Facial aging detection method, system, electronic device and computer program product

Abstract

This application relates to the field of computer image processing, providing a method, system, electronic device, and computer program product for facial aging detection. The method includes: acquiring a three-dimensional facial model to be detected and a three-dimensional facial reference model of a target face; calculating quantitative facial feature data of the target face at multiple facial anatomical levels based on the three-dimensional facial model to be detected and the three-dimensional facial reference model; the multiple facial anatomical levels include the skin layer, muscle fascia layer, fat layer, and bony structure layer; and performing aging comparison analysis based on the quantitative facial feature data to determine the quantitative aging information of the target face at the multiple facial anatomical levels. This solution can comprehensively capture facial aging features from multiple anatomical structural dimensions, improving the comprehensiveness of facial aging detection.

Description

Technical Field

[0001] This application belongs to the field of computer image processing, and in particular relates to a facial aging detection method, system, electronic device, and computer program product. Background Technology

[0002] With the development of 3D imaging and computer image processing technologies, facial aging detection methods based on 3D models are gradually being applied in fields such as medical aesthetics and health management. 3D models, to some extent, overcome the limitations of 2D images, which can only reflect changes in facial texture and blemishes. However, existing 3D model-based facial aging detection methods can only capture superficial morphological changes such as facial depressions and sagging, resulting in a single dimension of detection and analysis. Summary of the Invention

[0003] This application provides a facial aging detection method, system, electronic device, and computer program product to solve the problem that existing facial aging detection methods based on three-dimensional models can only capture superficial morphological changes such as facial depressions and sagging, resulting in a single dimension of detection and analysis.

[0004] The first aspect of this application provides a method for detecting facial aging, including: Obtain the 3D facial detection model and 3D facial reference model of the target face; Based on the three-dimensional facial model to be detected and the three-dimensional facial reference model, the facial feature quantification data of the target face at multiple facial anatomical levels are calculated respectively; the multiple facial anatomical levels include the skin layer, muscle fascia layer, fat layer and bony structure layer; Based on the facial feature quantification data, an aging comparison analysis is performed to determine the aging quantification information of the target face at multiple facial anatomical levels.

[0005] A second aspect of this application provides a facial aging detection system, comprising: The acquisition module is used to acquire the 3D facial detection model and the 3D facial reference model of the target face; The calculation module is used to calculate the facial feature quantification data of the target face at multiple facial anatomical levels based on the three-dimensional facial detection model and the three-dimensional facial reference model; the multiple facial anatomical levels include the skin layer, muscle fascia layer, fat layer and bony structure layer; The determination module is used to perform aging comparison analysis based on the facial feature quantification data to determine the aging quantification information of the target face under multiple facial anatomical levels.

[0006] A third aspect of this application provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described in the first aspect.

[0007] A fourth aspect of this application provides a computer program product comprising a computer program that, when executed by a processor, implements the steps of the method described in the first aspect.

[0008] A fifth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described in the first aspect.

[0009] As can be seen from the above, this application obtains a three-dimensional facial model to be detected and a three-dimensional facial reference model of the target face. It calculates the quantitative data of facial features between the three-dimensional facial model to be detected and the three-dimensional facial reference model from multiple facial anatomical layers, including the skin layer, muscle fascia layer, fat layer and bone structure layer. Based on the quantitative data of facial features, it performs aging comparison analysis, which realizes the comprehensive capture of facial aging features from multiple anatomical structure dimensions and improves the comprehensiveness of facial aging detection. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a flowchart of a facial aging detection method provided in an embodiment of this application. Figure 1 ; Figure 2 This is a flowchart of a facial aging detection method provided in an embodiment of this application. Figure 2 ; Figure 3 This application provides a hierarchical, labeled, visualized aging face illustration. Figure 1 ; Figure 4 This application provides a hierarchical, labeled, visualized aging face illustration. Figure 2 ; Figure 5 This is a structural diagram of a facial aging detection system provided in an embodiment of this application; Figure 6This is a structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0012] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0013] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0014] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0015] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0016] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once [the described condition or event] is detected," or "in response to detection of [the described condition or event]."

[0017] In specific implementations, the terminals described in the embodiments of this application include, but are not limited to, other portable devices such as mobile phones, laptop computers, or tablet computers with touch-sensitive surfaces (e.g., touchscreen displays and / or touchpads). It should also be understood that in some embodiments, the device is not a portable communication device, but a desktop computer with touch-sensitive surfaces (e.g., touchscreen displays and / or touchpads).

[0018] The following discussion describes terminals that include displays and touch-sensitive surfaces. However, it should be understood that terminals may include one or more other physical user interface devices such as physical keyboards, mice, and / or joysticks.

[0019] The terminal supports a variety of applications, such as one or more of the following: drawing applications, presentation applications, word processing applications, website creation applications, disc burning applications, spreadsheet applications, game applications, telephone applications, video conferencing applications, email applications, instant messaging applications, exercise support applications, photo management applications, digital camera applications, digital camcorder applications, web browsing applications, digital music player applications, and / or digital video player applications.

[0020] Various applications that can run on the terminal can use at least one common physical user interface device, such as a touch-sensitive surface. One or more functions of the touch-sensitive surface and the corresponding information displayed on the terminal can be adjusted and / or changed between and / or within applications. In this way, the terminal's common physical architecture (e.g., the touch-sensitive surface) can support various applications with user interfaces that are intuitive and transparent to the user.

[0021] It should be understood that the sequence number of each step in this embodiment does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of this application embodiment.

[0022] To illustrate the technical solution described in this application, specific embodiments are provided below.

[0023] See Figure 1 , Figure 1 This is a flowchart of a facial aging detection method provided in an embodiment of this application. Figure 1 .like Figure 1 As shown, a facial aging detection method includes the following steps: Step 101: Obtain the 3D facial detection model and the 3D facial reference model of the target face.

