Spectacle fitting parameter determination method, device and equipment and readable storage medium

Abstract

The application discloses a spectacle fitting parameter determination method, device and equipment and a readable storage medium, relates to the technical field of optical design, and the spectacle fitting parameter determination method comprises the following steps: obtaining a three-dimensional digital head model of a target user, wherein the three-dimensional digital head model at least comprises continuous curved surface information of a nose bridge support area, bilateral behind-ear hanging point areas and bilateral spectacle leg contact areas of the target user; extracting key features in the three-dimensional digital head model, and constructing a spectacle fitting constraint based on the key features, wherein the key features at least comprise nose bridge key features and bilateral ear side key features, and the spectacle fitting constraint at least comprises a nose bridge support constraint and an ear hanging point path constraint; performing posture optimization on an original three-dimensional model of a candidate spectacle according to the spectacle fitting constraint, so as to obtain a target three-dimensional model of the candidate spectacle; and determining a spectacle fitting parameter of the candidate spectacle according to the target three-dimensional model and the three-dimensional digital head model. The application can accurately and efficiently determine the spectacle fitting parameter.

Description

Technical Field

[0001] This application relates to the field of optical design technology, and in particular to a method, apparatus, device, and readable storage medium for determining the fitting parameters of eyeglasses. Background Technology

[0002] In the field of eyeglasses fitting, accurately obtaining fitting parameters such as tilt angle, mirror angle, interpupillary distance, pupillary distance, and pupillary height is the foundation for achieving comfortable wearing and good optical correction.

[0003] Currently, common methods for obtaining prescription lens parameters mainly include manual measurement, estimation based on frontal two-dimensional images, and three-dimensional scan analysis covering only the anterior facial area. However, manual measurement relies on the experience of the optometrist, resulting in low efficiency in determining prescription lens parameters; estimation based on frontal two-dimensional images and three-dimensional scan analysis covering only the anterior facial area rely on incomplete head data, leading to poor accuracy in determining prescription lens parameters. Summary of the Invention

[0004] The main objective of this application is to provide a method, apparatus, device, and readable storage medium for determining eyeglass fitting parameters, with the aim of accurately and efficiently determining eyeglass fitting parameters.

[0005] This application provides a method for determining the fitting parameters of eyeglasses, the method comprising: Obtain a three-dimensional digital head model of the target user, wherein the three-dimensional digital head model includes at least the continuous curved surface information of the target user’s nose bridge support area, bilateral ear hook area and bilateral temple contact area; Key features are extracted from the three-dimensional digital head model, and eyeglass fitting constraints are constructed based on the key features. The key features include at least key features of the bridge of the nose and key features of both ears. The eyeglass fitting constraints include at least key features of the bridge of the nose and key features of both ears. Based on the eyeglass fitting constraints, the original 3D model of the candidate eyeglasses is subjected to pose optimization to obtain the target 3D model of the candidate eyeglasses; Based on the target 3D model and the 3D digital head model, determine the fitting parameters for the candidate glasses.

[0006] In one embodiment, the step of optimizing the pose of the original 3D model of the candidate glasses according to the lens fitting constraints to obtain the target 3D model of the candidate glasses includes: Based on the aforementioned eyeglass fitting constraints, an objective function is constructed, which includes at least a nasal bridge fit error term and an ear path deviation term; With minimizing the function value of the objective function as the optimization objective, the pose parameters of the original 3D model are iteratively optimized to obtain the target 3D model.

[0007] In one embodiment, the step of determining the fitting parameters of the candidate glasses based on the target 3D model and the 3D digital head model includes: Map the target 3D model to the coordinate system of the 3D digital head model; Based on the spatial geometric relationship between the mapped target 3D model and the 3D digital head model, the lens fitting parameters of the candidate glasses are determined; The fitting parameters include frame wearing posture parameters and / or optical alignment parameters. The frame wearing posture parameters are used to characterize the spatial posture of the candidate glasses on the target user's face, and the optical alignment parameters are used to characterize the alignment relationship between the optical center of the candidate glasses lens and the pupil of the target user.

[0008] In one embodiment, when the lens fitting parameters include the lens wearing posture parameters, the lens wearing posture parameters include forward tilt angle, lens angle and / or lens-to-eye distance; The step of determining the fitting parameters of the candidate glasses based on the spatial geometric relationship between the mapped target 3D model and the 3D digital head model includes: The forward tilt angle of the candidate glasses is determined based on the angle between the lens plane normal vector of the mapped target 3D model and the facial reference plane in the 3D digital head model. And / or, based on the angle between the left and right lens plane normal vectors of the mapped target 3D model in the top-view direction, determine the mirror angle of the candidate glasses; And / or, calculate the spatial distance from the lens plane of the mapped target 3D model to the corneal vertex in the 3D digital head model to obtain the lens-to-eye distance of the candidate glasses.

