A method for evaluating the wrinkle improvement effect of cosmetics

By collecting and analyzing images from different angles of users, and calculating wrinkle change coefficients based on light intensity and focus distance, the problem of inaccurate wrinkle recognition in the prior art is solved, and a more accurate evaluation of the effect of cosmetic wrinkle improvement is achieved.

CN118470766BActive Publication Date: 2024-11-12GUANGZHOU LAIDE PU DETECTION TECH CO LTD
View PDF 15 Cites 0 Cited by

Patent Information

Application Number
CN202410504996.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-25
Publication Date
2024-11-12
Estimated Expiration
2044-04-25

AI Technical Summary

Technical Problem

The prior art recognizes inaccurate recognition due to changes in facial position when identifying wrinkles, which cannot meet the needs of accurate evaluation of cosmetic improvement effects.

Method used

Images from different angles of users are collected through the image acquisition device, and the wrinkle length and depth before and after makeup are analyzed using edge detection method. The wrinkle change coefficient is calculated based on the light intensity and focus distance, and the cosmetic effect is judged based on the makeup holding time.

Benefits of technology

It improves the accuracy of wrinkle recognition, reduces the error in cosmetic quality evaluation, and provides a more accurate evaluation of the effect of cosmetic wrinkle improvement.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118470766B_ABST
    Figure CN118470766B_ABST
Patent Text Reader

Abstract

The present invention discloses a method for evaluating the wrinkle improvement effect of cosmetics, which relates to the field of image recognition technology and is used to solve the problem that when a user uses software to identify wrinkles, the appearance of wrinkles may change due to the user's facial position, which may lead to inaccurate identification and thus cause deviation in the evaluation of the improvement effect of cosmetics. The method includes judging the effect of cosmetics according to the user's wrinkle variation coefficient and the user's makeup holding time, collecting images of the user at different angles for analysis, and determining the facial condition of the current user according to the wrinkle status of the user at each angle, thereby solving the problems of blurred wrinkles in existing image recognition and inaccurate evaluation of cosmetics. At the same time, the present invention comprehensively analyzes the wrinkle improvement situation by integrating the images of the user before and after makeup at each position of the user, and then evaluates the wrinkle improvement effect of the cosmetics. The accuracy of wrinkle recognition of the current user is improved, and the error in evaluating the quality of cosmetics is greatly reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition, and more particularly to a method for evaluating the wrinkle improvement effect of cosmetics. Background Art

[0002] Image recognition technology is an artificial intelligence technology designed to enable computers to understand and interpret digital images. This technology involves extracting useful information from images and classifying, identifying or analyzing them. When applied to wrinkle identification, image recognition technology can detect the degree of wrinkles by analyzing facial expressions, skin and eye features. Image recognition technology plays an important role in some software when testing the effect of cosmetics on wrinkle improvement.

[0003] The prior art has the following deficiencies:

[0004] When users use software to identify wrinkles, the appearance of wrinkles may change due to the position of the user's face, which may lead to inaccurate identification and thus deviation in the evaluation of the improvement effect of cosmetics. It cannot meet the accuracy requirements for evaluating cosmetics and cannot meet the needs of users to select suitable cosmetics.

[0005] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method for evaluating the wrinkle improvement effect of cosmetics to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for evaluating the wrinkle improvement effect of a cosmetic, comprising the following steps:

[0009] Step S1, collecting user images and the user's makeup-wearing time through image acquisition equipment and page guidance; using a light intensity meter to detect the light intensity when taking the image, and accessing the camera metadata to obtain the focus distance when taking the image;

[0010] Step S2, classifying the user image into a frontal face image, a side face image, an upward-looking image, and a top-down image according to the shooting position, obtaining the facial data of the user at each position in the user image using an edge detection method, and calculating the wrinkle improvement coefficient at each position of the user according to the facial data at each position of the user and the makeup wearing time;

[0011] Step S3, analyzing the clarity of the user image at each position by light intensity and focus distance, setting the weight of the wrinkle improvement coefficient at each position of the user according to the clarity of the user image at each position, and calculating the wrinkle change coefficient of the user;

[0012] Step S4, judging the effect of the cosmetics according to the wrinkle variation coefficient of the user and the makeup wearing time of the user.