[0024] The target face refers to the face that needs to be tested for aging.

[0025] The 3D facial detection model is a 3D model constructed based on the facial modeling data of the target human face in the detection stage.

[0026] The 3D facial baseline model is a reference model for comparison with the 3D facial model to be detected.

[0027] Three-dimensional facial baseline models serve as a benchmark for determining the degree of facial aging. Their construction must meet the requirements of stability and representativeness, and include the following types: individualized measured youthful state model (generated based on measured three-dimensional facial data of the same subject in a historical youthful state, a real control baseline model exclusively for the subject) and individualized ideal youthful state model (generated based on idealized youthful three-dimensional facial data obtained through algorithm deduction and optimization fitting based on the same subject's own facial anatomy and morphological characteristics, a standardized control baseline model exclusively for the subject).

[0028] In some embodiments, a three-dimensional facial model to be detected is constructed using a three-dimensional scanning device, such as a three-dimensional structured light scanner, a laser scanner, or a binocular vision imaging device.

[0029] In some embodiments, the three-dimensional facial reference model can be retrieved from a preset model library or constructed specifically using a method for constructing a three-dimensional facial model to be detected.

[0030] The three-dimensional facial detection model and facial baseline model overcome the technical limitations of two-dimensional images, which can only reflect changes in the surface texture of the face and cannot capture the three-dimensional spatial structural deformation of the face. This provides reliable three-dimensional data support for subsequent precise quantitative detection and structured comparative analysis of facial aging.

[0031] In some embodiments, obtaining the three-dimensional facial detection model of the target face includes: acquiring three-dimensional point cloud data of the target face; and constructing the three-dimensional facial detection model based on the three-dimensional point cloud data.

[0032] 3D point cloud data is a dataset composed of a large number of discrete points with spatial 3D coordinate information (x, y, z). The higher the point density, the higher the accuracy of facial 3D structure reconstruction.

[0033] In some embodiments, three-dimensional scanning devices such as three-dimensional structured light scanners, laser scanners, and binocular vision imaging devices are used to collect high-density three-dimensional point cloud data and other facial modeling data of the target face. During the collection process, the collection environment needs to be controlled (avoiding direct strong light and occlusion), and the target face should be guided to maintain a natural and relaxed expression. The collection range should cover the entire face and jawline area to ensure the integrity of the collected point cloud data, reduce redundant noise, and avoid affecting the accuracy of model construction due to occlusion or changes in expression.

[0034] In some embodiments, the acquired 3D point cloud data is preprocessed. The preprocessing operations include noise removal (removing redundant and interfering points generated during the acquisition process), point cloud smoothing (optimizing the uniformity of point cloud distribution), and point cloud registration (if the data is acquired in different regions, multiple sets of point cloud data need to be fused and aligned).

[0035] In some embodiments, Poisson reconstruction, Delaunay triangulation and other 3D modeling algorithms are used to reconstruct surfaces from preprocessed 3D point cloud data to generate a 3D facial detection model that can accurately map the 3D structure of the target face.

[0036] Accurate acquisition of 3D point cloud data and construction of 3D models ensure the authenticity and accuracy of the 3D facial model to be detected, avoiding subsequent aging analysis errors caused by missing data or model distortion.

[0037] Step 102: Based on the three-dimensional facial model to be detected and the three-dimensional facial reference model, calculate the facial feature quantification data of the target face at multiple facial anatomical levels; the multiple facial anatomical levels include the skin layer, muscle fascia layer, fat layer and bony structure layer.

[0038] Facial anatomical layers refer to the different structural layers of facial tissue from the surface to the deep layers.

[0039] In some embodiments, the facial anatomical hierarchy includes a skin layer, a muscle fascia layer, a fat layer, and a bony structure layer. The skin layer corresponds to skin aging (manifested as "loose"), the muscle fascia layer corresponds to flesh aging (manifested as "sagging"), the fat layer corresponds to lipid aging (manifested as "concave"), and the bony structure layer corresponds to bone aging (manifested as "sunken").

[0040] Facial feature quantification data refers to the quantitative indicators of the structural differences between each facial anatomical level of the three-dimensional facial detection model used to characterize the target human face and the corresponding level of the three-dimensional facial benchmark model.

[0041] In some embodiments, the 3D facial model to be detected is spatially registered with the 3D facial reference model. According to preset anatomical structure division rules, the 3D feature regions corresponding to the skin layer, muscle fascia layer, fat layer, and bony structure layer are located and divided on the aligned models, clarifying the data calculation and comparison range for each layer. For each layer, the geometric parameter differences between the feature regions in the 3D facial model to be detected and the feature regions in the 3D facial reference model are calculated one by one, generating and outputting quantitative facial feature data of the target face at each facial anatomical layer.

[0042] By calculating facial feature quantification data in a layered manner, changes in the face at various levels, such as the skin layer, muscle fascia layer, fat layer, and bony structure layer, can be accurately captured. This effectively avoids the problems of traditional aging detection, such as strong subjectivity, reliance on human experience, and large deviations in evaluation results, and achieves the objective and quantitative extraction of facial aging-related data.

[0043] In some embodiments, the step of calculating the facial feature quantization data of the target face at multiple facial anatomical levels based on the three-dimensional facial detection model and the three-dimensional facial reference model includes: spatially registering the three-dimensional facial detection model and the three-dimensional facial reference model; after spatial registration, determining at least one first feature region and at least one second feature region corresponding to each facial anatomical level from the three-dimensional facial detection model and the three-dimensional facial reference model; the first feature region and the second feature region of each facial anatomical level are in one-to-one correspondence; calculating the geometric quantization value between at least one first feature region and the corresponding second feature region corresponding to each facial anatomical level to obtain the facial feature quantization data of the target face at multiple facial anatomical levels.

