selected by the user; specifically, the most important thing for the comparison photo is to meet the skin color expectation of the target object, and the photo can be a retouched one of oneself, or that of others, or even that of other parts of one's own body (such as the inner side of the upper arm and other areas not often exposed).

[0147] S300. Determine the skin management suggestions for the target object according to the target optimization parameter mapping.

[0148] It should be noted that in some embodiments, determining the skin management suggestions for the target object according to the target optimization parameter mapping may include the following steps: comparing the target optimization parameters with their corresponding skin color parameter thresholds; according to the comparison result of the target optimization parameters and the skin color parameter thresholds, and in combination with the skin color range corresponding to the target optimization parameters, matching the skin management suggestions from the preset management suggestion database.

[0149] Specifically, in some specific application scenarios, the skin management suggestions include but are not limited to the application of skin color improvement active ingredients, the application of cosmetics, and medical beauty solutions, etc.

[0150] Exemplarily, in some specific embodiments, based on the clinical scoring results, thresholds for each skin parameter can be established, and above this threshold, it is recommended to take intervention measures to specifically solve the facial skin color problems. Examples of the intervention include but are not limited to whitening, freckle removal, antioxidant, anti-inflammatory, skin rejuvenation, medical beauty, and color cosmetics, etc.

[0151] To explain the principle of the technical solution of the present invention in detail, the overall process of the present invention will be described below in combination with some specific embodiments. It is easy to understand that the following is an explanation of the technical principle of the present invention and should not be regarded as a limitation of the present invention.

[0152] First of all, it should be noted that when using existing consumer perception methods, there may be a possibility of inaccuracy due to the following reasons:

[0153] 1. Select panel members to evaluate the model's skin or color pictures and provide feedback:

[0154] 1.1. Panel members may have inconsistent understandings of the theme;

[0155] 1.2. The degree of participation in the survey completion;

[0156] 1.3. Mental fatigue that may occur after repeatedly performing the required tasks multiple times [13,14].

[0157] 2. Selection of models or color pictures:

[0158] 2.1. The models or pictures selected for the study may not be representative.

[0159] 2.2. Preparing high-quality models or color pictures requires a high cost.

[0160] 2.3. Many times, it may be impossible to identify the models or pictures that represent the ideal skin color required by consumers.

[0161] 3. Research design and data analysis:

[0162] 3.1. Consumer perception research requires careful design. Strict protocols need to be followed to obtain meaningful results. Statistical inference needs to be used to interpret the data, which may not usually be clear or straightforward.

[0163] 3.2. The results of consumers' perception of the ideal skin color are usually limited to the sample range selected for the study. It is usually relative rather than precise.

[0164] In view of this, the present invention proposes a novel consumer study that precisely quantifies the self-perceived color target of the ideal skin color through image analysis of multiple skin color parameters before and after consumers beautify their selfies. Specifically, the present invention allows the research subjects to independently modify their selfies using image editing software to express their own perceived ideal skin color. This method optimizes the intrinsic motivation and enthusiasm of each subject to achieve a nearly perfect goal. The advantages of this novel method are obvious, because the psychological principle of the drama framework shows that beauty-conscious consumers are less likely to be indifferent when preparing to present their images to the world.

[0165] In addition, the present invention has also developed some unique algorithms to objectively and comprehensively record and analyze the attributes of the ideal skin color self-perceived by consumers.

[0166] Such asFigure 9 As shown, the present invention relates to a combination of the following key steps to accurately measure the consumer's self-perceived ideal skin color for future development of skin color products and management plans. The specific implementation is as follows:

[0167] 1. With the help of laboratory technicians, in the environment of a skin test laboratory, use the main camera of a smartphone to take a full-face frontal photo of the research participant under specified lighting (white light).

[0168] 2. Display a specially selected set of standard color palettes in the scene and take photos together with the face of each self-portrait of the participant.