[0013] In a preferred embodiment, in step S1, the user image includes a frontal face image of the user, a side face image of the user, an upward-looking image of the user, and a downward-looking image of the user. A light intensity meter is placed on the image sensor of the camera to collect the light intensity when the image is taken, and the metadata of the camera is accessed to obtain the focus distance of the image.

[0014] In a preferred embodiment, in step S2, the length and depth of wrinkles before makeup in the image of the user before makeup are detected using an edge detection method, and the specific steps are as follows:

[0015] Image preprocessing: first preprocess the collected user images;

[0016] Edge detection: Use edge detection algorithms to detect edges in images;

[0017] Contour extraction: extract contours from detected edges;

[0018] Measure length and depth: Based on the extracted wrinkle contours.

[0019] In a preferred embodiment, in step S2, the product of the wrinkle length before makeup and the wrinkle depth before makeup in the user image at each position is used as the wrinkle degree coefficient of the user before makeup, and then the wrinkle length and wrinkle depth after makeup in the user image at each position are detected using an edge detection method, and the product of the wrinkle length after makeup and the wrinkle depth after makeup at each position is used as the wrinkle degree coefficient of the user after makeup, and the wrinkle degree coefficient of the user before makeup and the wrinkle degree coefficient of the user after makeup at the corresponding position are subtracted to obtain the wrinkle variation coefficient of each position.

[0020] In a preferred embodiment, in step S3, the illumination intensity when shooting the front face image of the user before makeup and the illumination intensity when shooting the front face image of the user after makeup collected by the light intensity meter are averaged as the light intensity coefficient of the front face image of the user, the focus distance of the front face image of the user before makeup and the focus distance of the front face image of the user after makeup obtained by accessing the metadata of the camera are averaged as the focus coefficient of the front face image of the user, and the light intensity coefficient of the side face image of the user and the focus coefficient of the side face image of the user are obtained in sequence;

[0021] The light intensity coefficient and focus coefficient of the image at each position are normalized, the clarity score of the image at each position is weighted and calculated, and the clarity score of the image at each position is weighted according to the priority diagram method to determine the weight value of the image at each position.

[0022] In a preferred embodiment, in step S3, the specific weighted calculation method is as follows:

[0023] After normalizing the image intensity coefficient and the image focus coefficient at each position, they are recorded as g and d respectively, and the clarity score calculation formula of the image at each position is Q(j)=gd. In the formula, Q(j) is the clarity score of the image at each position, and j represents the sequence number of the image at each position.

[0024] In a preferred embodiment, in step S3, after the clarity scores of the images at each position are calculated, the clarity scores of the images at each position are compared, and clarity weights are assigned to the clarity scores of the images at each position according to the priority diagram method. The wrinkle variation coefficient G at each position of the user is weighted averaged according to the clarity weight values ​​of each position to obtain a comprehensive wrinkle variation coefficient.

[0025] In a preferred embodiment, in step S4, after obtaining the user wrinkle variation coefficient and the user makeup holding time, the user wrinkle variation coefficient and the user makeup holding time are defined as input variables, and they are divided into different fuzzy sets respectively;

[0026] The cosmetic effect is defined as the output variable and divided into fuzzy sets;

[0027] Formulate fuzzy rules to describe the impact of the user's wrinkle variation coefficient and the user's makeup holding time definition on the cosmetics effect;

[0028] Perform fuzzy reasoning based on fuzzy rules to determine the effect of cosmetics.

