Makeup color analysis method

Abstract

The invention relates to a makeup color analysis method. The makeup color analysis method comprises the following steps: acquiring a baseline picture and a non-baseline picture; setting colors of which the color difference is not greater than a first color tolerance as the same color number, analyzing the color numbers contained in the baseline picture and the area proportion thereof, and selecting a plurality of color numbers as reference color numbers; setting colors of which the color difference is not greater than a second color tolerance as the same color number, analyzing the color numbers included in the non-baseline picture and the area proportion of the color numbers, and obtaining color numbers to be compared and the area proportion of the color numbers to be compared; and for any reference color number, counting the sum of the area proportions of all the color numbers to be compared in the non-baseline picture, and comparing the sum with the area proportion of the reference color number in the baseline picture to obtain the area proportion change value of the current reference color number. The makeup color change can be effectively, accurately and quickly analyzed.

Description

Technical Field

[0001] The present invention relates to the technical field of makeup color analysis, and in particular to a makeup color analysis method. Background Art

[0002] Makeup effect analysis is an important part of the cosmetics industry and related fields. It involves evaluating and analyzing the changes in color, texture, and durability of cosmetics, especially color cosmetics, after application. By analyzing the color changes, durability, gloss and other effects of color cosmetics, cosmetics companies can develop products that better meet market demand.

[0003] The color difference of makeup before and after the color change is small. The makeup may fall off or oxidize, and the color may fade or even expose the skin. Makeup color analysis is needed to evaluate the color effect change of makeup. The existing makeup color analysis method mainly relies on the subjective evaluation of evaluators in the laboratory, which has the following problems:

[0004] 1. Data is not objective: The evaluation of cosmetic color effects often involves personal visual perception, which may lead to subjective data. For example, different evaluators may have different evaluations of the same cosmetic effect, which affects the objectivity of the data.

[0005] 2. The consistency of repeated evaluations is average: Even if the same evaluator evaluates the same makeup effect at different times, he or she may get different results due to fatigue, emotions or other factors, which affects the consistency of the evaluation.

[0006] 3. Human evaluation takes a long time: Human evaluation usually takes a long time, especially when multiple people or multiple rounds of evaluation are required. This not only reduces the efficiency of the evaluation, but also increases the cost.

[0007] Therefore, there is an urgent need for a makeup color analysis method that can solve the above problems. Summary of the invention

[0008] The technical problem to be solved by the present invention is to provide a makeup color analysis method that can effectively, accurately and quickly analyze makeup color changes.

[0009] The technical solution adopted by the present invention to solve the technical problem is: to provide a makeup color analysis method, comprising the following steps:

[0010] Get baseline images and non-baseline images;

[0011] Set colors whose color difference is not greater than the first color tolerance as the same color number, analyze the color numbers and their area proportions contained in the baseline image, and select several color numbers therein as reference color numbers;

[0012] Set colors whose color difference is not greater than the second color tolerance as the same color number, analyze the color numbers and their area proportions contained in the non-baseline image, and obtain the color numbers to be compared and their area proportions;

[0013] For any of the reference color numbers, the sum of the area proportions of all the color numbers to be compared whose color differences are less than the tolerance threshold in the non-baseline image is counted, and then compared with the area proportion of the reference color number in the baseline image to obtain the area proportion change value of the current reference color number.

[0014] Furthermore, the first color tolerance is an integer multiple of the second color tolerance.

[0015] Furthermore, the tolerance threshold is equal to the first color tolerance.

[0016] Furthermore, the second color tolerance is 1.

[0017] Furthermore, the first color tolerance is 5.

[0018] Furthermore, the reference color numbers are the color numbers with the largest area among the color numbers included in the baseline image.

[0019] Furthermore, the baseline image and the non-baseline image are subjected to color analysis by using a color clustering algorithm.

[0020] Furthermore, the color clustering algorithm comprises the following steps:

[0021] Count the color values ​​of the pixels contained in the image to be analyzed and the number of pixels corresponding to them;

[0022] Perform cluster analysis based on the set color difference and the number of pixels corresponding to the color value of each pixel to obtain multiple cluster centers and their weight values;

[0023] Each of the cluster centers is regarded as a color number, and its weight value is regarded as the area ratio corresponding to the color number.

[0024] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above-described makeup color analysis methods when executing the computer program.

[0025] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any of the above-described makeup color analysis methods.

[0026] Beneficial Effects

[0027] Due to the adoption of the above technical scheme, the present invention has the following advantages and positive effects compared with the prior art: the present invention performs color cluster analysis on the baseline image and the non-baseline image by respectively setting different color tolerances, and then calculates the change in the area ratio of the target color number in the baseline image and the area ratio of the equivalent color number in the non-baseline image, the analysis standard is consistent, and the makeup color change can be effectively, accurately and quickly analyzed; the present invention can adjust the distinction according to the color number range by adjusting the color tolerance, and is suitable for base makeup, lip makeup, and makeup analysis, with rich usage scenarios, high analysis efficiency and high consistency of repeated analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 is a flow chart of a first embodiment of the present invention;

[0029] Figure 2 This is a diagram of the color clustering analysis results of the first embodiment of the present invention. DETAILED DESCRIPTION

[0030] The present invention will be further described below in conjunction with specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention. In addition, it should be understood that after reading the content taught by the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms fall within the scope limited by the appended claims of the application equally.