[0169] 3. Require each owner of the self-portrait to use a photo editing APP to enhance the color of the self-portrait to their satisfaction to achieve the ideal skin color in their mind.

[0170] 4. Two photos are generated in the above process, one is the original self-portrait and the other is the retouched self-portrait.

[0171] 5. Use an image color correction algorithm to correct the color of the original self-portrait according to the known standard color values of the embedded color chips. The specific implementation can be:

[0172] 5.1. Focus on the color measurement of the picture in the lower half of the picture according to the picture size data.

[0173] 5.2. In the red (a*) channel of the CIE-LAB color system, use the means of analyzing the picture pixel brightness histogram to calculate the threshold value showing the highest pixel brightness in the a* image to outline the red color card contour.

[0174] 5.3. Then adjust the color channels in turn, and use the means of analyzing the picture pixel brightness histogram to calculate the threshold value showing the highest pixel brightness to outline the contours of other color cards such as green, blue, brown, black, white, etc.

[0175] 5.4. Read the measured values of the RGB color system of each color card through image color analysis.

[0176] 5.5. Compare the measured values of the standard color card with the standard values to obtain the correlation between the two and the calibration factor in the RGB color system.

[0177] 5.6. Use the calibration factor to correct the measured values of the image color to obtain the color-corrected image.

[0178] 6. To measure the color characteristics of facial skin, the present invention crops the entire region of interest (ROI) of the face from the original selfie. By means of automatic facial feature detection and a function with built-in manual verification steps, the pixels of the eyes, eyebrows, nostrils, and lips can be identified, and the threshold of the pixel light intensity is automatically calculated in a specific image color channel to exclude these features from the facial skin ROI. The specific implementation can be as follows:

[0179] 6.1. In the color-corrected original selfie, convert the image from the RGB color system to the CIE-LAB color system, and subtract the a* (also known as the A* channel, which is the green-to-red channel) and b* (also known as the B channel, which is the blue-to-yellow channel) images from the L* channel image (the L* channel is the lightness channel, containing information about black, white, and gray). Name this image LBA.

[0180] 6.2. Using the method of analyzing the pixel brightness histogram of the picture, calculate the threshold value containing the largest amount of skin pixels in the LBA image to outline the facial skin contour (such as Figure 3 ).

[0181] 6.3. Preliminary positioning of facial feature recognition: Calculate the coordinate range from the Figure 3 red facial contour area, including the minimum (X1) and maximum (X2) values of the abscissa, and the minimum (Y1) and maximum (Y2) values of the ordinate.

[0182] 6.4. Subtract the L* image from the b* channel image. Name this image BL. Establish the second quadrant centered at the coordinates (X1 + X2) / 2, Y1+(Y2 - Y1) / 3*2 in the full-face image as the preliminary measurement area for the right eye and right eyebrow (such as Figure 4 ), and at the same time establish the first quadrant centered at the coordinates (X1 + X2) / 2, Y1+(Y2 - Y1) / 3*2 in the full-face image as the preliminary measurement area for the left eye and left eyebrow (such as Figure 5 ). Using the method of analyzing the pixel brightness histogram of the picture, calculate the threshold value containing the largest amount of eye or hair color pixels in the BL right-eye and left-eye images and outline the eye or eyebrow contour to determine the precise positioning of the eyes and eyebrows (see Figure 4 and Figure 5 ).

[0183] 6.5. Subtract the b* image from the a* channel image. Name this image a - b. Establish the lower half of the full-face image with the coordinate Y1+(Y2 - Y1) / 3*2 as the longitudinal dividing line as the preliminary measurement area for the lips (such as Figure 6 ). Using the method of analyzing the pixel brightness histogram of the picture, calculate the threshold value containing the largest amount of lip color pixels in the a - b image and outline the lip contour to determine the precise positioning of the lips (such as Figure 6 ).