[0029] Technical effects and advantages of a method for evaluating the wrinkle improvement effect of cosmetics of the present invention:

[0030] The present invention first collects images of the user at different angles for analysis, and determines the current user's facial condition based on the wrinkle status of the user at each angle, thereby solving the problems of blurred wrinkle recognition in existing images and inaccurate evaluation of cosmetics. At the same time, the present invention comprehensively analyzes the wrinkle improvement status of the user before and after makeup at various positions of the user, and then evaluates the wrinkle improvement effect of the cosmetics. The accuracy of wrinkle recognition of the current user is improved, and the error in evaluating the quality of cosmetics is greatly reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is a flow chart of a method for evaluating the wrinkle improvement effect of cosmetics according to the present invention;

[0032] Figure 2 The present invention is a logic diagram of a method for evaluating the wrinkle improvement effect of cosmetics. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] The present invention first collects images of the user at different angles for analysis, and determines the current user's facial condition based on the wrinkle status of the user at each angle, thereby solving the problems of blurred wrinkle recognition in existing images and inaccurate evaluation of cosmetics. At the same time, the present invention comprehensively analyzes the wrinkle improvement status of the user before and after makeup at various positions of the user, and then evaluates the wrinkle improvement effect of the cosmetics. The accuracy of wrinkle recognition of the current user is improved, and the error in evaluating the quality of cosmetics is greatly reduced.

[0035] Example

[0036] like Figure 1 , Figure 2 As shown, a method for evaluating the wrinkle improvement effect of a cosmetic according to the present invention comprises the following steps:

[0037] Step S1, collect user images and the makeup-wearing time of the user through image acquisition equipment and page guidance. Use a light intensity meter to detect the light intensity when taking the image, and access the camera metadata to obtain the focus distance when taking the image.

[0038] Step S2: classify the user image into a frontal face image, a side face image, an upward-looking image, and a top-down image according to the shooting position. Use edge detection to obtain the facial data of the user at each position in the user image, and calculate the wrinkle improvement coefficient of each position of the user according to the facial data of each position of the user and the makeup wearing time.

[0039] Step S3, analyzing the clarity of the user image at each position by light intensity and focus distance, setting the weight of the wrinkle improvement coefficient at each position of the user according to the clarity of the user image at each position, and calculating the wrinkle change coefficient of the user.

[0040] Step S4, judging the effect of the cosmetics according to the wrinkle variation coefficient of the user and the makeup wearing time of the user.

[0041] The specific implementation is as follows:

[0042] In step S1, it is first necessary to collect user images, and use the image acquisition device on the user device, such as a camera, to collect user images. In this step, the software will provide a page to guide the collection of user makeup holding time, and require the user to provide user images from four angles, where the user images include the user's front face image, the user's side face image, the user's upward view image, and the user's overhead view image. The user's front face image includes the user's front face image before makeup and the user's front face image after makeup, the user's side face image includes the user's side face image before makeup and the user's side face image after makeup, the user's upward view image includes the user's upward view image before makeup and the user's upward view image after makeup, and the user's overhead view image includes the user's overhead view image before makeup and the user's overhead view image after makeup. The light intensity meter is placed on the image sensor of the camera to collect the light intensity when shooting the image, and the metadata of the camera is accessed to obtain the focus distance of the image.

[0043] It should be noted that the image acquisition device can be various types of camera devices, among which the software uses more mobile device cameras. The page guidance requires the user to complete the requirements before jumping to the next page. The user can be required to fill in the makeup time from the completion of makeup to the capture of the user's makeup image, and when collecting user images, the user can be required to complete the front face, side face, head up, and head down operations in sequence to obtain user images in four positions. The specific left and right sides of the side face image are determined by the position of the wrinkles. A light meter is a device that measures the intensity of light. By converting light into digital signals, data processing and analysis can be conveniently performed. The metadata of the camera contains a lot of information about the captured image, and the focus distance data can be obtained through the metadata of the camera.