[0031] The first embodiment of the present invention relates to an image-based makeup color analysis method, such as Figure 1 As shown, the following steps are included:

[0032] S0 obtains baseline images and non-baseline images;

[0033] S1 performs cluster analysis on the baseline image according to color, so that the color difference within the class is not greater than the set color tolerance, which is set to be no greater than 5 in this embodiment, and can also be set to other values; the color tolerance can adopt the CIE76 algorithm (Euclidean distance in Lab color space), and the CIEDE2000 algorithm that is more in line with human eye perception is preferred;

[0034] S2, according to the different categories of color numbers and the corresponding area proportions obtained in step S1, select a number of color numbers whose color changes need to be further analyzed. In this embodiment, the first few color numbers with the largest recorded area proportions are selected as reference color numbers. Alternatively, any color number that needs to be analyzed can be selected from the obtained color numbers as reference color numbers.

[0035] S3 resets the color tolerance, which can be set to an integer fraction of the color tolerance used in step S1, and is set to 1 here. Then, the non-baseline photo is analyzed using the method in step S1, and the tolerance between each color number in the non-baseline photo and the reference color number is calculated. Pixels with a tolerance less than 5 (i.e., the color tolerance value set in step S1) are calculated as the area ratio of the reference color in the non-baseline photo.

[0036] S4 uses the change in the area ratio of the reference color number in subsequent non-baseline photos as an objective analysis indicator of makeup color changes.

[0037] In step S1 and step S2, the color clustering analysis can use the k-means algorithm. Specifically, the following steps are included:

[0038] A0 extracts color information from the image to be analyzed and counts the number of pixels corresponding to each color value. The color value may be an RGB color value representing the three color channels of red, green and blue of the pixel.

[0039] A1 sets the color tolerance, that is, the difference between the number of pixels corresponding to each color value and the color value, and clusters each color value based on the color tolerance to obtain a clustering result. Specifically, it includes:

[0040] Initialize cluster centers: randomly select k colors as initial cluster centers, or use other methods (such as k-means++) to select initial centers to improve clustering quality;

[0041] Assign pixels to the nearest cluster center: For each pixel in the image, calculate its distance to each cluster center (usually using Euclidean distance) and assign the pixel to the nearest cluster center;

[0042] Update cluster centers: For each cluster, calculate the average color of all pixels assigned to the cluster and update the cluster center;

[0043] Repeat the steps of assigning pixels and updating cluster centers until the cluster centers no longer change or the preset number of iterations is reached; eventually, each pixel will be assigned to a cluster, and you can replace the color of each pixel with the color of the cluster center to obtain a clustered image, such as Figure 2 As shown;

[0044] Each cluster center is regarded as a color number, and its weight value is regarded as the area ratio corresponding to the color number to obtain the final color clustering analysis result.

[0045] As can be seen from the above, the method of the present invention can be used to evaluate the color effect changes of cosmetics by capturing the subtle differences between color numbers. The analysis standard of this method is fixed, and the accuracy of color cluster analysis can be adjusted by adjusting the color tolerance values ​​in steps S1 and S2 (that is, the discrimination can be adjusted according to the color number range). It is suitable for color change analysis in different application scenarios such as base makeup, lip makeup, and color makeup, with high analysis efficiency and high consistency in repeated analysis.

[0046] A second embodiment of the present invention relates to an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the image-based makeup color analysis method of the first embodiment when executing the computer program.

[0047] A third embodiment of the present invention relates to a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the image-based makeup color analysis method of the first embodiment are implemented.

[0048] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0049] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0050] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction method, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0051] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0052] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A makeup color analysis method, characterized in that: The following steps are involved: Get baseline images and non-baseline images; Set colors whose color difference is not greater than the first color tolerance as the same color number, analyze the color numbers and their area proportions contained in the baseline image, and select several color numbers therein as reference color numbers; Set colors whose color difference is not greater than the second color tolerance as the same color number, analyze the color numbers and their area proportions contained in the non-baseline image, and obtain the color numbers to be compared and their area proportions; For any of the reference color numbers, the sum of the area proportions of all the color numbers to be compared whose color differences are less than the tolerance threshold in the non-baseline image is counted, and then compared with the area proportion of the reference color number in the baseline image to obtain the area proportion change value of the current reference color number.

2. The method according to claim 1, characterized in that The first color tolerance is an integer multiple of the second color tolerance.

3. The method according to claim 2, characterized in that The tolerance threshold is equal to the first color tolerance.

4. The method according to claim 2, characterized in that The second color tolerance is 1.

5. The method according to claim 2, characterized in that: The first color tolerance is 5.

6. The method according to claim 1, characterized in that The reference color numbers are the color numbers with the largest area among the color numbers included in the baseline image.

7. The method according to claim 1, characterized in that The baseline image and the non-baseline image are subjected to color analysis by a color clustering algorithm.

8. The method according to claim 7, characterized in that The color clustering algorithm comprises the following steps: Count the color values ​​of the pixels contained in the image to be analyzed and the number of pixels corresponding to them; Perform cluster analysis based on the set color difference and the number of pixels corresponding to the color value of each pixel to obtain multiple cluster centers and their weight values; Each of the cluster centers is regarded as a color number, and its weight value is regarded as the area ratio corresponding to the color number.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the makeup color analysis method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the makeup color analysis method according to any one of claims 1 to 8 are implemented.

Images