[0044] Spatial registration refers to adjusting the spatial pose of the 3D facial model to be detected and the 3D facial reference model so that the corresponding anatomical structures (especially bony stable structures) of the two models are precisely aligned, eliminating spatial position deviations caused by differences in acquisition angle and head posture, and ensuring the accuracy of subsequent feature region comparison.

[0045] The first feature region refers to a specific region corresponding to a certain facial anatomical level that is divided from the three-dimensional facial model to be detected after spatial registration.

[0046] The second feature region refers to a specific region that is divided from the three-dimensional facial reference model after spatial registration and corresponds one-to-one with the first feature region. The anatomical location and extent of this region are consistent with the corresponding first feature region.

[0047] The three-dimensional facial model to be detected and the three-dimensional facial reference model are composed of triangular mesh surfaces, and the first feature region and the second feature region are both triangular mesh surfaces.

[0048] Geometric quantization values ​​are numerical values ​​used to characterize the differences in three-dimensional geometric structure between the first and second feature regions. The selection of geometric quantization values ​​for different anatomical levels should be consistent with the aging characteristics of that level to ensure that the quantification data can accurately reflect the aging changes at that level. For example, the muscle fascia layer focuses on displacement parameters, while the fat layer and bony structure layer focus on volume-related parameters.

[0049] In some embodiments, a stable bony structure region in the model is selected as a registration reference benchmark, and the three-dimensional facial model to be detected is spatially registered with the three-dimensional facial reference model to correct the posture and position deviations generated during the acquisition and construction process.

[0050] The bony structural stability region refers to the region whose geometric position remains stable during facial expression changes and soft tissue deformation. Preferably, this includes the brow ridge, orbital rim, nasal bone, and zygomatic arch. These regions are less affected by aging and can provide a stable reference for registration.

[0051] In some embodiments, the Iterative Closest Point (ICP) algorithm or an improved ICP algorithm is used to perform the registration operation. First, feature points of the stable bony structures in the two models are extracted. The spatial coordinates of the model to be detected are adjusted through iterative optimization to ensure that the stable bony structures of the two models are accurately aligned. The registration error is controlled within a preset threshold (e.g., 0.1 mm) to ensure the accuracy and effectiveness of subsequent feature region comparison.

[0052] In the two registered 3D models, the feature regions corresponding to each facial anatomical level are identified.

[0053] In some embodiments, an automatic segmentation algorithm based on anatomical structure can be combined with manual correction to ensure the accuracy of feature region segmentation. Specifically, the skin layer can select areas prone to sagging and fine lines, such as the periorbital region, forehead, nasolabial folds, and mandibular margin, as feature regions; the muscle fascia layer can select fascia aggregation areas such as the masseter, temporalis, and orbicularis oculi muscles as feature regions; the fat layer can select areas prone to atrophy or displacement, such as the malar fat pad and nasolabial fat pad; and the bony structure layer can select key bony support areas such as the brow ridge, orbital margin, nasal bone, zygomatic arch, and mandible as feature regions.

[0054] Each anatomical level needs to be divided into at least one feature region, and the first feature region in the three-dimensional facial model to be detected corresponds one-to-one with the second feature region in the three-dimensional facial reference model, with the region range and anatomical position being completely matched.

[0055] In some embodiments, for each anatomical level, the geometric quantization value between each first feature region and the corresponding second feature region of the corresponding level is calculated to obtain facial feature quantization data corresponding to each facial anatomical level.

[0056] In some embodiments, calculating the geometric quantization values ​​between at least one first feature region and the corresponding second feature region corresponding to each of the facial anatomical levels to obtain the facial feature quantization data of the target face under multiple facial anatomical levels includes: calculating first feature quantization data representing surface geometric changes between each first feature region and the corresponding second feature region corresponding to the skin layer, as the facial feature quantization data corresponding to the skin layer; calculating second feature quantization data representing gravitational displacement between each first feature region and the corresponding second feature region corresponding to the muscle fascia layer, as the facial feature quantization data corresponding to the muscle fascia layer; and calculating third feature quantization data representing deep geometric changes between each first feature region and the corresponding second feature region corresponding to the fat layer and the bony structure layer, as the facial feature quantization data corresponding to the fat layer and the bony structure layer.

[0057] Among them, the surface geometric changes of the skin layer focus on the changes in the geometric shape and texture attributes of the skin surface, and at its core reflect the surface morphological changes such as the formation of fine lines, wrinkles, and sagging caused by skin aging. Its quantification needs to be achieved through targeted surface geometric parameters (such as the amount of curvature change, the amount of normal vector dispersion change, and the amount of gradient change). The gravitational displacement of the muscle fascia layer focuses on the positional shift of the gravitational direction caused by the weakening of the mechanical support capacity of the muscle fascia layer and its associated soft tissues. It at its core reflects the "sagging" characteristic of flesh aging. Its quantification needs to be completed through specific displacement parameters, namely the gravitational displacement value. The deep geometric changes of the fat layer and the bony structure layer focus on the changes in the spatial arrangement, volume and other geometric attributes of the deep facial support tissues. It at its core reflects the volume loss and structural displacement caused by fat aging (fat atrophy and depression) and bone aging (bone resorption and indentation). Its quantification needs to be achieved through deep tissue-related geometric parameters (such as the amount of distance change, the amount of surface area change, and the amount of volume change).

[0058] The change in curvature is a numerical value that characterizes the change in the degree of curvature of the face. Skin aging is manifested by the formation of fine lines and wrinkles on the skin surface, as well as the sudden change in curvature caused by sagging and wrinkles. The change in curvature is a geometric parameter that characterizes the degree of change in the curvature of the surface.