[0044] In step S2, the edge detection method is first used to detect the length and depth of the wrinkles before makeup in the image of the user before makeup. The specific steps are as follows:

[0045] Image preprocessing: First, the collected user images are preprocessed, such as denoising, adjusting brightness and contrast. Preprocessing operations help improve the accuracy of subsequent wrinkle analysis.

[0046] Edge detection: Edge detection algorithms, such as the Canny edge detection algorithm, are used to detect edges in the image. These algorithms can identify significant changes between different areas in the image, usually manifested as drastic changes in color, that is, the edges of wrinkles.

[0047] Contour extraction: Extract contours from detected edges. This can be done by using a contour detection algorithm to get the contours of the wrinkles.

[0048] Measuring length and depth: Given the extracted wrinkle contours, measurement tools can be used to measure the length and depth of the wrinkles. The length can be obtained directly from the path length of the contour, while the depth can usually be estimated by measuring the distance from the contour to the image background.

[0049] The product of the wrinkle length before makeup and the wrinkle depth before makeup in the user image at each position is taken as the wrinkle degree coefficient of the user before makeup, and then the edge detection method is used to detect the wrinkle length and wrinkle depth after makeup in the user image at each position. The product of the wrinkle length after makeup and the wrinkle depth after makeup at each position is taken as the wrinkle degree coefficient of the user after makeup, and the wrinkle degree coefficient of the user before makeup and the wrinkle degree coefficient of the user after makeup at the corresponding position are subtracted to obtain the wrinkle variation coefficient G at each position.

[0050] It should be noted that edge detection is a common technique in computer vision and image processing, which is used to detect the position of the edge of an object in an image. This helps to identify and segment objects in an image. Edge detection can be used to initially segment the user image before wrinkle processing. When identifying wrinkles, the length and depth of the wrinkles can be analyzed by setting the brightness mode. The Sigmoid function is usually used to map values ​​to the (0,1) interval and can be used for data normalization. The Canny edge detection algorithm is a classic edge detection method that determines the edge by analyzing whether adjacent pixels are within a given threshold. Contour detection is a common technique in image processing that is used to detect the boundaries of objects in an image. It can help identify and describe the shape and structure of objects in an image and is often used in applications such as target detection, image segmentation, and shape recognition.

[0051] In step S3, since the image clarity of each position of the user is different, the weight of the wrinkle improvement coefficient of each position of the user is different. Specifically, the reflected light intensity of the user's face to the camera is different at different positions, and the light intensity will affect the shutter speed. The stronger the light, the faster the shutter speed, and the clearer the image taken. Similarly, the focus distance will also affect the clarity of the image. The focus distance between users at different positions and the focus point of the camera is different. The shorter the focus distance, the clearer the user's facial features. It can be seen that the greater the light intensity, the higher the image clarity, and the shorter the focus distance, the clearer the user's facial features.

[0052] The light intensity collected by the light intensity meter when taking the front face image of the user before makeup and the light intensity collected when taking the front face image of the user after makeup are taken as the light intensity coefficient of the front face image of the user, and the focus distance of the front face image of the user before makeup and the focus distance of the front face image of the user after makeup obtained by accessing the metadata of the camera are taken as the focus coefficient of the front face image of the user. Similarly, the light intensity coefficient of the side face image of the user, the focus coefficient of the side face image of the user, etc. are obtained.

[0053] Normalize the image light intensity coefficient at each position and the image focus coefficient at each position, and use linear normalization to map the light intensity to the interval [0,1], the formula is: Where X normis the normalized value. The normalization formula given here is a general formula. The process of normalizing the focus distance is consistent with the general formula and will not be described in detail here.

[0054] After normalizing the light intensity coefficient of each position image and the focus coefficient of each position image, they are recorded as g and d respectively, then the clarity score calculation formula of each position image can be Q(j)=gd. In the formula, Q(j) is the clarity score of each position image, and j represents the sequence number of each position image, such as the front face image is recorded as 1, the side face image is recorded as 2, the upward view image is recorded as 3, and the downward view image is recorded as 4.

