An ai technology-based makeup effect image data processing system

Abstract

The present application belongs to the technical field of color cosmetic effect image data processing, and relates to a color cosmetic effect image data processing system based on AI technology. The present application analyzes the similarity of the initial facial image of each specified user and each reference initial facial image, which helps to ensure the personalization and customization of the color cosmetic scheme, improves the user's satisfaction and the naturalness of the color cosmetic effect, and simplifies the selection process. By analyzing the color cosmetic evaluation index of each recommended color cosmetic simulation facial image of each specified user, it is helpful to provide objective and accurate color cosmetic effect evaluation, verify the accuracy of the recommended color cosmetic scheme, optimize the personalized color cosmetic recommendation algorithm, and improve the accuracy of the recommendation. By analyzing the color cosmetic preference evaluation index of each recommended color cosmetic simulation facial image of each specified user, the user's preference and expectation for color cosmetic products are accurately understood, and the user's satisfaction and loyalty are improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of makeup effect image data processing, and relates to a makeup effect image data processing system based on AI technology. BACKGROUND

[0002] In recent years, artificial intelligence technology has made significant progress, especially in the fields of image recognition, deep learning, computer vision, etc. The breakthroughs in these technologies have provided strong technical support for makeup effect image data processing. With the popularity of the Internet and the rise of e-commerce, the beauty industry has gradually shifted from offline to online. Online shopping platforms, social media, and live e-commerce channels have become important positions for the sale of beauty products. In order to improve user experience and shopping efficiency, the beauty industry urgently needs a technology that can quickly and accurately display makeup effects. Therefore, the makeup effect image data analysis and processing method based on AI technology has very important significance and role.

[0003] The existing makeup effect image data analysis and processing method has basically met the use requirements, but it still has certain deficiencies: on the one hand, the existing makeup effect image data analysis and processing method can automatically simulate makeup on the user's face, but the existing makeup effect image data analysis and processing method lacks the formulation and recommendation of makeup schemes based on the user's bare makeup face image, so it cannot quickly recommend suitable makeup schemes for users and cannot simplify the selection process.

[0004] On the other hand, the existing makeup effect image data analysis and processing method ignores the analysis of the makeup effect on the user's face from multiple dimensions such as the effect of the makeup and the user's personal evaluation, so it cannot provide objective and accurate makeup effect evaluation, which is not conducive to the user's understanding of the actual effect of the makeup and not conducive to improving the user's satisfaction and loyalty. SUMMARY

[0005] In view of this, in order to solve the problems raised in the background art, a makeup effect image data processing system based on AI technology is proposed.

[0006] The purpose of the present application can be achieved by the following technical solutions: the present application provides a makeup effect image data processing system based on AI technology, which comprises: a face image acquisition module, a face detection and analysis module, a makeup simulation module, a makeup evaluation feedback module, a user evaluation feedback module, a user preferred makeup acquisition module, an evaluation feedback module and a data repository.

[0007] The face image acquisition module is used to record each designated user as a user, and to obtain the initial face image of each designated user.

[0008] The face detection analysis module is configured to analyze the similarity between the initial face image of each specified user and each reference initial face image, and to obtain the reference initial face image of each specified user, and to obtain each recommended makeup scheme of each specified user based on the reference initial face image.

[0009] The makeup simulation module is configured to simulate makeup on each specified user based on each recommended makeup scheme of each specified user, and to obtain a simulated face image corresponding to each recommended makeup scheme of each specified user.

[0010] The makeup evaluation feedback module is configured to compare the simulated face image corresponding to each recommended makeup scheme of each specified user with the initial face image corresponding thereto, and to analyze the makeup evaluation index of the simulated face image corresponding to each recommended makeup scheme of each specified user.

[0011] The user evaluation feedback module is configured to obtain user evaluation data of the simulated face image corresponding to each recommended makeup scheme of each specified user, and to analyze the makeup preference evaluation index of the simulated face image corresponding to each recommended makeup scheme of each specified user.

[0012] The user preferred makeup obtaining module is configured to obtain each preferred makeup scheme of each specified user based on the makeup evaluation index and the makeup preference evaluation index of the simulated face image corresponding to each recommended makeup scheme of each specified user.

[0013] The evaluation feedback module is configured to analyze the makeup praise rate of the user and to feed back the same.