[0184] 6.6. Establish the image with the lower eyelid to the lower lip as the longitudinal boundary in the full-face image as the preliminary measurement area for the left and right nostrils (as Figure 7 ). Using the method of analyzing the pixel brightness histogram of the picture, calculate the threshold value containing the maximum amount of nostril color pixels in the L* image and outline the nostril contour to determine the precise positioning of the nostrils (as Figure 7 ).

[0185] 6.7. After performing the complete steps, the region of interest of the facial skin can be cropped (as Figure 8 shown).

[0186] 7. Then apply the above ROI to the retouched self-portrait of the same participant to generate the same ROI as the original self-portrait. This ensures that the difference in skin color parameters measured between the original self-portrait and the retouched self-portrait represents the true difference in skin properties after photo editing.

[0187] 8. Measure multiple (28) skin color parameters from the above ROI to describe the color properties of the facial skin before and after selfie retouching. A proprietary algorithm was developed to measure the skin color properties that consumers can visually perceive. These properties include, but are not limited to, the following parameters. For the full version, please refer to the detailed description in Table 1 above.

[0188] 8.1. Severity index of shiny spots (SI-gShine);

[0189] 8.2. Lightness different from shiny spots;

[0190] 8.3. Severity index of macular spots (SI-Dark);

[0191] 8.4. Severity index of erythema (SI-Redness);

[0192] 8.5. Pinkness different from erythema;

[0193] 8.6. Surface imperfection degree, i.e., skin visual defect index (SVI);

[0194] 8.7. Skin redness index (IRG);

[0195] 8.8. Skin glossiness index (ISR).

[0196] 9. Analyze the ideal skin color perceived by consumers and the potential uses of such data in new product development and skin color management programs.

[0197] 9.1. Calculate the percentage improvement of each property of the ideal skin color to identify the core parameters that most effectively affect the skin color condition. In this equation, %IMPX is the improvement percentage, where the subscript X represents any skin parameter, and ΔX is the absolute difference between the skin parameter values in the original image and the ideal skin color picture. is the average value of the skin parameter in the original image.

[0198] 9.2. Select the top 5 (or any top 3 - 10) skin parameters and match the measurement results of each parameter with the results of the expert clinical scoring. As Figure 10 shown, the radar chart shows the ranking order of the skin attributes that significantly contribute to consumers achieving the ideal skin color. For example, the top five here are the individual skin type angle (whiteness), surface flaw degree, oil spot index, oil spot area, and yellowness.

[0199] 9.3. Based on the clinical scoring results, establish a threshold for each skin parameter. Above this threshold, it is recommended to take intervention measures to specifically address the facial skin color problem. Examples of interventions include but are not limited to whitening, freckle removal, antioxidant, anti - inflammation, skin rejuvenation, medical aesthetics, and makeup. The following is an example of a personalized skin color management solution in Table 2:

[0200] Table 2

[0201]

[0202] Based on the degree of difference in the improvement of skin attributes that significantly contribute to individual consumers achieving the ideal skin color, such as mild demand, moderate demand, severe demand (which can be further subdivided), and solutions that match each dimension, personalized combination solutions can be developed to meet the personalized needs of any individual. The solutions can include but are not limited to skincare (selection and dosage of active ingredients), medical aesthetics (different treatment methods and frequencies), and makeup modification.

[0203] As Figure 11 shown, it is a schematic diagram of the change in the original color values expressed in the self - portraits of the research participants before and after modification. Charts in column A: Histograms of the average color values of the test population before (blue) and after (orange) selfie modification. Color bar charts: Distribution; Curves: Normal distribution curves. Grey bar charts in column B: Histograms of the color attribute changes required to achieve the ideal skin color. It can be seen that after modification, statistically significant increases in L* and ITA° are detected, and b* decreases. The a* value shows a bimodal distribution, indicating that some participants reduced facial redness, while others chose to increase facial redness.