[0055] After calculating the clarity scores of the images at each position, the clarity scores of each position are compared. Obviously, the greater the light intensity and / or the closer the focus distance, the higher the clarity of the image, the more accurate the wrinkle reflection, and the greater the clarity consideration weight. Specifically, the clarity scores of the images at each position are assigned clarity weights according to the priority diagram method as shown in Table 1 below:

[0056]

[0057] Table 1

[0058] It should be noted that in Table 1, positions A, B, C, and D correspond to four position images in this embodiment respectively. After sorting the position images according to the size of the clarity score, they correspond to positions A, B, C, and D in descending order.

[0059] The wrinkle variation coefficient G at each position of the user is weighted averaged according to the clarity weight value of each position to obtain the comprehensive wrinkle variation coefficient.

[0060] In step S4, the durability of the wrinkle improvement effect is also an important factor. Whether the effect of the cosmetics can last for a period of time can also reflect the wrinkle improvement effect of the cosmetics. The user's makeup holding time is confirmed through the page guidance, that is, the makeup time from the user's makeup to the time when the user's makeup is taken. The longer the user's makeup holding time is, the better the wrinkle improvement effect of the cosmetics is. After calculating the user's comprehensive wrinkle change coefficient, the user's comprehensive wrinkle change coefficient and makeup holding time are defined as input variables, and they are divided into different fuzzy sets.

[0061] For example, "High", "Normal", "Low" for the comprehensive wrinkle variation coefficient, and "Long", "Medium", "Short" for the user's makeup holding time.

[0062] Define the wrinkle improvement effect as the output variable and divide it into fuzzy sets, for example, “Good”, “Normal”, “Bad” for wrinkle improvement effect.

[0063] Formulate a set of fuzzy rules to describe the impact of different input variables on output variables. The definition of rules can be based on professional knowledge or obtained through data analysis. For example, if the comprehensive wrinkle variation coefficient is marked as BH, the makeup holding time is marked as CZ, and the wrinkle improvement effect is marked as GS, then it can be defined

[0064] Rule 1: IF(BH is High)AND(CZ is Long)THEN(GS is Good)

[0065] Rule 2: IF(BH is Low)AND(CZ is Short)THEN(GS is Bad) ...

[0067] Fuzzy reasoning is performed based on fuzzy rules to determine the solution for wrinkle improvement.

[0068] It should be noted that the division of fuzzy sets can be adjusted according to actual conditions, and the above division is not unique. Furthermore, the judgment of the comprehensive wrinkle change coefficient, medium, high and low, and the long, medium and short makeup holding time can be judged by setting thresholds according to actual conditions, which will not be elaborated here.

[0069] This design detects and classifies user images, calculates the wrinkle improvement coefficient of users before and after makeup through multi-angle images, and scores the clarity of user images at different positions by analyzing the factors affecting clarity. The weights are set according to the clarity scores, and finally the wrinkle improvement coefficients of users at different positions are combined through the weights. The final user wrinkle improvement coefficient is compared with the threshold to determine the wrinkle improvement effect of cosmetics. This greatly reduces the judgment error of cosmetics effects.