[0014] The data repository is configured to store each reference initial face image, to store each recommended makeup scheme of each reference initial face image, and to store the reference face contrast deviation, the reference face stereoscopic degree deviation, and the reference face proportion coordination deviation of the simulated face image corresponding to each recommended makeup scheme and the initial face image corresponding thereto.

[0015] Compared with the prior art, the present application has the following advantages: 1. The present application analyzes the similarity between the initial face image of each specified user and each reference initial face image, and obtains each recommended makeup scheme of each specified user, which helps to ensure the individualization and customization of the makeup scheme, improves the satisfaction of the user and the naturalness of the makeup effect, and simplifies the selection process.

[0016] 2. The present application analyzes the makeup evaluation index of the simulated face image corresponding to each recommended makeup scheme of each specified user, which helps to provide an objective and accurate evaluation of the makeup effect, helps the user to understand the actual effect of the makeup, verifies the accuracy of the recommended makeup scheme, and helps to optimize the individualized makeup recommendation algorithm and improve the accuracy of the recommendation.

[0017] 3、The application is helpful to accurately understand the user's favorite degree and expectation of the makeup product, also helps to improve the user's satisfaction and loyalty, is beneficial to optimize the product design and formula, and improves the market competitiveness of the product.

[0018] 4、The application is helpful to provide more personalized preferred makeup scheme for the user, also is beneficial to accurately position the product, optimize the product combination, improve the market competitiveness, and promotes the technical innovation of the makeup industry. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0020] Figure 1 It is a system module connection diagram of the present application.

[0021] Figure 2 It is a feature vector acquisition step diagram of the present application. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0023] Please refer to Figure 1As shown, this invention provides a makeup effect image data processing system based on AI technology, with the following module distribution: a facial image acquisition module, a facial detection and analysis module, a makeup simulation module, a makeup evaluation and feedback module, a user evaluation and feedback module, a user-preferred makeup acquisition module, an evaluation feedback module, and a data storage library. The modules are connected as follows: the facial image acquisition module is connected to the facial detection and analysis module; the facial detection and analysis module is connected to the makeup simulation module; the makeup simulation module is connected to the makeup evaluation and feedback module; the makeup evaluation and feedback module is connected to the user evaluation and feedback module; the user evaluation and feedback module is connected to the user-preferred makeup acquisition module; the user-preferred makeup acquisition module is connected to the evaluation and feedback module; and the data storage library is connected to both the facial detection and analysis module and the makeup evaluation and feedback module.

[0024] The facial image acquisition module is used to identify the users as designated users and obtain the initial facial images of each designated user.

[0025] The facial detection and analysis module is used to analyze the similarity between the initial facial image of each specified user and each reference initial facial image, thereby obtaining the reference initial facial image of each specified user, and based on this, obtaining each recommended makeup scheme for each specified user.

[0026] As a preferred feasible example, the specific analysis method for the similarity between the initial facial images of each specified user and each reference initial facial image includes: obtaining the feature vector of the initial facial image of each specified user. and the feature vectors of each reference initial facial image ,in , For each designated user, To specify the number of users, , Each reference initial facial image is numbered. The number of initial facial images is used as a reference.

[0027] According to the calculation formula The similarity between each reference initial facial image and the initial facial image of each specified user is obtained. ,in For the first The feature vector of the first reference initial facial image and the first The dot product of the feature vectors of the initial facial images of a specified user. The first The modulus of the feature vector of the initial facial image of a specified user and the first The modulus of the feature vector of a reference initial facial image.

[0028] As a preferred feasibility example, the feature vectors of the initial facial images of the specified users and the feature vectors of the reference initial facial images are specifically obtained in the following manner: S1, image preprocessing: performing grayscale and normalization processing on the initial facial images of the specified users and the reference initial facial images, respectively, to obtain grayscale images of the initial facial images of the specified users and grayscale images of the reference initial facial images.

[0029] S2, gradient calculation: calculating the gradient amplitude and direction of each pixel point in the grayscale images of the initial facial images of the specified users and the grayscale images of the reference initial facial images.

[0030] S3, cell division: dividing the grayscale images of the initial facial images of the specified users and the grayscale images of the reference initial facial images into a plurality of small cell units.

