Skin evaluation and prediction method, device and equipment

Abstract

The invention relates to the technical field of skin assessment, in particular to a skin assessment and prediction method, device and equipment, and the method comprises the steps: firstly selecting sensitive areas for facial images of a user in different states, then detecting the sensitive areas of the facial images of the user in different states, and determining wrinkles of the user in different states. The wrinkles before the expression change of the user are static wrinkles, the wrinkles in the expression change of the user and the wrinkles after the expression change of the user are dynamic wrinkles, finally carrying out correlation detection on the wrinkles in different states of the user, and carrying out skin evaluation and prediction through a correlation detection result in combination with the static wrinkles and the dynamic wrinkles. The problem that the change of the skin under different expressions cannot be accurately reflected due to the lack of dynamic skin analysis at present is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of skin assessment, and in particular to a skin assessment and prediction method, device and equipment. Background Art

[0002] Current wrinkle detection lacks data on dynamic expressions and cannot objectively display changes in dynamic and static data. The existing technology only has static data on dynamic expressions, which are usually recorded by cameras and verified by subjective comparison. At the same time, the commonly used skin image analysis methods have problems such as incomplete information. The above problems are increasingly demanded by dermatologists and the beauty industry for accurate assessment of dynamic skin feature changes. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a skin assessment and prediction method, device and equipment to overcome the current problem of lack of dynamic analysis of the skin and inability to accurately reflect the changes in the skin under different expressions.

[0004] To achieve the above objectives, the present invention adopts the following technical solutions: On the first side, the present application provides a skin assessment and prediction method, comprising: Obtaining a facial image of the user before the expression changes, a facial image during the expression changes, and a facial image after the expression changes; Selecting a perceptual region in all the facial images, wherein the perceptual region is consistent under different expressions of the user; performing wrinkle detection on all said sensitive areas; Determining static wrinkles of the user based on wrinkle detection results in the perceptual area of ​​the facial image before the user's expression changes; Determining the dynamic wrinkles of the user through the wrinkle detection result of the perceptual area of ​​the facial image during the expression change of the user and the wrinkle detection result of the perceptual area of ​​the facial image after the expression change of the user; Performing correlation detection on the wrinkle detection results of the perceptual area of ​​the facial image before the user's expression changes, the wrinkle detection results of the perceptual area of ​​the facial image during the user's expression changes, and the wrinkle detection results of the perceptual area of ​​the facial image after the user's expression changes; The user's skin is evaluated and predicted based on the correlation detection result, the user's static wrinkles, and the user's dynamic wrinkles.

[0005] Furthermore, the method described above, wherein determining the static wrinkles of the user based on the wrinkle detection result of the perceptual area of ​​the facial image before the user's expression changes, comprises: The user's static wrinkle data is determined according to the wrinkle detection result of the perceptual area of ​​the facial image before the user's expression changes, and the user is marked with static wrinkles in the user's facial model according to the static wrinkle data.

[0006] Furthermore, the method described above, wherein determining the dynamic wrinkles of the user through the wrinkle detection results of the perceptual area of ​​the facial image during the user's expression change and the wrinkle detection results of the perceptual area of ​​the facial image after the user's expression change, comprises: Determining dynamic wrinkles in the user's expression change according to wrinkle detection results in the perceptual area of ​​the facial image in the user's expression change, and marking the dynamic wrinkles in the user's expression change in the user's facial model; According to the wrinkle detection result of the perceptual area of ​​the facial image after the user's expression changes, the dynamic wrinkles after the user's expression changes are determined, and the dynamic wrinkles after the user's expression changes are marked in the user's facial model.

[0007] Furthermore, in the method described above, the wrinkle detection result of the facial image perceptual area before the user's expression changes, the wrinkle detection result of the facial image perceptual area during the user's expression changes, and the wrinkle detection result of the facial image perceptual area after the user's expression changes are performed with correlation detection, including: Dividing the perceptual regions of all facial images of the user into a preset number of sub-regions; Using a sub-pixel DIC algorithm, the perceptual area before the user's expression changes, the perceptual area during the expression changes, and the perceptual area after the expression changes are matched, and a reverse Gauss-Newton algorithm is used for iterative optimization; By calculating the value of the normalized cross-correlation function as a criterion for judging the quality of the match, the deformation information of each sub-region in the perceptual region of the user's facial image is determined, and the correlation result corresponding to the static wrinkles is extracted; The user is marked in the user face model according to the correlation results corresponding to the static wrinkles.