[0009] In one embodiment, when the lens fitting parameters include the optical alignment parameters, the optical alignment parameters include interpupillary distance and / or pupillary height; The step of determining the fitting parameters of the candidate glasses based on the spatial geometric relationship between the mapped target 3D model and the 3D digital head model includes: Based on the mapping position of the pupil center in the three-dimensional digital head model on the lens plane of the mapped target three-dimensional model, the interpupillary distance and / or pupil height corresponding to the candidate glasses are determined.

[0010] In one embodiment, the step of obtaining the three-dimensional digital head model of the target user includes: Acquire multi-view 3D scan data covering at least the frontal facial region and the bilateral behind-ear regions of the target user; The multi-view 3D scanning data is filtered, and the filtered multi-view 3D scanning data is registered to a preset coordinate system; Based on the registered multi-view 3D scan data, a 3D digital head model of the target user is constructed.

[0011] In one embodiment, prior to the step of extracting key features from the three-dimensional digital head model, the method further includes: Establish a wearing coordinate system on the three-dimensional digital head model; Based on the wearing coordinate system, the wearing reference geometric elements of the three-dimensional digital head model are established. The wearing reference geometric elements include at least the front support reference surface of the frame and the ear hook constraint path reference line of the temple. The front support reference surface of the frame provides a reference surface for the nose bridge support constraint to calculate the nose bridge fit, and the ear hook constraint path reference line of the temple constitutes the constraint target path of the ear hook point path constraint.

[0012] In one embodiment, the bilateral auricular key features include left auricular key features and right auricular key features; The step of optimizing the pose of the original 3D model of the candidate glasses based on the lens fitting constraints to obtain the target 3D model of the candidate glasses includes: Based on the key features of the left ear and the key features of the right ear, the left and right ear position difference information of the target user is determined; Based on the lens fitting constraints and the left and right ear position difference information, the original three-dimensional model of the candidate glasses is optimized for pose to obtain the target three-dimensional model of the candidate glasses.

[0013] In one embodiment, before the step of performing pose optimization on the original 3D model of the candidate glasses based on the lens fitting constraints, the method further includes: Based on the key features of the bridge of the nose and the key features of both ears, the original three-dimensional model of the candidate glasses is registered with the three-dimensional digital head model so that the nose pad area of ​​the original three-dimensional model is aligned with the bridge of the nose support area, and the temple path of the original three-dimensional model is aligned with the hanging point area behind both ears. After registering the original 3D model of the candidate glasses with the 3D digital head model, the step of optimizing the pose of the original 3D model of the candidate glasses according to the lens fitting constraints is performed.

[0014] Furthermore, to achieve the above objectives, this application also provides a device for determining the fitting parameters of eyeglasses, the device comprising: The digital head model acquisition module is used to acquire a three-dimensional digital head model of the target user. The three-dimensional digital head model includes at least the continuous curved surface information of the target user's nose bridge support area, the bilateral ear hook area, and the bilateral temple contact area. The feature extraction module is used to extract key features from the three-dimensional digital head model and construct eyeglass fitting constraints based on the key features. The key features include at least key features of the bridge of the nose and key features of both ears. The eyeglass fitting constraints include at least key features of the bridge of the nose and key features of both ears. The posture optimization module is used to optimize the posture of the original 3D model of the candidate glasses according to the lens fitting constraints, so as to obtain the target 3D model of the candidate glasses. The lens fitting parameter determination module is used to determine the lens fitting parameters of the candidate glasses based on the target 3D model and the 3D digital head model.

[0015] In addition, to achieve the above objectives, this application also provides an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the method for determining eyeglass fitting parameters as described above.

[0016] In addition, to achieve the above objectives, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for determining eyeglass fitting parameters as described above.

[0017] This application provides a method for determining the fitting parameters of eyeglasses, comprising: acquiring a three-dimensional digital head model of a target user, wherein the three-dimensional digital head model includes at least continuous surface information of the target user's nose bridge support area, bilateral ear hook point areas, and bilateral temple contact areas; extracting key features from the three-dimensional digital head model, and constructing fitting constraints based on the key features, wherein the key features include at least nose bridge key features and bilateral ear key features, and the fitting constraints include at least nose bridge support constraints and ear hook point path constraints; performing posture optimization on the original three-dimensional model of the candidate eyeglasses according to the fitting constraints to obtain a target three-dimensional model of the candidate eyeglasses; and determining the fitting parameters of the candidate eyeglasses based on the target three-dimensional model and the three-dimensional digital head model.