[0204] In summary, the maximum application scope of the present invention is to objectively and accurately quantify and analyze digital pictures that can reflect an individual's true skin color and digital pictures of the ideal skin color that the user is satisfied with using self-defined digital algorithms, and then compare the differences to obtain skin attributes that significantly contribute to the user achieving the ideal skin color, so as to match a personalized skin color management solution. The algorithm of the present invention can be a specific multi-dimensional digital skin color analysis algorithm or an AI model algorithm further trained based on the results of the analysis algorithm, and its results match specific clinical skin manifestations; the true skin color refers to the true digital skin color picture calibrated by the user with a standard color card; the ideal skin color can be the result of the user's independent skin color modification and optimization using digital retouching software tools, or the skin color result generated by AI that satisfies the user, or the statistical result obtained from a large amount of data of the user's population; the skin color solution includes skin care products for skin color improvement (such as whitening, soothing and reducing redness, antioxidant, anti-inflammatory, sunscreen, tanning, etc.), medical beauty products for skin color treatment (such as photon rejuvenation, picosecond freckle removal, etc.), and makeup products for skin color modification, etc.

[0205] The most specific achievement is that the present invention has constructed a multi-dimensional digital skin color evaluation system (a total of 28 parameter indicators, including multiple clinically first-defined parameter definitions). Based on the corresponding algorithm program, through multi-dimensional objective quantification and differential comparison of the digital facial pictures of consumers and the skin color optimization P-map results that meet the aesthetic needs of consumers, it is possible to accurately understand and describe consumers' pursuit of their ideal skin color. This is an innovation in scientific research methods - objectively quantifying subjective wishes and judgments and making differential comparisons with the true skin color, so as to obtain more accurate consumer insights. Further, based on the collection of a large amount of data, the standard range of the ideal skin color of different populations (age, gender, region, etc.) is obtained, and an AI ideal skin color prediction system is generated. With such result support, the algorithm can directly predict the result of the consumer's expected ideal skin color after analyzing the consumer's true digital facial picture, ask the consumer to select and confirm, and then develop unique skin color optimization products or recommend solutions for them to meet their personalized skin color management needs.

[0206] Compared with the prior art, the present invention has at least the following beneficial effects:

[0207] 1) It is possible to obtain an accurate, consumer self-perceived ideal skin color in the most direct participation way for each research participant, so as to improve her self-taken photo to a satisfactory degree. 2) The novel skin color parameters developed for the present invention have definite clinical significance and comprehensively and objectively describe skin characteristics. 3) The skin color detection and analysis method carried out by the present invention is for the entire area (if it is the face, that is, the whole face). Compared with the detection of local pictures or probes at points, it can more comprehensively, truly and accurately analyze and precisely evaluate the skin color information of the whole face.

[0208] On the other hand, an embodiment of the present invention provides a skin color quantization and management system, which may include:

[0209] A first module, configured to obtain a skin color picture of a target object;

[0210] A second module, configured to extract multi-dimensional skin color parameters based on the skin color picture, and then quantitatively determine target optimization parameters according to the reference skin color parameters corresponding to the multi-dimensional skin color parameters;

[0211] A third module, configured to map and determine skin management suggestions for the target object according to the target optimization parameters.

[0212] In some embodiments, the system may further include:

[0213] A fourth module, configured to perform color correction on the skin color picture based on a preset color system.

[0214] In some embodiments, the skin color picture is determined according to the skin picture of the target improvement area of the target object; the system may further include:

[0215] A fifth module, configured to locate and crop facial features of the skin picture of the facial area, and retain the region of interest of the facial skin of the target object;

[0216] A sixth module, configured to use the region of interest of the facial skin as the skin color picture.

[0217] In some embodiments, the system may further include a seventh module, and the seventh module is configured to:

[0218] Use the multi-dimensional skin color parameters extracted from the expected skin color picture provided by the target object as the reference skin color parameters;

[0219] Or, use the statistical result of the skin color quantization data in the target area range as the reference skin color parameters;

[0220] Or, use the preset skin color parameter value as the reference skin color parameters.