[0059] The change in normal vector dispersion is a numerical value characterizing the difference in the uniformity of the distribution of facial normal vectors. The change in normal vector dispersion is used to assess skin aging because skin aging causes a decrease in the elasticity of the skin surface, leading to sagging and wrinkles. This causes irregular deformation of the originally regular skin surface, resulting in a significant decrease in the uniformity of the spatial distribution of normal vectors. This indicator can sensitively capture this change in the degree of distribution disorder, achieving a quantitative characterization of skin laxity and fine lines, characteristic of skin aging.

[0060] Gradient change is a numerical value representing the change in the gradient of facial contour undulations. Gradient change is used to assess skin aging because skin aging leads to changes such as increased fine lines and surface roughness in the skin surface, resulting in changes in the steepness and gradient distribution characteristics of the skin surface contour undulations. Gradient change can sensitively capture such gradient changes in surface texture, achieving effective quantification of skin roughness, fine lines, and other skin aging characteristics.

[0061] The displacement value in the direction of gravity represents the amount of facial positional shift in the direction of gravity (including direction and magnitude; direction is downward due to gravity, and magnitude is the displacement distance). The displacement value in the direction of gravity is used to characterize the aging of the muscle and fascia layer because the core of facial aging is the weakening of soft tissue mechanical support, leading to gravitational sagging.

[0062] The change in distance is a numerical value representing the change in facial spatial distance. This change in distance is used to characterize the aging of the fat and bony structures because local depressions caused by fat aging and deep indentations caused by bony aging directly alter the spatial spacing at corresponding points. This indicator can intuitively quantify the degree of deformation resulting from structural displacement and volume loss.

[0063] The change in surface area is a numerical value representing the change in the surface area of ​​the face. The change in surface area is used to characterize the aging of the fat layer and the bony structure layer because the local depressions caused by the aging of the fat layer and the deep indentations caused by the aging of the bone layer directly lead to changes in the surface area of ​​the characteristic areas. This indicator can quantify the surface area differences caused by such structural deformation.

[0064] Volume change is a quantitative value characterizing the increase or decrease in the three-dimensional volume of the face. Volume change is used to characterize the aging of the fat layer and the bony structure layer because the atrophy of the fat pads due to lipid aging and the resorption of the bony structure due to bone aging both cause local volume loss. This indicator can directly quantify the degree of core volume change.

[0065] In some embodiments, each first feature region and its corresponding second feature region are referred to as a set of feature regions.

[0066] In some embodiments, for each first feature region and its corresponding second feature region at the skin layer level, core indicators characterizing surface geometric changes, such as curvature change, normal vector dispersion change, and gradient change, are calculated respectively. Specifically, the curvature change is obtained by subtracting the curvature of each group of feature regions in the two models; the normal vector dispersion within each feature region is determined, and the normal vector dispersion change is obtained by subtracting the normal vector dispersion of each group of feature regions in the two models; the gradient change is obtained by calculating the difference in gradient magnitude between each group of feature regions in the two models.

[0067] In some embodiments, multiple indicators such as curvature change, normal vector dispersion, and gradient change of each group of feature regions are normalized and converted into values ​​in the range of 0-1. Then, they are weighted and summed according to preset weights (such as curvature change weight 0.4, normal vector dispersion weight 0.3, and gradient change weight 0.3) to obtain the first feature quantification data of the three-dimensional facial model under the skin layer, that is, the facial feature quantification data corresponding to the first feature region of the skin layer. The larger the data, the more obvious the skin aging.

[0068] In some embodiments, for each first feature region and its corresponding second feature region at the muscle fascia layer level, the gravity direction is first determined (preset as a downward direction perpendicular to the horizontal plane, and the negative z-axis direction can be preset as the gravity direction in the coordinate system). Then, the gravity direction coordinate components of each feature region of the two models are extracted, and the difference of the gravity direction coordinate components of each group of feature regions is calculated to obtain the gravity direction displacement value (including direction and amplitude) that represents the gravity direction displacement. Finally, the second feature quantization data of the three-dimensional facial model to be detected at the muscle fascia layer level is obtained, which is the facial feature quantization data corresponding to the first feature region of the muscle fascia layer.

[0069] In some embodiments, for each first feature region and its corresponding second feature region in the two layers of fat layer and bony structure layer, core indicators characterizing deep geometric changes, such as distance change, surface area change, and volume change, are calculated. Specifically, the distance change is obtained by calculating the three-dimensional distance (e.g., three-dimensional Euclidean distance) between each group of feature regions in the two models; the surface area change is obtained by calculating the area of ​​each feature region in the two models and subtracting the areas of each group of feature regions; and the volume change is obtained by constructing a three-dimensional closed body at each feature region in the two models and calculating the volume of the three-dimensional closed body for each feature region and subtracting the volumes of each group of feature regions.

[0070] In some embodiments, multiple indicators such as distance change, surface area change, and volume change of each group of feature regions are normalized and converted into values ​​within the range of 0-1. These values ​​are then weighted and summed according to preset weights (e.g., volume change weight 0.5, distance change weight 0.25, surface area change weight 0.25) to obtain the third feature quantification data of the 3D facial model under the fat layer level, i.e., the facial feature quantification data corresponding to the first feature region of the fat layer, and the third feature quantification data of the 3D facial model under the bony structure layer level, i.e., the facial feature quantification data corresponding to the first feature region of the bony structure layer. The fat layer quantification data reflects the degree of depression due to lipid aging, while the bony structure layer quantification data reflects the degree of bone aging. Larger data indicates more pronounced aging, thus achieving layered quantification and differentiation of volume loss.