[0008] Furthermore, the method described above, wherein the skin assessment and prediction of the user is performed based on the correlation detection result, the static wrinkles of the user, and the dynamic wrinkles of the user, comprises: Determine the wrinkle data of the user according to the correlation results corresponding to the static wrinkles in the user's facial model, the static wrinkles and the dynamic wrinkles, and determine the growth and development trend of the wrinkles on the user's skin surface through a calculation formula according to the wrinkle data of the user; Performing skin assessment and prediction on the user according to the wrinkle data of the user and the growth and development trend of wrinkles on the skin surface of the user; Wherein, the calculation formula is: ; Among them, W n (n=1,2,…n) are the prediction results of wrinkle growth trend in the perceptual area during and after expression changes, S n (n=1,2,…n) are the wrinkle detection results in the perceptual area during and after expression changes, C n (n=1,2,…n) are the results of the perceptual area correlation detection during and after the expression change.

[0009] Furthermore, the above method further includes: In combination with image processing and computer vision technology, the user's facial geometry and skin features are analyzed to determine the user's spot data, pore data and color spot data, and the growth and development trend of the user's skin surface spots, pores and color spots is determined based on the user's spot data, pore data and color spot data; Perform skin assessment based on the spot data, pore data and color spot data of the user; The user's skin is predicted based on the growth and development trends of the user's skin surface, spots, pores and pigmentation.

[0010] In a second aspect, the present application provides a skin assessment and prediction device, comprising: An image acquisition module is used to acquire a facial image of the user before the expression changes, during the expression changes, and after the expression changes; A region marking module, used for selecting a perceptual region in all the facial images, wherein the perceptual region is consistent under different expressions of the user; a wrinkle detection module, configured to perform wrinkle detection on all the perceptual areas, determine the static wrinkles of the user based on the wrinkle detection results of the perceptual areas of the facial image before the user's expression changes, and determine the dynamic wrinkles of the user based on the wrinkle detection results of the perceptual areas of the facial image during the user's expression changes and the wrinkle detection results of the perceptual areas of the facial image after the user's expression changes; The skin assessment and prediction module is used to perform correlation detection on the wrinkle detection results of the perceptual area of ​​the facial image before the user's expression changes, the wrinkle detection results of the perceptual area of ​​the facial image during the user's expression changes, and the wrinkle detection results of the perceptual area of ​​the facial image after the user's expression changes, and perform skin assessment and prediction on the user based on the correlation detection results, the user's static wrinkles, and the user's dynamic wrinkles.

[0011] In a third aspect, the present application provides a skin assessment and prediction device, including a processor and a memory, wherein the processor is connected to the memory: Wherein, the processor is used to call and execute the program stored in the memory; The memory is used to store the program, and the program is at least used to execute any one of the above skin assessment and prediction methods.