[0070] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0071] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0072] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0073] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0074] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0075] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for evaluating the wrinkle improvement effect of a cosmetic, characterized in that: The steps include: Step S1, collecting user images and the user's makeup-wearing time through image acquisition equipment and page guidance; using a light intensity meter to detect the light intensity when taking the image, and accessing the camera metadata to obtain the focus distance when taking the image; Step S2, classifying the user image into a frontal face image, a side face image, an upward-looking image, and a top-down image according to the shooting position, obtaining the facial data of the user at each position in the user image using an edge detection method, and calculating the wrinkle improvement coefficient at each position of the user according to the facial data at each position of the user and the makeup wearing time; Step S3, analyzing the clarity of the user image at each position by light intensity and focus distance, setting the weight of the wrinkle improvement coefficient at each position of the user according to the clarity of the user image at each position, and calculating the wrinkle change coefficient of the user; Step S4, judging the effect of the cosmetics according to the wrinkle variation coefficient of the user and the makeup wearing time of the user; In step S1, the user image includes a frontal face image of the user, a side face image of the user, an upward-looking image of the user, and an overhead-looking image of the user. A light intensity meter is placed on the image sensor of the camera to collect the light intensity when the image is taken, and metadata of the camera is accessed to obtain the focus distance of the image. In step S2, the product of the wrinkle length before makeup and the wrinkle depth before makeup in the user image at each position is used as the wrinkle degree coefficient of the user before makeup, and then the wrinkle length and wrinkle depth after makeup in the user image at each position are detected by edge detection method, and the product of the wrinkle length after makeup and the wrinkle depth after makeup at each position is used as the wrinkle degree coefficient of the user after makeup, and the wrinkle degree coefficient of the user before makeup and the wrinkle degree coefficient of the user after makeup at the corresponding position are subtracted to obtain the wrinkle variation coefficient of each position; In step S3, the illumination intensity when shooting the front face image of the user before makeup and the illumination intensity when shooting the front face image of the user after makeup collected by the light intensity meter are averaged as the light intensity coefficient of the front face image of the user, the focus distance of the front face image of the user before makeup and the focus distance of the front face image of the user after makeup obtained by accessing the metadata of the camera are averaged as the focus coefficient of the front face image of the user, and the light intensity coefficient of the side face image of the user and the focus coefficient of the side face image of the user are obtained in turn; Normalize the light intensity coefficient of each position image and the focus coefficient of each position image, calculate the clarity score of each position image by weighted calculation, and assign weights to the clarity scores of each position image according to the priority diagram method to determine the weight value of each position image; In step S3, the specific weighted calculation method is as follows: After normalizing the light intensity coefficient of each position image and the focus coefficient of each position image, they are recorded as g and d respectively. Then, the clarity score calculation formula of each position image is Q(j)=gd; where Q(j) is the clarity score of each position image, and j represents the sequence number of each position image; In step S3, after calculating the clarity score of the image at each position, the clarity scores of each position are compared, and the clarity weights of the clarity scores of the images at each position are assigned according to the priority diagram method. The wrinkle change coefficient G of each position of the user is weighted averaged according to the clarity weight value of each position to obtain the comprehensive wrinkle change coefficient.

2. A method for evaluating the wrinkle improvement effect of cosmetics according to claim 1, characterized in that: In step S2, the length and depth of wrinkles before makeup in the image of the user before makeup are detected using an edge detection method. The specific steps are as follows: Image preprocessing: first preprocess the collected user images; Edge detection: Use edge detection algorithms to detect edges in images; Contour extraction: extract contours from detected edges; Measure length and depth: Based on the extracted wrinkle contours.

3. A method for evaluating the wrinkle improvement effect of cosmetics according to claim 1, characterized in that: In step S4, after obtaining the user wrinkle variation coefficient and the user makeup holding time, the user wrinkle variation coefficient and the user makeup holding time are defined as input variables, and they are divided into different fuzzy sets respectively; The cosmetic effect is defined as the output variable and divided into fuzzy sets; Formulate fuzzy rules to describe the impact of the user's wrinkle variation coefficient and the user's makeup holding time definition on the cosmetics effect; Perform fuzzy reasoning based on fuzzy rules to determine the effect of cosmetics.

Citation Information

Patent Citations

  • Method and apparatus for realistic simulation of wrinkle aging and de-aging

    CN101755288A

  • Wrinkle detection method, wrinkle detection device and wrinkle detection program, as well as wrinkle evaluation method, wrinkle evaluation device and wrinkle evaluation program

    CN103827916A

  • Method and system for evaluating skin wrinkles in specified position

    CN108324247A

  • Test method for moistening capacity of skincare product for human skin

    CN108982759A

  • Wrinkle detection model training method, electronic equipment and storage medium

    CN112101185A