[0031] S4, gradient histogram statistics: performing histogram statistics of the gradient direction in each cell unit in the grayscale images of the initial facial images of the specified users and the grayscale images of the reference initial facial images.

[0032] S5, combination into feature vectors: combining the histograms of each cell unit in the grayscale images of the initial facial images of the specified users and the grayscale images of the reference initial facial images to form the feature vectors of the initial facial images of the specified users and the feature vectors of the grayscale images of the reference initial facial images.

[0033] It should be further noted that the feature vector acquisition step is shown in the schematic diagram as Figure 2

[0034] As a preferred feasibility example, the reference initial facial images of the specified users are specifically obtained in the following manner: sorting the similarity of each reference initial facial image with the initial facial image of the specified user from large to small, and screening the reference initial facial image with the first similarity ranking to obtain the reference initial facial image of the specified user.

[0035] As a preferred feasibility example, the recommended makeup schemes of the specified users are specifically obtained in the following manner: matching the reference initial facial image of each specified user with the recommended makeup scheme of each reference initial facial image stored in the data repository to obtain the recommended makeup scheme of each specified user.

[0036] ​The application helps to ensure the personalization and customization of the makeup scheme, helps to improve the satisfaction of the user and the naturalness of the makeup effect, and quickly recommends a suitable makeup scheme for the user, simplifying the selection process.

[0037] The makeup simulation module is configured to simulate makeup on each of the specified users based on the recommended makeup scheme of each of the specified users, and obtain a simulated facial image corresponding to the recommended makeup scheme of each of the specified users.

[0038] The makeup evaluation feedback module is configured to compare the simulated facial image corresponding to the recommended makeup scheme of each of the specified users with the initial facial image corresponding thereto, and analyze a makeup evaluation index of the simulated facial image corresponding to the recommended makeup scheme of each of the specified users.

[0039] As a preferred feasible example, the makeup evaluation index of the simulated facial image corresponding to the recommended makeup scheme of each of the specified users includes: comparing the simulated facial image corresponding to the recommended makeup scheme of each of the specified users with the initial facial image corresponding thereto, and obtaining a facial contrast deviation, a facial stereoscopic degree deviation and a facial proportion coordination degree deviation of the simulated facial image corresponding to the recommended makeup scheme of each of the specified users and the initial facial image corresponding thereto, respectively denoted as , wherein , is the number of each of the specified users, is the number of the specified users, , is the number of each of the recommended makeup schemes, is the number of the recommended makeup schemes.

[0040] The makeup evaluation index of the simulated facial image corresponding to the recommended makeup scheme of each of the specified users is analyzed , wherein are reference facial contrast deviations, reference facial stereoscopic degree deviations and reference facial proportion coordination degree deviations of the simulated facial image corresponding to the makeup scheme extracted from the information repository and the initial facial image corresponding thereto, are permissible difference values of the facial contrast deviation and the reference facial contrast deviation, the facial stereoscopic degree deviation and the reference facial stereoscopic degree deviation, and the facial proportion coordination degree deviation and the reference facial proportion coordination degree deviation.

[0041] It needs to be further explained that the permitted difference values of the set face contrast deviation from the reference face contrast deviation, the face stereoscopic degree deviation from the reference face stereoscopic degree deviation, and the face proportion coordination degree deviation from the reference face proportion coordination degree deviation can be respectively 0.01, 0.01, and 0.01. It means that the face contrast deviation from the reference face contrast deviation, the face stereoscopic degree deviation from the reference face stereoscopic degree deviation, and the face proportion coordination degree deviation from the reference face proportion coordination degree deviation can all allow one percent deviation.

[0042] The application helps to provide objective and accurate makeup effect evaluation by analyzing the makeup evaluation indexes of the simulation face images corresponding to the recommended makeup schemes of each specified user, which is beneficial for the user to understand the actual effect of makeup and verify the accuracy of the recommended makeup scheme, and further helps to optimize the personalized makeup recommendation algorithm and improve the accuracy of the recommendation.

[0043] The user evaluation feedback module is configured to obtain user evaluation data of the simulation face images corresponding to the recommended makeup schemes of each specified user, and analyze a makeup preference evaluation index of the simulation face images corresponding to the recommended makeup schemes of each specified user.