[0071] To address the differences in aging mechanisms across the four facial anatomical layers—skin (dermal phase), muscle and fascia (muscular phase), fat (lipid phase), and bony structure (bone phase)—differentiated quantitative indicators and calculation methods were employed to achieve precise quantification of aging characteristics at each layer, avoiding the problem that a single quantitative indicator cannot comprehensively reflect the aging state.

[0072] For hierarchical data calculations involving multiple quantitative indicators, the problem of differences in the magnitude of multiple indicators was solved by normalization and integration processing. The resulting comprehensive quantitative data, namely facial feature quantitative data, is convenient for subsequent threshold comparison and aging degree determination.

[0073] Step 103: Perform aging comparison analysis based on the facial feature quantification data to determine the aging quantification information of the target face under multiple facial anatomical levels.

[0074] Aging quantification information refers to the comprehensive quantitative results that characterize the aging status of each facial anatomical layer of a target person's face. It includes at least the presence of aging characteristics (whether aging exists at this level) and the degree of aging (the severity of aging). It is a precise description of the aging status of each layer, including the skin layer, muscle and fascia layer, fat layer, and bony structure layer.

[0075] Differentiated comparison rules are established for the skin layer, muscle fascia layer, fat layer, and bone structure layer. By comparing quantitative data of facial features with preset thresholds, the aging state is determined, ensuring the accuracy of the determination results.

[0076] Through comparative analysis, facial feature quantification data is transformed into aging quantification information carrying four phases of aging type and degree, enabling the stratification and grading of facial aging. This overcomes the limitations of existing technologies in aging assessment, such as subjectivity and inability to accurately distinguish aging levels and degrees, thus enhancing the diagnostic value of aging detection and providing a reference for the formulation of subsequent medical aesthetic intervention pathways.

[0077] In some embodiments, the aging quantification information includes the presence status of aging features and the degree of aging. The step of performing aging comparison analysis based on the facial feature quantification data to determine the aging quantification information of the target face under multiple facial anatomical levels includes: comparing the facial feature quantification data of at least one first feature region corresponding to each facial anatomical level with a level feature quantification threshold; and determining the presence status of aging features and the degree of aging of the first feature region based on the data comparison results.

[0078] In some embodiments, statistical analysis is performed based on a large amount of facial sample data (facial aging sample data and facial youthful sample data of different ages, skin types, and degrees of aging), and numerical standards are set for each facial anatomical level to determine the presence and degree of aging, so as to obtain the level feature quantification thresholds for each facial anatomical level, including skin layer feature quantification thresholds, muscle fascia layer feature quantification thresholds, fat layer feature quantification thresholds, and bony structure layer feature quantification thresholds.

[0079] Different aging levels (such as mild, moderate, and severe) are determined based on the difference between facial feature quantification data and hierarchical feature quantification thresholds.

[0080] For example, the difference between the quantitative data of facial features in the skin layer (dermal phase) and the quantitative threshold of the layer features can be set as follows: 0-0.3 indicates no obvious aging, 0.3-0.6 indicates mild aging, and above 0.6 indicates moderate to severe aging; the difference between the quantitative data of facial features in the muscle fascia layer (fleshy phase) and the quantitative threshold of the layer features can be set as follows: 0-0.5 indicates no obvious sagging, 0.5-1.0 indicates mild sagging, and above 1.0 indicates moderate to severe sagging.

[0081] In some embodiments, individualized threshold adjustment is supported to adapt to the differences in basic facial structure among different individuals.

[0082] In some embodiments, the facial feature quantization data of each first feature region of each facial anatomical level is compared with the level feature quantization threshold of that level to determine whether there is aging at the corresponding level. If aging at the corresponding level exists, the data difference between the two is further determined to determine the degree of aging (mild, moderate, or severe).

[0083] By setting preset hierarchical feature quantification thresholds, the existence and degree of aging can be accurately determined, transforming aging assessment from qualitative description to quantitative grading, thereby improving the objectivity and standardization of assessment results.

[0084] In some embodiments, for the first feature region corresponding to the fat layer and the bony structure layer, determining the presence status and degree of aging of the first feature region based on the data comparison results includes: if the facial feature quantification data of the first feature region is greater than the fat layer feature quantification threshold and less than or equal to the bony structure layer feature quantification threshold, then it is determined that the first feature region exhibits lipid aging, and the degree of lipid aging is determined based on the data difference between the facial feature quantification data and the fat layer feature quantification threshold; if the facial feature quantification data of the first feature region is greater than the bony structure layer feature quantification threshold, then it is determined that the first feature region exhibits bone aging, and the degree of bone aging is determined based on the data difference between the facial feature quantification data and the bony structure layer feature quantification threshold; wherein the bony structure layer feature quantification threshold is greater than the fat layer feature quantification threshold.

[0085] The fat layer feature quantification threshold is a threshold specifically used to determine whether the fat layer (lipophase aging) is aging and the degree of aging.

[0086] The quantification threshold for bony structural layer features is a threshold specifically used to determine whether aging exists in the bony structural layer (bone aging) and the degree of aging.

[0087] Both the fat layer and the bony structure layer exhibit volume changes. When their characteristic regions overlap, misjudgment of aging type can easily occur. This application achieves accurate differentiation between the two aging types by setting differentiated thresholds and formulating clear judgment rules.

[0088] The quantification threshold for the bony structure layer is higher than that for the fat layer. This is because the fat layer corresponds to the aging of the middle soft tissue lipid phase, resulting only in localized superficial volume loss and relatively small geometric quantification changes. The bony structure layer, on the other hand, corresponds to the aging of the deep supporting bone phase, characterized by deep contour collapse caused by bone resorption and remodeling. The magnitude of structural deformation and quantification data are significantly higher in this case. By setting gradient thresholds, the two types of aging can be accurately distinguished. For example, the threshold for the fat layer can be set to 0.3, and the threshold for the bony structure layer to 0.6.