[0012] The beneficial effects of the present invention are: The present application first obtains facial images before, during and after a user's expression changes; selects perceptual areas in all facial images; performs wrinkle detection on all perceptual areas; determines the user's static wrinkles based on the wrinkle detection results of the perceptual areas of the facial images before the user's expression changes; determines the user's dynamic wrinkles based on the wrinkle detection results of the perceptual areas of the facial images during and after the user's expression changes; performs correlation detection on the wrinkle detection results of the perceptual areas of the facial images before the user's expression changes, the wrinkle detection results of the perceptual areas of the facial images during and after the user's expression changes; and performs skin assessment and prediction on the user based on the correlation detection results, the user's static wrinkles and the user's dynamic wrinkles. In the present application, firstly, the perceptual area of ​​the facial images of the user in different states is framed and selected, and then the perceptual area of ​​the facial images of the user in different states is detected to determine the wrinkles of the user in different states. The wrinkles before the user's expression changes are static wrinkles, and the wrinkles during the user's expression change and the wrinkles after the expression change are dynamic wrinkles. Finally, the wrinkles of the user in different states are detected for correlation, and the skin is evaluated and predicted by combining the correlation detection results with static wrinkles and dynamic wrinkles, which solves the current problem of lack of dynamic analysis of the skin and inability to accurately reflect the changes of the skin under different expressions. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0014] Figure 1 It is a flow chart provided by an embodiment of a skin assessment and prediction method of the present invention; Figure 2 It is a structural schematic diagram provided by an embodiment of a skin assessment and prediction device of the present invention; Figure 3 It is a structural schematic diagram provided by an embodiment of a skin assessment and prediction device of the present invention; Figure 4It is a wrinkle detection result diagram of a user in different states before and after the change provided by an embodiment of a skin evaluation and prediction method of the present invention; Figure 5 A wrinkle comparison diagram of a user's expression changes provided by an embodiment of a skin evaluation and prediction method of the present invention; Figure 6 A wrinkle comparison diagram after a user's expression changes provided by an embodiment of a skin evaluation and prediction method of the present invention; Figure 7 A wrinkle growth and development trend prediction diagram in user expression changes provided by an embodiment of a skin evaluation and prediction method of the present invention; Figure 8 A wrinkle growth trend prediction diagram after a user's expression changes is provided by an embodiment of a skin evaluation and prediction method of the present invention; Fig. 9 This is a correlation detection flow chart provided by an embodiment of a skin assessment and prediction method of the present invention.

[0015] Figure 5-Figure 8 In the figure, the green lines are dynamic wrinkles related to static wrinkles, and the purple lines are dynamic wrinkles. DETAILED DESCRIPTION

[0016] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0017] Figure 1 is a flowchart provided by an embodiment of a skin assessment and prediction method of the present invention. Figure 1 and Figure 4-Figure 8 , this embodiment may include the following steps: S1. Obtain a facial image of the user before expression changes, a facial image during expression changes, and a facial image after expression changes.

[0018] S2. Select the perceptual area in all facial images, where the perceptual area is consistent under different expressions of the user.

[0019] S3. Perform wrinkle detection on all sensitive areas.

[0020] S4. Determine the static wrinkles of the user based on the wrinkle detection result of the perceptual area of ​​the facial image before the user's expression changes.

[0021] S5. Determine the dynamic wrinkles of the user through the wrinkle detection results of the perceptual area of ​​the facial image during the user's expression change and the wrinkle detection results of the perceptual area of ​​the facial image after the user's expression change.

[0022] S6. Perform correlation detection on the wrinkle detection results of the perceptual area of ​​the facial image before the user's expression changes, the wrinkle detection results of the perceptual area of ​​the facial image during the user's expression changes, and the wrinkle detection results of the perceptual area of ​​the facial image after the user's expression changes.

[0023] S7. Perform skin assessment and prediction on the user based on the correlation detection results, the user's static wrinkles, and the user's dynamic wrinkles.

[0024] It can be understood that the present embodiment first obtains facial images before the user's expression changes, facial images during the expression changes, and facial images after the expression changes; selects perceptual areas in all facial images; performs wrinkle detection on all perceptual areas; determines the user's static wrinkles based on the wrinkle detection results of the perceptual areas of the facial images before the user's expression changes; determines the user's dynamic wrinkles through the wrinkle detection results of the perceptual areas of the facial images during the user's expression changes and the wrinkle detection results of the perceptual areas of the facial images after the user's expression changes; performs correlation detection on the wrinkle detection results of the perceptual areas of the facial images before the user's expression changes, the wrinkle detection results of the perceptual areas of the facial images during the user's expression changes, and the wrinkle detection results of the perceptual areas of the facial images after the user's expression changes; and performs skin assessment and prediction on the user based on the correlation detection results, the user's static wrinkles, and the user's dynamic wrinkles. In the present application, firstly, the perceptual area of ​​the facial images of the user in different states is framed and selected, and then the perceptual area of ​​the facial images of the user in different states is detected to determine the wrinkles of the user in different states. The wrinkles before the user's expression changes are static wrinkles, and the wrinkles during the user's expression change and the wrinkles after the expression change are dynamic wrinkles. Finally, the wrinkles of the user in different states are detected for correlation, and the skin is evaluated and predicted based on the correlation detection results, combining static wrinkles and dynamic wrinkles, which solves the current problem of lack of dynamic analysis of the skin and inability to accurately reflect the changes of the skin under different expressions.