[0044] As a preferred feasibility example, the user evaluation data of the simulation face images corresponding to the recommended makeup schemes of each specified user includes a like value score and an expectation value score.

[0045] It needs to be further explained that the specific obtaining method of the like value score and the expectation value score of the simulation face images corresponding to the recommended makeup schemes of each specified user is to design a questionnaire for each specified user to score the like value and the expectation value of the simulation face images corresponding to the recommended makeup schemes, and then obtain the like value score and the expectation value score of the simulation face images corresponding to the recommended makeup schemes of each specified user.

[0046] As a preferred feasibility example, the makeup preference evaluation index of the simulation face images corresponding to the recommended makeup schemes of each specified user includes a specific analysis method, which includes extracting the like value score and the expectation value score of the simulation face images corresponding to the recommended makeup schemes of each specified user, respectively denoted as , and analyzing the makeup preference evaluation index of the simulation face images corresponding to the recommended makeup schemes of each specified user , wherein are the set like value score threshold and expectation value score threshold of the simulation face image, respectively.

[0047] In a specific example, the like value score and the expectation value score can be 10 points and 10 points, respectively, and the set like value score threshold and expectation value score threshold of the simulation face image can be 7 points and 7 points, respectively.

[0048] The present application helps to accurately understand the user's preference degree and expectation for the makeup product by obtaining the user evaluation data of the recommended makeup scheme corresponding to the simulation facial image of each specified user, analyzing the makeup preference evaluation index of the recommended makeup scheme corresponding to the simulation facial image of each specified user, and helps to improve the user's satisfaction and loyalty, and is beneficial to the optimization of product design and formula, and improves the market competitiveness of the product.

[0049] The user preferred makeup obtaining module is used to obtain each preferred makeup scheme of each specified user based on the makeup evaluation index and the makeup preference evaluation index of each recommended makeup scheme corresponding to the simulation facial image of each specified user.

[0050] As a preferred feasible example, the specific obtaining method of each preferred makeup scheme of each specified user includes: according to the analysis formula obtain the comprehensive evaluation coefficient of each recommended makeup scheme of each specified user , wherein are the weight factors of the comprehensive evaluation coefficient corresponding to the set makeup evaluation index and the makeup preference evaluation index, respectively.

[0051] It needs to be further pointed out that the weight factors of the comprehensive evaluation coefficient corresponding to the set makeup evaluation index and the makeup preference evaluation index can be respectively set to 0.6 and 0.4.

[0052] The makeup effect evaluation index is usually based on professional image analysis technology and aesthetic standard, which can objectively measure the performance of makeup in color matching, contour shaping, clarity, etc. These indexes have certain scientificity and accuracy, which can provide more reliable evaluation for the quality and effect of makeup. The indexes such as contrast, stereoscopic degree, proportion coordination degree and clarity in the makeup effect evaluation index can be determined by specific numerical calculation and analysis, which are not affected by personal subjective preference. Therefore, the weight factor of the comprehensive evaluation coefficient corresponding to the makeup evaluation index is valued as 0.6, which is beneficial to ensure that the comprehensive evaluation result has certain professionalism and objectivity.

[0053] The makeup preference evaluation index reflects the demand and satisfaction of consumers for makeup. Although the makeup effect evaluation index can objectively measure the quality and effect of makeup, the ultimate purpose is to meet the needs and preferences of consumers. Therefore, the weight factor of the comprehensive evaluation coefficient corresponding to the makeup preference evaluation index is valued as 0.4.

[0054] The comprehensive evaluation coefficients of each recommended makeup scheme of each specified user are compared with the set comprehensive evaluation coefficient threshold respectively, and each recommended makeup scheme of each specified user whose comprehensive evaluation coefficient is greater than or equal to the comprehensive evaluation coefficient threshold is screened out, which is recorded as each preferred makeup scheme of each specified user.

[0055] The evaluation and feedback module is used to analyze users' positive feedback rates for makeup products and provide feedback accordingly.

[0056] As a preferred example of feasibility, the user's positive review rate for makeup can be analyzed by: statistically analyzing each preferred makeup scheme for each specified user to obtain the number of preferred makeup schemes for each specified user.