[0089] In some embodiments, for a first feature region where the fat layer and the bony structure layer overlap, the corresponding facial feature quantification data is compared with thresholds from both layers: (1) If the facial feature quantification data is less than or equal to the fat layer feature quantification threshold, it is determined that the feature region has no fat phase aging or bone phase aging. (2) If the quantification threshold of the fat layer features < the quantification data of the facial features ≤ the quantification threshold of the bony structure layer features, it is determined that there is lipid aging in the feature area. The degree of aging is determined according to the difference between the quantification data of the facial features and the quantification threshold of the fat layer features (the larger the data difference, the more serious the lipid aging. For example, a data difference of 0-0.2 indicates mild lipid aging, and 0.2-0.3 indicates moderate lipid aging). (3) If the facial feature quantification data is greater than the bony structure layer feature quantification threshold, it is determined that there is bone aging in the feature area. The degree of aging is determined according to the data difference between the facial feature quantification data and the bony structure layer feature quantification threshold (the larger the data difference, the more serious the bone aging. For example, a data difference of 0-0.2 indicates mild bone aging, and a difference of more than 0.2 indicates moderate to severe bone aging).

[0090] By employing differentiated thresholds and judgment rules, the system achieves precise differentiation between lipid-phase aging and bone-phase aging, resolving the technical challenge of easily confusing aging in the fat layer and bone structure layer, and avoiding detection errors and the resulting deviations in intervention plans. Furthermore, determining the degree of aging based on data differences further improves the accuracy of aging grading.

[0091] In this embodiment, a three-dimensional facial model to be detected and a three-dimensional facial reference model of the target face are obtained. The facial feature quantification data between the three-dimensional facial model to be detected and the three-dimensional facial reference model are calculated from multiple facial anatomical layers, including the skin layer, muscle fascia layer, fat layer and bone structure layer. Based on the facial feature quantification data, an aging comparison analysis is performed, which realizes the comprehensive capture of facial aging features from multiple anatomical structure dimensions and improves the comprehensiveness of facial aging detection.

[0092] See Figure 2 , Figure 2 This is a flowchart of a facial aging detection method provided in an embodiment of this application. Figure 2 .like Figure 2 As shown, a facial aging detection method includes the following steps: Step 201: Obtain the 3D facial detection model and the 3D facial reference model of the target face.

[0093] The implementation process of this step is the same as that of step 101 in the aforementioned embodiments, and will not be repeated here.

[0094] Step 202: Based on the three-dimensional facial model to be detected and the three-dimensional facial reference model, calculate the facial feature quantification data of the target face at multiple facial anatomical levels; the multiple facial anatomical levels include the skin layer, muscle fascia layer, fat layer and bony structure layer.

[0095] The implementation process of this step is the same as that of step 102 in the aforementioned embodiments, and will not be repeated here.

[0096] Step 203: Perform aging comparison analysis based on the facial feature quantification data to determine the aging quantification information of the target face under multiple facial anatomical levels.

[0097] The implementation process of this step is the same as that of step 103 in the aforementioned embodiments, and will not be repeated here.

[0098] Step 204: Based on the mapping relationship between the quantitative aging information and the visualization identifiers at each of the facial anatomical levels, the target face is visualized to obtain a hierarchically labeled aging visualized face.

[0099] Visual identifiers are used to represent different facial anatomical levels and different degrees of aging. Color-coded identifiers are preferred, but they can be combined with text and numerical labels. Visual identifiers have fixed semantic correspondences to ensure the semantic consistency of the visualization results.

[0100] In some embodiments, skin aging areas are mapped to light blue, flesh aging areas to blue, fat aging areas to yellow, and bone aging areas to red.

[0101] In some embodiments, auxiliary text and numerical labels can be used to annotate the aging level of aging regions at each facial anatomical level. When the interactive cursor hovers over the corresponding aging region of the visualized aging face, a floating pop-up window is triggered to dynamically display the anatomical level, aging type, and aging level of the region. Simultaneously, the corresponding facial feature quantification data can be overlaid to display the region, achieving a collaborative visualization of color semantics and quantification information.

[0102] In some embodiments, the aging level of each aging region can be displayed in text form, such as when the cursor moves to the corresponding region.

[0103] Figure 3 This application provides a hierarchical, labeled, visualized aging face illustration. Figure 1 In practical applications, in hierarchical facial aging visualization, different levels of aging are typically represented by different colors. For example, green areas represent normal, aging-free areas; light blue areas represent skin aging; blue areas represent flesh aging; yellow areas represent fat aging; and red areas represent bone aging. Figure 3In this system, different levels of aging are represented using varying shades of gray. By overlaying different shades of gray, the system visually presents the overall distribution and cumulative effect of four types of aging—skin, flesh, fat, and bone—on the target face. Through the fusion visualization effect of multiple gray-level overlays, the system intuitively presents the distribution of the four types of aging on the entire face, helping users quickly grasp the overall contour and severity of facial aging.

[0104] Figure 4 This application provides a hierarchical, labeled, visualized aging face illustration. Figure 2 . Figure 4 A visual breakdown of the four phases of aging is provided, displaying each of the four types of aging independently and precisely corresponding to the "loose-sagging-depression" four-phase aging model of this application. The upper left face is specifically used to mark the skin aging area (18.24%), mainly distributed in areas prone to skin laxity and fine lines such as the forehead and periorbital region, quantifying the scope and proportion of skin aging. The upper right face is specifically used to mark the fat aging area (3.71%), concentrated in areas of fat pad atrophy / depression such as the cheekbone area and nasolabial folds, visually presenting the distribution of fat layer volume loss. The lower left face is specifically used to mark the flesh aging area (6.10%), mainly appearing in areas of soft tissue sagging such as the jawline and cheeks, accurately locating the gravitational sagging of the muscle fascia layer. The lower right face is specifically used to mark the bone aging area (3.07%), distributed in areas of bone structure absorption / collapse such as the brow bone and orbital rim, clearly identifying areas of insufficient bone support. Through the visualization of the four-phase aging stratification, the regional distribution and proportion of aging at each level of skin, muscle, fat, and bone can be accurately located and quantitatively assessed.