[0025] It should be noted that the selective sensitive area at least includes the forehead area, the eye corner area and the specific shooting area.

[0026] Static lines: usually refer to the fixed wrinkles on the facial skin, which are mainly caused by age, skin aging, sun exposure and other factors. These lines usually exist normally.

[0027] Dynamic lines: refers to the wrinkles or lines that appear when facial expressions change. These lines are caused by the contraction of facial muscles or changes in expression, and are related to muscle tension and activity.

[0028] Wrinkle prediction: refers to the process of speculating that dynamic wrinkles may gradually develop into static wrinkles under long-term facial expressions or facial muscle activities based on the appearance and development trend of dynamic wrinkles.

[0029] Preferably, step S4 comprises: According to the wrinkle detection result of the perceptual area of ​​the facial image before the user's expression changes, the user's static wrinkle data is determined, and the user's static wrinkle is marked in the user's facial model according to the static wrinkle data.

[0030] It can be understood that the static wrinkle detection before the expression change is recorded as S0, and the processed data is marked and mapped to the facial model to achieve an intuitive presentation of the static wrinkle quantitative analysis results.

[0031] Preferably, step S5 includes: Determine dynamic wrinkles in the user's expression change according to wrinkle detection results in the perceptual area of ​​the facial image during the user's expression change, and mark the dynamic wrinkles in the user's expression change in the user's facial model; According to the wrinkle detection result of the perceptual area of ​​the facial image after the user's expression changes, the dynamic wrinkles after the user's expression changes are determined, and the dynamic wrinkles after the user's expression changes are marked in the user's facial model.

[0032] It is understandable that if Figure 4 As shown, the user's dynamic wrinkles are marked with different colors in the user's facial model. By continuously displaying the marked facial models of the user in different states, the change process of wrinkles can be recorded and presented more intuitively. Figure 4 In the figure, S1 is the wrinkle detection result of the perceptual area of ​​the facial image before the expression changes, i.e., static wrinkles; S2 is the wrinkle detection result of the perceptual area of ​​the facial image during the expression changes, i.e., dynamic wrinkles during the expression changes; S3 is the wrinkle detection result of the perceptual area of ​​the facial image after the expression changes, i.e., dynamic wrinkles after the expression changes.

[0033] Preferably, step S6 comprises: Dividing the perceptual regions of all facial images of the user into a preset number of sub-regions; The sub-pixel DIC algorithm is used to match the perceptual area before, during and after the user's expression changes, and the reverse Gauss-Newton algorithm is used for iterative optimization. By calculating the value of the normalized cross-correlation function as a criterion for judging the quality of the match, the deformation information of each sub-region in the perceptual region of the user's facial image is determined, and the correlation results corresponding to the static wrinkles are extracted; Users are marked in the user face model based on the correlation results corresponding to static wrinkles.

[0034] It is understandable that if Figure 5-Figure 6 As shown, the correlation results corresponding to static wrinkles are mapped to the facial model, where Figure 5 A comparison chart of wrinkles during user expression changes. Figure 5 The middle left picture is a comparison of the coarse dynamic wrinkles during expression changes and the coarse static wrinkles before expression changes, and the right picture is a comparison of the fine dynamic wrinkles during expression changes and the fine static wrinkles before expression changes; Figure 6 This is a comparison chart of wrinkles after the user's expression changes. Figure 6 The left picture in the middle is a comparison of the coarse dynamic wrinkles after the expression change and the coarse static wrinkles before the expression change. The right picture is a comparison of the fine dynamic wrinkles after the expression change and the fine static wrinkles before the expression change, which realizes the intuitive presentation of dynamic display and quantitative analysis results. The wrinkle correlation detection in different states before and after the expression change is carried out on the perceptual area. In order to find the deformation of the subset, the extreme value of the correlation (cost) function is found. Two different correlation criteria are used to find the initial guess and its subsequent refinement. The initial guess is found by calculating the normalized cross-correlation at the integer position, so as to obtain the deformation information of each sub-region of the face. Finally, the perceptual area information during and after the expression change is extracted and recorded as C n (n=1,2,…n).