[0221] The content of the method embodiment of the present invention is applicable to the system embodiment of the present invention. The functions specifically implemented by the system embodiment of the present invention are the same as those of the above method embodiment, and the beneficial effects achieved are also the same as those of the above method.

[0222] On the other hand, an embodiment of the present invention further provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the above-mentioned skin color quantization and management method is implemented. The electronic device may be any intelligent terminal including a tablet computer, an in-vehicle computer, etc.

[0223] It can be understood that the content in the above method embodiments is applicable to the device embodiments of the present invention. The functions specifically implemented by the device embodiments of the present invention are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method embodiments.

[0224] As Figure 12 shown, Figure 12 FIG. schematically shows the hardware structure of an electronic device 1000 according to another embodiment. The electronic device 1000 includes:

[0225] A processor 1001, which can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided by the embodiments of the present invention;

[0226] A memory 1002, which can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory 1002 can store an operating system and other application programs. When implementing the technical solutions provided by the embodiments of the present specification through software or firmware, the relevant program codes are stored in the memory 1002 and are called by the processor 1001 to execute the network node population optimization method of the embodiments of the present invention;

[0227] An input / output interface 1003, which is used to implement information input and output;

[0228] A communication interface 1004, which is used to implement communication and interaction between the present device and other devices, and can implement communication through a wired method (such as USB, network cable, etc.) or through a wireless method (such as mobile network, WIFI, Bluetooth, etc.);

[0229] A bus 1005, which transmits information between various components of the device (such as the processor 1001, the memory 1002, the input / output interface 1003, and the communication interface 1004);

[0230] Among them, the processor 1001, the memory 1002, the input / output interface 1003, and the communication interface 1004 are communicatively connected to each other inside the device through the bus 1005.

[0231] The embodiments of the electronic device described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0232] The content of the method embodiments of the present invention is applicable to the embodiments of this electronic device. The functions specifically implemented by the embodiments of this electronic device are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method.

[0233] Another aspect of the embodiments of the present invention also provides a computer-readable storage medium. The storage medium stores a program, and the program is executed by a processor to implement the foregoing method.

[0234] It should be noted that the computer-readable medium shown in the embodiments of the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program can be used by or combined with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0235] The content of the method embodiments of the present invention is applicable to the embodiments of the computer-readable storage medium. The functions specifically implemented by the embodiments of the computer-readable storage medium are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method.

[0236] The embodiments of the present invention also disclose a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the foregoing method.

[0237] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code includes one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0238] It should be noted that although several modules of the devices for performing actions are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present invention, the features and functions of the two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0239] Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described here can be implemented by software, or can be implemented by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present invention can be embodied in the form of a software product, and the software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present invention.

[0240] In some alternative embodiments, the functions / operations recited in the block diagrams may not occur in the order presented in the operational illustrations. For example, depending on the functions / operations involved, two consecutive blocks shown may actually be executed substantially simultaneously or the blocks may sometimes be executed in the reverse order. Additionally, the embodiments presented and described in the flowcharts of the present invention are provided by way of example for the purpose of providing a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logical flows presented herein. Alternative embodiments are contemplated in which the order of various operations is altered and where sub-operations described as part of a larger operation are executed independently.

[0241] Furthermore, although the present invention has been described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the functions and / or features may be integrated in a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It should also be understood that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, given the attributes, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the modules will be understood within the ordinary skill of an engineer. Thus, those skilled in the art can implement the present invention as set forth in the claims without undue experimentation. It should also be understood that the particular concepts disclosed are illustrative only and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0242] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0243] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definitional sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution device, apparatus or equipment (such as a computer-based device, a device including a processor, or other devices that can fetch and execute instructions from the instruction execution device, apparatus or equipment), or used in combination with these instruction execution devices, apparatus or equipment. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution device, apparatus or equipment.

[0244] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which a program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.