[0105] Through visualization, abstract quantitative data is transformed into intuitive, diagnostically meaningful visual images, generating hierarchical aging visualizations of the face. These images clearly present aging areas, types, and degrees of aging, allowing users to easily identify the aging status of different facial regions. For example, red areas indicate deep bony support issues, potentially requiring bone grafting or lifting; yellow areas suggest mid-layer fat atrophy, suitable for fat grafting or hyaluronic acid injections.

[0106] In some embodiments, the generated hierarchically labeled aging visualization faces are three-dimensional model files (supporting rotation and zoom viewing), and can be accompanied by an aging analysis report, which clearly defines the aging areas, aging degree and aging type at each level, providing intuitive support for the formulation of aging intervention programs.

[0107] In this embodiment, after determining the quantitative information of aging at each facial anatomical level, the abstract quantitative data is transformed into an intuitive visual model through visualization processing, realizing the hierarchical and visual presentation of facial aging, and further improving the readability of aging detection results.

[0108] See Figure 5 , Figure 5 This is a structural diagram of a facial aging detection system provided in an embodiment of this application. For ease of explanation, only the parts related to the embodiment of this application are shown.

[0109] The facial aging detection system 300 includes: an acquisition module 301, a calculation module 302, and a determination module 303.

[0110] The acquisition module 301 is used to acquire the three-dimensional facial detection model and the three-dimensional facial reference model of the target face.

[0111] The calculation module 302 is used to calculate the facial feature quantification data of the target face at multiple facial anatomical levels based on the three-dimensional facial detection model and the three-dimensional facial reference model; the multiple facial anatomical levels include the skin layer, muscle fascia layer, fat layer and bony structure layer.

[0112] The determination module 303 is used to perform aging comparison analysis based on the facial feature quantification data to determine the aging quantification information of the target face under multiple facial anatomical levels.

[0113] In some embodiments, the acquisition module is specifically used for: Collect the three-dimensional point cloud data of the target face; The three-dimensional facial detection model is constructed based on the three-dimensional point cloud data.

[0114] In some embodiments, the computing module is specifically used for: Spatial registration is performed on the three-dimensional facial model to be detected and the three-dimensional facial reference model; After spatial registration, at least one first feature region and at least one second feature region corresponding to each facial anatomical level are determined from the three-dimensional facial model to be detected and the three-dimensional facial reference model, respectively; the first feature region and the second feature region of each facial anatomical level correspond one-to-one. The geometric quantization values ​​between at least one first feature region and the corresponding second feature region corresponding to each of the facial anatomical levels are calculated respectively to obtain the facial feature quantization data of the target face under multiple facial anatomical levels.

[0115] In some embodiments, the computing module is further configured to: Calculate the first feature quantization data representing the surface geometric changes between each first feature region and the corresponding second feature region of the skin layer, and use it as the facial feature quantization data corresponding to the skin layer; Calculate the second feature quantization data representing the displacement in the direction of gravity between each first feature region and the corresponding second feature region corresponding to the muscle fascia layer, and use it as the facial feature quantization data corresponding to the muscle fascia layer; The third feature quantification data, which characterizes the deep geometric changes between each first feature region and the corresponding second feature region corresponding to the fat layer and the bony structure layer, is calculated respectively, and is used as the facial feature quantification data corresponding to the fat layer and the bony structure layer.

[0116] In some embodiments, the aging quantification information includes the presence of aging characteristics and the degree of aging, and the determining module is specifically used for: The facial feature quantization data of at least one first feature region corresponding to each facial anatomical level is compared with the level feature quantization threshold. Based on the data comparison results, the presence status of the aging characteristics and the degree of aging in the first feature region are determined.

[0117] In some embodiments, for the first characteristic region corresponding to the fat layer and the bony structure layer, the determining module is further configured to: If the facial feature quantification data of the first feature region is greater than the fat layer feature quantification threshold and less than or equal to the bony structure layer feature quantification threshold, then it is determined that there is lipid phase aging in the first feature region, and the degree of lipid phase aging is determined based on the data difference between the facial feature quantification data and the fat layer feature quantification threshold. If the facial feature quantification data of the first feature region is greater than the bony structure layer feature quantification threshold, then it is determined that there is bone aging in the first feature region, and the degree of aging of the bone aging is determined according to the data difference between the facial feature quantification data and the bony structure layer feature quantification threshold. The feature quantization threshold of the bony structure layer is greater than the feature quantization threshold of the fat layer.

[0118] In some embodiments, the system further includes a visualization processing module for: Based on the mapping relationship between the quantitative aging information and the visual identifiers at each of the aforementioned facial anatomical levels, the target face is visualized to obtain a hierarchically labeled aging visualized face.

[0119] The facial aging detection system provided in this application can implement all the processes of the above-described facial aging detection method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0120] Figure 6This is a structural diagram of an electronic device provided in an embodiment of this application. As shown in the figure, the electronic device 4 of this embodiment includes: at least one processor 40 ( Figure 6 (Only one is shown in the diagram), memory 41, and computer program 42 stored in said memory 41 and executable on said at least one processor 40, which, when executed, implements the steps in any of the above method embodiments.