[0057] Extract the makeup preference rating index of each recommended makeup scheme for each specified user and the corresponding simulated facial image. Compare each index with the set makeup preference rating index threshold. If the makeup preference rating index of a specified user's recommended makeup scheme is greater than or equal to the makeup preference rating index threshold, then the specified user's recommended makeup scheme is recorded as the specified user's preferred recommended makeup scheme. This process is repeated to obtain the preferred recommended makeup schemes for each specified user. Finally, the number of preferred recommended makeup schemes for each specified user is calculated.

[0058] The number of preferred makeup schemes for each designated user is summed with the number of their favorite recommended makeup schemes, and the sum is recorded as the number of highly-rated recommended makeup schemes for each designated user. ;

[0059] Analyze user reviews of makeup products And provide feedback.

[0060] The data repository is used to store each reference initial facial image, each recommended makeup scheme for each reference initial facial image, and the reference facial contrast deviation, reference facial three-dimensionality deviation, and reference facial proportion coordination deviation between the simulated facial image corresponding to the makeup scheme and its corresponding initial facial image.

[0061] This invention analyzes and provides feedback on the preferred makeup solutions for each designated user and the user's positive feedback rate for the makeup products. This helps to provide users with more personalized preferred makeup solutions, and also helps to accurately position products, optimize product portfolios, enhance market competitiveness, and promote technological innovation in the makeup industry.

[0062] The above content is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, and all such modifications and additions should fall within the protection scope of the present invention.

Claims

1. A makeup effect image data processing system based on AI technology, characterized in that: include: The facial image acquisition module records the users as designated users and acquires the initial facial images of each designated user. The facial detection and analysis module analyzes the similarity between the initial facial image of each specified user and each reference initial facial image to obtain the reference initial facial image of each specified user, and based on this, obtains each recommended makeup scheme for each specified user. The makeup simulation module simulates makeup application for each specified user based on their recommended makeup schemes, and obtains simulated facial images corresponding to each specified user's recommended makeup schemes. The makeup evaluation and feedback module compares the simulated facial images corresponding to each recommended makeup scheme for each specified user with their corresponding initial facial images, thereby obtaining the facial contrast deviation between the simulated facial images and their corresponding initial facial images for each specified user. Facial three-dimensionality deviation and facial proportions , , For each designated user, To specify the number of users, , Each recommended makeup scheme is assigned a number. The number of recommended makeup options; Analyze the makeup evaluation metrics of each recommended makeup scheme for each specified user and the corresponding simulated facial images. ,in These are the reference facial contrast deviation, reference facial three-dimensionality deviation, and reference facial proportion harmony deviation between the simulated facial image corresponding to the makeup scheme extracted from the information reserve and its corresponding initial facial image. These are the permissible differences between the set facial contrast deviation and the reference facial contrast deviation, the permissible differences between the facial three-dimensionality deviation and the reference facial three-dimensionality deviation, and the permissible differences between the facial proportion coordination deviation and the reference facial proportion coordination deviation, respectively. The user review and feedback module obtains user review data for each recommended makeup scheme corresponding to the simulated facial images of each specified user, and analyzes the makeup liking evaluation index for each recommended makeup scheme corresponding to the simulated facial images of each specified user. The user-preferred makeup acquisition module obtains each user's preferred makeup scheme based on the makeup evaluation index and makeup preference evaluation index of each user's recommended makeup scheme corresponding to the simulated facial image. The evaluation and feedback module analyzes users' positive review rates for makeup products and provides feedback accordingly. The data repository stores each initial reference facial image, each recommended makeup scheme for each initial reference facial image, and... .

2. The makeup effect image data processing system based on AI technology according to claim 1, characterized in that: The specific analysis method for the similarity between the initial facial image of each designated user and each reference initial facial image includes: Obtain the feature vector of the initial facial image of each specified user. and the feature vectors of each reference initial facial image ,in , For each designated user, To specify the number of users, , Each reference initial facial image is numbered. The number of initial facial images is used as a reference; According to the calculation formula The similarity between each reference initial facial image and the initial facial image of each specified user is obtained. ,in For the first The feature vector of the first reference initial facial image and the first The dot product of the feature vectors of the initial facial images of a specified user. The first The modulus of the feature vector of the initial facial image of a specified user and the first The modulus of the feature vector of a reference initial facial image.