[0245] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution device. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0246] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc., mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0247] Although embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the claims and their equivalents.

[0248] The above has specifically described the preferred embodiments of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art can also make various equivalent deformations or substitutions without violating the spirit of the present invention, and these equivalent deformations or substitutions are all included within the scope defined by the claims of the present invention.

Claims

1. A skin color quantization and management method, characterized in that, Including the following steps: Obtain a skin color picture of the target object; Extract multi-dimensional skin color parameters based on the skin color picture, and then quantify and determine the target optimization parameters according to the reference skin color parameters corresponding to the multi-dimensional skin color parameters; Map and determine the skin management suggestions for the target object according to the target optimization parameters.

2. The skin color quantization and management method according to claim 1, characterized in that, Before the step of extracting multi-dimensional skin color parameters based on the skin color picture, the method further includes the following steps: Perform color correction on the skin color picture based on a preset color system.

3. The skin color quantization and management method according to claim 2, characterized in that, The performing color correction on the skin color picture based on a preset color system includes the following steps: Process the skin color picture based on the CIE-LAB color system to obtain the channel images of each color channel of the skin color picture, and then draw the chip contour of the preset color chip in the skin color picture according to a preset pixel brightness threshold; Read the measurement values of the RGB color system according to each chip contour; Obtain a calibration factor by comparing the measurement values with the standard values of the standard color card; Perform color correction on the skin color picture through the calibration factor.

4. The skin color quantization and management method according to claim 1, characterized in that, The skin color picture is determined according to the skin picture of the target improvement area of the target object; when the skin color picture is the skin picture of the facial area, the method further includes the following steps: Perform positioning and cropping of facial features on the skin picture of the facial area, and retain the facial skin interested area of the target object; Use the facial skin interested area as the skin color picture.

5. The skin color quantization and management method according to claim 4, characterized in that The performing positioning and cropping of facial features on the skin picture of the facial area, and retaining the facial skin interested area of the target object includes the following steps: Perform color system conversion on the skin picture of the facial area, and then subtract the A* channel image and the B* channel image from the L* channel image to obtain an LBA image; Perform picture pixel brightness histogram analysis on the LBA image, and then calculate a threshold according to the analysis result and draw the facial skin contour of the target object; Locate the coordinate range of the facial skin contour in the skin picture of the facial area; Based on the coordinate range, locate the preliminary measurement area of each facial feature in the skin picture of the facial area; Perform picture pixel brightness histogram analysis on the preliminary measurement area of each facial feature, and then calculate a threshold according to the analysis result and draw the facial feature contour of each facial feature; Crop all the facial feature contours from the skin picture of the facial area to obtain the facial skin interested area of the target object.

6. The skin color quantization and management method according to claim 1, characterized in that, The multi-dimensional skin color parameters include surface flaw degree, lightness, lightness intensity difference, lightness area, redness degree, redness intensity difference, redness area, rosiness and glossiness; the extracting multi-dimensional skin color parameters based on the skin color picture includes the following steps: Extract the average intensity difference between the imperfect features and the normal skin area, the entropy of the gray-level co-occurrence matrix texture features, the average major length of the imperfect shapes greater than a preset ratio, the average pixel intensity of the imperfect shapes, the circularity of the imperfect shapes, and the average area percentage of the imperfect shapes from the skin color picture, and then calculate the surface flaw degree; Among them, the expression of the surface flaw degree is as follows: In the formula, SVI represents the surface flaw degree; dINT represents the average intensity difference between the imperfect features and the normal skin area; S represents the entropy of the gray-level co-occurrence matrix texture features; L represents the average major length of the imperfect shapes greater than a preset ratio; I represents the average pixel intensity of the imperfect shapes; C represents the circularity of the imperfect shapes; pctA represents the average area percentage of the imperfect shapes; Statistically obtain the mode value of the skin color distribution curve, the whiteness and redness of the CIE-LAB color system, and the oil spot index from the skin color picture; Determine the lightness based on the white pixels in the skin color picture whose whiteness values are between the standard deviations of the preset multiple ranges of the mode value of the skin color distribution curve; Determine the lightness intensity difference based on the difference between the intensity of the pixels corresponding to the lightness and the average brightness of all face pixels in the skin color picture; Determine the lightness area based on the proportion of the pixels corresponding to the lightness in the skin color picture; Determine the light redness based on the red pixels in the skin color picture whose redness values are between the standard deviations of the preset multiple ranges of the mode value of the skin color distribution curve; Determine the light red intensity difference based on the difference between the intensity of the pixels corresponding to the light redness and the average redness of all face pixels in the skin color picture; Determine the light red area based on the proportion of the pixels corresponding to the light redness in the skin color picture; The rosiness is calculated based on the light redness and the whiteness; wherein, the expression of the rosiness is: Rosiness = Light redness × Whiteness X , where X represents a constant parameter; The glossiness is calculated based on the lightness and the oil stain index; wherein, the expression of the glossiness is: Glossiness = (Lightness / Oil stain index X ) Y , where X and Y represent constant parameters.