[0121] The electronic device 4 can be a desktop computer, laptop, handheld computer, or cloud server, etc. The electronic device 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will understand that... Figure 6 This is merely an example of electronic device 4 and does not constitute a limitation on electronic device 4. It may include more or fewer components than shown, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0122] The processor 40 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0123] The memory 41 can be an internal storage unit of the electronic device 4, such as a hard disk or memory. The memory 41 can also be an external storage device of the electronic device 4, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 41 can include both internal and external storage units of the electronic device 4. The memory 41 is used to store the computer program and other programs and data required by the electronic device. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0124] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0125] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0126] Those skilled in the art will recognize that the units and algorithm steps of the various examples 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 implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0127] In the embodiments provided in this application, it should be understood that the disclosed systems / electronic devices and methods can be implemented in other ways. For example, the system / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of systems or units may be electrical, mechanical, or other forms.

[0128] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0129] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0130] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0131] The processes in the above-described embodiments can be implemented by a computer program product. When the computer program product is run on an electronic device, the electronic device executes the steps in the above-described method embodiments.

[0132] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for detecting facial aging, characterized in that, include: Obtain the 3D facial detection model and 3D facial reference model of the target face; Based on the three-dimensional facial detection model and the three-dimensional facial reference model, the facial feature quantification data of the target face at multiple facial anatomical levels are calculated respectively. The multiple facial anatomical layers include the skin layer, muscle fascia layer, fat layer, and bony structure layer; Based on the facial feature quantification data, an aging comparison analysis is performed to determine the aging quantification information of the target face at multiple facial anatomical levels.

2. The method according to claim 1, characterized in that, The process of obtaining the three-dimensional facial detection model of the target face includes: Collect the three-dimensional point cloud data of the target face; The three-dimensional facial detection model is constructed based on the three-dimensional point cloud data.

3. The method according to claim 1, characterized in that, Based on the three-dimensional facial detection model and the three-dimensional facial reference model, the facial feature quantification data of the target face at multiple facial anatomical levels are calculated, including: Spatial registration is performed on the three-dimensional facial model to be detected and the three-dimensional facial reference model; After spatial registration, at least one first feature region and at least one second feature region corresponding to each facial anatomical level are determined from the three-dimensional facial model to be detected and the three-dimensional facial reference model, respectively; the first feature region and the second feature region of each facial anatomical level correspond one-to-one. The geometric quantization values ​​between at least one first feature region and the corresponding second feature region corresponding to each of the facial anatomical levels are calculated respectively to obtain the facial feature quantization data of the target face under multiple facial anatomical levels.

4. The method according to claim 3, characterized in that, The step of calculating the geometric quantization value between at least one first feature region and the corresponding second feature region at each of the facial anatomical levels to obtain the facial feature quantization data of the target face at multiple facial anatomical levels includes: Calculate the first feature quantization data representing the surface geometric changes between each first feature region and the corresponding second feature region of the skin layer, and use it as the facial feature quantization data corresponding to the skin layer; Calculate the second feature quantization data representing the displacement in the direction of gravity between each first feature region and the corresponding second feature region corresponding to the muscle fascia layer, and use it as the facial feature quantization data corresponding to the muscle fascia layer; The third feature quantification data, which characterizes the deep geometric changes between each first feature region and the corresponding second feature region corresponding to the fat layer and the bony structure layer, is calculated respectively, and is used as the facial feature quantification data corresponding to the fat layer and the bony structure layer.

5. The method according to claim 3, characterized in that, The aging quantification information includes the presence and degree of aging features. The step of performing aging comparison analysis based on the facial feature quantification data to determine the aging quantification information of the target face at multiple facial anatomical levels includes: The facial feature quantization data of at least one first feature region corresponding to each facial anatomical level is compared with the level feature quantization threshold. Based on the data comparison results, the presence status of the aging characteristics and the degree of aging in the first feature region are determined.

6. The method according to claim 5, characterized in that, For the first characteristic region corresponding to the fat layer and the bony structure layer, determining the presence and degree of aging of the aging characteristics in the first characteristic region based on data comparison results includes: If the facial feature quantification data of the first feature region is greater than the fat layer feature quantification threshold and less than or equal to the bony structure layer feature quantification threshold, then it is determined that there is lipid phase aging in the first feature region, and the degree of lipid phase aging is determined based on the data difference between the facial feature quantification data and the fat layer feature quantification threshold. If the facial feature quantification data of the first feature region is greater than the bony structure layer feature quantification threshold, then it is determined that there is bone aging in the first feature region, and the degree of aging of the bone aging is determined according to the data difference between the facial feature quantification data and the bony structure layer feature quantification threshold. The feature quantization threshold of the bony structure layer is greater than the feature quantization threshold of the fat layer.

7. The method according to claim 1, characterized in that, After performing aging comparison analysis based on the facial feature quantification data to determine the aging quantification information of the target face at multiple facial anatomical levels, the method further includes: Based on the mapping relationship between the quantitative aging information and the visual identifiers at each of the aforementioned facial anatomical levels, the target face is visualized to obtain a hierarchically labeled aging visualized face.

8. A facial aging detection system, characterized in that, include: The acquisition module is used to acquire the 3D facial detection model and the 3D facial reference model of the target face; The calculation module is used to calculate the facial feature quantification data of the target face at multiple facial anatomical levels based on the three-dimensional facial detection model and the three-dimensional facial reference model. The multiple facial anatomical layers include the skin layer, muscle fascia layer, fat layer, and bony structure layer; The determination module is used to perform aging comparison analysis based on the facial feature quantification data to determine the aging quantification information of the target face under multiple facial anatomical levels.

9. An electronic device, characterized in that, The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device performs the method as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, Includes a computer program, which, when run, causes the method as described in any one of claims 1 to 7 to be performed.

Images