[0035] like Fig. 9 As shown, specify the calculation point P L 0 (x L 0 ,y L 0 ), in the reference state, a sub-pixel-based method is used to convert P L 0 (x L 0 ,y L 0 ) and P r 0 (x r 0 ,y r 0 ) is matched, and in the deformed state, P L 1 (x L 1 ,y L 1 ) and P r 1 (x r 1 ,y r 1) are matched. The inverse Gauss-Newton algorithm is used for iterative optimization, and the normalized cross-correlation is calculated at integer positions to find:

[0036] Here, f and g are the reference and current image grayscale intensity functions at the specified position (x, y), respectively. Functions fm and gm correspond to the average grayscale values ​​of the reference subset and the current subset:

[0037] where n(S) is the number of data points in subset S. Therefore, the initial guess produces u and v with integer (pixel) precision.

[0038] Preferably, step S7 includes: Determine the wrinkle data of the user according to the correlation results corresponding to the static wrinkles in the user's facial model, the static wrinkles and the dynamic wrinkles, and determine the growth and development trend of the wrinkles on the user's skin surface according to the wrinkle data of the user; The user's skin is evaluated and predicted based on the user's wrinkle data and the growth and development trend of wrinkles on the user's skin surface.

[0039] Preferably, it also includes: By combining image processing and computer vision technology, the user's facial geometry and skin features are analyzed to determine the user's spot data, pore data and color spot data, and the growth and development trend of the user's skin surface spots, pores and color spots is determined based on the user's spot data, pore data and color spot data; Perform skin assessment based on the user's spot data, pore data, and color spot data; Make skin predictions for users based on the growth and development trends of their skin surface, spots, pores and pigmentation.

[0040] It is understandable that if Figure 7-Figure 8 As shown, Figure 7 This is a prediction chart of the growth and development trend of wrinkles during facial expression changes. Figure 7 Static and dynamic wrinkle recognition, accurately assessing the length, width, depth and other quantitative changes of dynamic wrinkles during facial skin expression changes and static wrinkles before expression changes. Figure 8 This is a prediction chart of wrinkle growth and development trend after facial expression changes. Figure 8 Static and dynamic wrinkle recognition accurately evaluates the length, width, depth and other quantitative changes of dynamic wrinkles after facial expression changes and static wrinkles before expression changes. This solves the problem that traditional evaluation methods cannot evaluate the comprehensive quantitative information of wrinkles under expression.

[0041] According to the correlation results corresponding to the static wrinkles in the user's facial model, the static wrinkles and dynamic wrinkles are used to determine the growth and development trend of the wrinkles on the user's skin surface, which include original wrinkles, newly grown wrinkles and disappeared wrinkles, which are distinguished by different colors. The specific calculation is as follows:

[0042] W n (n=1,2,…n) are the prediction results of wrinkle growth trend in the perceptual area during and after expression changes, S n (n=1,2,…n) are the wrinkle detection results in the perceptual area during and after expression changes, C n (n=1,2,…n) are the results of the perceptual area correlation detection during and after the expression change.

[0043] Combining image processing and computer vision technology, high-precision dynamic and static analysis of multiple features of facial skin, such as geometric structure, spot density, pore diameter and depth, is performed to determine the data extraction and analysis of the possible growth and development trends of the characteristic points of wrinkles, spots, pores and spots on the user's skin surface, and to predict the user's skin. This makes the assessment of facial skin conditions more comprehensive and objective. By color-labeling the changes in wrinkle depth and morphology, combined with image stitching and texture mapping technology, an intuitive display of dynamic and static changes in facial skin is achieved. This provides a novel and objective way to evaluate skin.

[0044] Specifically, when extracting the growth and development trends of spots, pores and pigmentation, the same method as for wrinkles is adopted, that is, firstly obtaining images before, during and after the user's expression changes, and then detecting all images to determine the conditions of the spots, pores and pigmentation before, during and after the expression changes, and then performing correlation detection on the spots, pores and pigmentation in different states before, during and after the expression changes, and finally adopting the same calculation formula as for wrinkles to predict the growth trends of spots, pores and pigmentation.