3. The makeup effect image data processing system based on AI technology according to claim 2, characterized in that: The specific methods for obtaining the feature vectors of the initial facial images of each designated user and the feature vectors of each reference initial facial image include: S1. Image preprocessing: The initial facial images of each specified user and each reference initial facial image are processed by grayscale and normalization respectively to obtain the grayscale images of the initial facial images of each specified user and the grayscale images of each reference initial facial image. S2. Calculate gradient: Calculate the gradient magnitude and direction of each pixel in the grayscale image of the initial facial image of each specified user and the grayscale image of each reference initial facial image; S3. Divide into cell units: Divide the grayscale images of the initial facial images of each specified user and the grayscale images of each reference initial facial image into several small cell units. S4. Statistical gradient histogram: A histogram of the statistical gradient directions within each cell unit in the grayscale images of the initial facial images of each specified user and the grayscale images of each reference initial facial image. S5. Combine to form feature vectors: Combine the histograms of each cell unit in the grayscale images of the initial facial images of each specified user and the grayscale images of each reference initial facial images to form the feature vectors of the initial facial images of each specified user and the feature vectors of the grayscale images of each reference initial facial images.

4. The makeup effect image data processing system based on AI technology according to claim 2, characterized in that: The specific methods for obtaining the reference initial facial images of each designated user include: Sort the similarity between each reference initial facial image and the initial facial image of each specified user in descending order, and select the reference initial facial images with the highest similarity to the initial facial images of each specified user. These reference initial facial images are then recorded as the reference initial facial images of each specified user.

5. The makeup effect image data processing system based on AI technology according to claim 4, characterized in that: The specific methods for obtaining the recommended makeup schemes for each designated user include: The reference initial facial image of each specified user is matched with each recommended makeup scheme of each reference initial facial image stored in the database to obtain each recommended makeup scheme of each specified user.

6. The makeup effect image data processing system based on AI technology according to claim 1, characterized in that: The user evaluation data for each recommended makeup scheme for each designated user, corresponding to the simulated facial image, includes preference score and expectation score.

7. The makeup effect image data processing system based on AI technology according to claim 6, characterized in that: The specific analysis method for evaluating the makeup preference index of each recommended makeup scheme for each designated user corresponding to the simulated facial image includes: Extract the preference score and expected score of each user's simulated facial image corresponding to each recommended makeup scheme, and record them as follows: Analyze the makeup preference evaluation index of each user based on the simulated facial images corresponding to each recommended makeup scheme. ,in These are the set preference value rating threshold and expected value rating threshold for the simulated facial image, respectively.

8. The makeup effect image data processing system based on AI technology according to claim 7, characterized in that: The specific methods for obtaining the preferred makeup schemes for each designated user include: According to the analysis formula The overall evaluation coefficient of each recommended makeup scheme for each designated user was obtained. ,in These are the weighting factors for the comprehensive evaluation coefficients corresponding to the set makeup evaluation indicators and makeup liking evaluation indicators, respectively; The overall evaluation coefficient of each recommended makeup scheme of each designated user is compared with the set overall evaluation coefficient threshold. The recommended makeup schemes of each designated user with an overall evaluation coefficient greater than or equal to the overall evaluation coefficient threshold are selected and recorded as the preferred makeup schemes of each designated user.

9. The makeup effect image data processing system based on AI technology according to claim 8, characterized in that: The specific analysis methods for the user's positive review rate for makeup products include: The number of preferred makeup schemes for each designated user is obtained by statistically analyzing each user's preferred makeup scheme. Extract the makeup preference rating index of each recommended makeup scheme for each specified user and the corresponding simulated facial image. Compare the index with the set makeup preference rating index threshold. If the makeup preference rating index of a specified user's recommended makeup scheme is greater than or equal to the makeup preference rating index threshold, then the specified user's recommended makeup scheme is recorded as the specified user's preferred recommended makeup scheme. This process is repeated to obtain the preferred recommended makeup schemes of each specified user. The number of preferred recommended makeup schemes for each specified user is then calculated. The number of preferred makeup schemes for each designated user is summed with the number of their favorite recommended makeup schemes, and the sum is recorded as the number of highly-rated recommended makeup schemes for each designated user. ; Analyze user reviews of makeup products And provide feedback.

Images