7. The skin color quantization and management method according to claim 1, characterized in that, Quantitatively determining the target optimization parameters according to the reference skin color parameters corresponding to the multi-dimensional skin color parameters includes the following steps: Quantitatively analyze the improvement percentage of each dimension of the skin color parameters based on the reference skin color parameters corresponding to the multi-dimensional skin color parameters; Sort and screen according to the improvement percentage to obtain the target optimization parameters.

8. The skin color quantization and management method according to claim 7, characterized in that The quantitatively analyzing the improvement percentage of each dimension of the skin color parameters based on the reference skin color parameters corresponding to the multi-dimensional skin color parameters includes the following steps: Average the values of the same skin color parameter in all regions of the skin color picture to obtain the skin color parameter average value corresponding to each dimension of the skin color parameters; Determine the absolute parameter difference according to each dimension of the skin color parameter and its corresponding reference skin color parameter; Obtain the improvement percentage of each dimension of the skin color parameter according to the ratio of the absolute parameter difference corresponding to each dimension of the skin color parameter to the skin color parameter average value.

9. The skin color quantization and management method according to claim 7, characterized in that, The sorting and screening according to the improvement percentage to obtain the target optimization parameters includes the following steps: Sort the skin color parameters of all dimensions based on the numerical size of the improvement percentage; Use the preset number of skin color parameters with the largest improvement percentage in the sorting result as the target optimization parameters.

10. The skin color quantization and management method according to claim 1, characterized in that, Determining the skin management suggestions for the target object according to the mapping of the target optimization parameters includes the following steps: Compare the target optimization parameter with its corresponding skin color parameter threshold; Based on the comparison result between the target optimization parameter and the skin color parameter threshold, match the skin management advice from the preset management advice database in combination with the skin color range corresponding to the target optimization parameter.

11. The skin color quantization and management method according to claim 1, characterized in that, The method further includes the following steps: Use the multi-dimensional skin color parameters extracted from the expected skin color picture provided by the target object as the reference skin color parameters; Or, use the statistical result of the skin color quantization data in the target area range as the reference skin color parameters; Or, use the preset skin color parameter value as the reference skin color parameters.

12. A skin color quantization and management system, characterized in that, It includes: A first module for obtaining a skin color picture of a target object; A second module for extracting multi-dimensional skin color parameters based on the skin color picture, and then quantifying and determining target optimization parameters according to the reference skin color parameters corresponding to the multi-dimensional skin color parameters; A third module for mapping and determining the skin management advice of the target object according to the target optimization parameter.

13. An electronic device, characterized in that, It includes a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 11.

14. A computer storage medium storing a program executable by a processor, characterized in that, The program executable by the processor, when executed by the processor, is used to implement the method according to any one of claims 1 to 11.

Images