[0045] It should be noted that the user's spot area, pore diameter, pore depth, density, area and color difference data of the spot are determined by analyzing the user's facial image.

[0046] The present invention also provides a skin assessment and prediction device for implementing the above method embodiment. Figure 2 FIG. 1 is a schematic diagram of a structure of an embodiment of a skin evaluation and prediction device according to the present invention. Figure 2 As shown, including: Image acquisition module 1, used to acquire the facial image of the user before the expression changes, the facial image during the expression changes, and the facial image after the expression changes; Region marking module 2, used to select the perceptual region in all facial images, where the perceptual region is consistent under different expressions of the user; Wrinkle detection module 3, used to perform wrinkle detection on all perceptual areas, determine the user's static wrinkles based on the wrinkle detection results of the perceptual areas of the facial image before the user's expression changes, and determine the user's dynamic wrinkles based on the wrinkle detection results of the perceptual areas of the facial image during the user's expression changes and the wrinkle detection results of the perceptual areas of the facial image after the user's expression changes; The skin assessment and prediction module 4 is used to perform correlation detection on the wrinkle detection results of the perceptual area of ​​the facial image before the user's expression changes, the wrinkle detection results of the perceptual area of ​​the facial image during the user's expression changes, and the wrinkle detection results of the perceptual area of ​​the facial image after the user's expression changes, and perform skin assessment and prediction on the user based on the correlation detection results, the user's static wrinkles, and the user's dynamic wrinkles.

[0047] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0048] The present invention also provides a skin assessment and prediction device for implementing the above method embodiment. Figure 3 FIG. 1 is a schematic diagram of a structure of an embodiment of a skin assessment and prediction device according to the present invention. Figure 3 As shown, the skin assessment and prediction device of this embodiment includes a processor 21 and a memory 22, and the processor 21 is connected to the memory 22. The processor 21 is used to call and execute the program stored in the memory 22; the memory 22 is used to store the program, and the program is at least used to execute the skin assessment and prediction method in the above embodiment.

[0049] The specific implementation scheme of the skin assessment and prediction device provided in the embodiments of the present application can refer to the implementation scheme of the skin assessment and prediction method in any of the above embodiments, which will not be repeated here.

[0050] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0051] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0052] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0053] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0054] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0055] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0056] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0057] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0058] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A skin assessment and prediction method, characterized in that: include: Obtaining a facial image of the user before the expression changes, a facial image during the expression changes, and a facial image after the expression changes; Selecting a perceptual region in all the facial images, wherein the perceptual region is consistent under different expressions of the user; performing wrinkle detection on all said sensitive areas; Determining static wrinkles of the user based on wrinkle detection results in the perceptual area of ​​the facial image before the user's expression changes; Determining the dynamic wrinkles of the user through the wrinkle detection result of the perceptual area of ​​the facial image during the expression change of the user and the wrinkle detection result of the perceptual area of ​​the facial image after the expression change of the user; Performing correlation detection on the wrinkle detection results of the perceptual area of ​​the facial image before the user's expression changes, the wrinkle detection results of the perceptual area of ​​the facial image during the user's expression changes, and the wrinkle detection results of the perceptual area of ​​the facial image after the user's expression changes; The user's skin is evaluated and predicted based on the correlation detection result, the user's static wrinkles, and the user's dynamic wrinkles.

2. The method according to claim 1, characterized in that The step of determining the static wrinkles of the user according to the wrinkle detection result of the perceptual area of ​​the facial image before the expression of the user changes comprises: The user's static wrinkle data is determined according to the wrinkle detection result of the perceptual area of ​​the facial image before the user's expression changes, and the user is marked with static wrinkles in the user's facial model according to the static wrinkle data.

3. The method according to claim 2, characterized in that The method of determining the dynamic wrinkles of the user by detecting the wrinkles in the perceptual area of ​​the facial image during the expression change of the user and the wrinkles in the perceptual area of ​​the facial image after the expression change of the user comprises: Determining dynamic wrinkles in the user's expression change according to wrinkle detection results in the perceptual area of ​​the facial image in the user's expression change, and marking the dynamic wrinkles in the user's expression change in the user's facial model; According to the wrinkle detection result of the perceptual area of ​​the facial image after the user's expression changes, the dynamic wrinkles after the user's expression changes are determined, and the dynamic wrinkles after the user's expression changes are marked in the user's facial model.

4. The method according to claim 3, characterized in that The performing correlation detection on the wrinkle detection result of the perceptual area of ​​the facial image before the user's expression changes, the wrinkle detection result of the perceptual area of ​​the facial image during the user's expression changes, and the wrinkle detection result of the perceptual area of ​​the facial image after the user's expression changes, comprises: Dividing the perceptual regions of all facial images of the user into a preset number of sub-regions; Using a sub-pixel DIC algorithm, the perceptual area before the user's expression changes, the perceptual area during the expression changes, and the perceptual area after the expression changes are matched, and a reverse Gauss-Newton algorithm is used for iterative optimization; By calculating the value of the normalized cross-correlation function as a criterion for judging the quality of the match, the deformation information of each sub-region in the perceptual region of the user's facial image is determined, and the correlation result corresponding to the static wrinkles is extracted; The user is marked in the user face model according to the correlation results corresponding to the static wrinkles.

5. The method according to claim 4, characterized in that The step of performing skin assessment and prediction on the user according to the correlation detection result, the static wrinkles of the user, and the dynamic wrinkles of the user includes: Determine the wrinkle data of the user according to the correlation results corresponding to the static wrinkles in the user's facial model, the static wrinkles and the dynamic wrinkles, and determine the growth and development trend of the wrinkles on the user's skin surface through a calculation formula according to the wrinkle data of the user; Performing skin assessment and prediction on the user according to the wrinkle data of the user and the growth and development trend of wrinkles on the skin surface of the user; Wherein, the calculation formula is: ； Among them, W n (n=1,2,…n) are the prediction results of wrinkle growth trend in the perceptual area during and after expression changes, S n (n=1,2,…n) are the wrinkle detection results in the perceptual area during and after expression changes, C n (n=1,2,…n) are the results of the perceptual area correlation detection during and after the expression change.

6. The method according to claim 5, characterized in that Also includes: In combination with image processing and computer vision technology, the user's facial geometry and skin features are analyzed to determine the user's spot data, pore data and color spot data, and the growth and development trend of the user's skin surface spots, pores and color spots is determined based on the user's spot data, pore data and color spot data; Perform skin assessment based on the spot data, pore data and color spot data of the user; The user's skin is predicted based on the growth and development trends of the user's skin surface, spots, pores and pigmentation.

7. A skin assessment and prediction device, characterized in that: include: An image acquisition module is used to acquire a facial image of the user before the expression changes, during the expression changes, and after the expression changes; A region marking module, used for selecting a perceptual region in all the facial images, wherein the perceptual region is consistent under different expressions of the user; a wrinkle detection module, configured to perform wrinkle detection on all the perceptual areas, determine the static wrinkles of the user based on the wrinkle detection results of the perceptual areas of the facial image before the user's expression changes, and determine the dynamic wrinkles of the user based on the wrinkle detection results of the perceptual areas of the facial image during the user's expression changes and the wrinkle detection results of the perceptual areas of the facial image after the user's expression changes; The skin assessment and prediction module is used to perform correlation detection on the wrinkle detection results of the perceptual area of ​​the facial image before the user's expression changes, the wrinkle detection results of the perceptual area of ​​the facial image during the user's expression changes, and the wrinkle detection results of the perceptual area of ​​the facial image after the user's expression changes, and perform skin assessment and prediction on the user based on the correlation detection results, the user's static wrinkles, and the user's dynamic wrinkles.

8. A skin assessment and prediction device, characterized in that The invention comprises a processor and a memory, wherein the processor is connected to the memory: Wherein, the processor is used to call and execute the program stored in the memory; The memory is used to store the program, and the program is at least used to execute the skin assessment and prediction method according to any one of claims 1-6.

Images