[0018] Therefore, the technical solution provided in this application obtains a three-dimensional digital head model containing complete surface information of at least the nose bridge support area, the bilateral ear hook point areas, and the bilateral temple contact areas. From this model, key features of the nose bridge and bilateral ear sides are extracted, and nose bridge support constraints and ear hook point path constraints are constructed to optimize the posture of the original three-dimensional model of the candidate glasses. This ensures that the frame posture optimization process is jointly constrained by the real geometric conditions of the nose bridge and ears, thereby reconstructing a target three-dimensional model in digital space that is highly consistent with the actual wearing state. Then, based on the precise spatial relationship between this target three-dimensional model and the digital head model, the fitting parameters of the candidate glasses can be accurately determined. Furthermore, the entire process from obtaining the three-dimensional digital head model to determining the fitting parameters is completed automatically, eliminating the need for repeated trial fittings and manual adjustments, thus effectively improving the efficiency of determining the fitting parameters.

[0019] In summary, the technical solution provided in this application can accurately and efficiently determine the fitting parameters of eyeglasses. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A flowchart illustrating the method for determining eyeglass fitting parameters provided in the first embodiment of this application; Figure 2 This is a schematic diagram of the structure of the three-dimensional scanning test system for the face and bilateral ear sides provided in the first embodiment of this application; Figure 3 A schematic diagram of the module structure of the eyeglass fitting parameter determination device provided in the embodiments of this application; Figure 4 This is a schematic diagram of the hardware operating environment involved in the embodiments of this application.

[0023] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0024] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0025] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0026] In the field of eyeglasses fitting, accurately obtaining fitting parameters such as tilt angle, mirror angle, interpupillary distance, pupillary distance, and pupillary height is the foundation for achieving comfortable wearing and good optical correction.

[0027] Currently, common methods for obtaining prescription lens parameters mainly include manual measurement, estimation based on frontal two-dimensional images, and three-dimensional scan analysis covering only the anterior facial area. However, manual measurement relies on the experience of the optometrist, resulting in low efficiency in determining prescription lens parameters; estimation based on frontal two-dimensional images and three-dimensional scan analysis covering only the anterior facial area rely on incomplete head data, leading to poor accuracy in determining prescription lens parameters.

[0028] Based on this, this application provides a method for determining the fitting parameters of eyeglasses, comprising: acquiring a three-dimensional digital head model of a target user, wherein the three-dimensional digital head model includes at least continuous surface information of the target user's nose bridge support area, bilateral ear hook point areas, and bilateral temple contact areas; extracting key features from the three-dimensional digital head model, and constructing fitting constraints based on the key features, wherein the key features include at least nose bridge key features and bilateral ear key features, and the fitting constraints include at least nose bridge support constraints and ear hook point path constraints; performing posture optimization on the original three-dimensional model of the candidate eyeglasses according to the fitting constraints to obtain a target three-dimensional model of the candidate eyeglasses; and determining the fitting parameters of the candidate eyeglasses based on the target three-dimensional model and the three-dimensional digital head model.

[0029] Therefore, the technical solution provided in this application obtains a three-dimensional digital head model containing complete surface information of at least the nose bridge support area, the bilateral ear hook point areas, and the bilateral temple contact areas. From this model, key features of the nose bridge and bilateral ear sides are extracted, and nose bridge support constraints and ear hook point path constraints are constructed to optimize the posture of the original three-dimensional model of the candidate glasses. This ensures that the frame posture optimization process is jointly constrained by the real geometric conditions of the nose bridge and ears, thereby reconstructing a target three-dimensional model in digital space that is highly consistent with the actual wearing state. Then, based on the precise spatial relationship between this target three-dimensional model and the digital head model, the fitting parameters of the candidate glasses can be accurately determined. Furthermore, the entire process from obtaining the three-dimensional digital head model to determining the fitting parameters is completed automatically, eliminating the need for repeated trial fittings and manual adjustments, thus effectively improving the efficiency of determining the fitting parameters.

[0030] In summary, the technical solution provided in this application can accurately and efficiently determine the fitting parameters of eyeglasses.

[0031] The subject executing the method for determining the fitting parameters of eyeglasses in this application can be an electronic device with data processing, network communication and program execution functions, but this embodiment does not specifically limit it.

[0032] The following description uses an electronic device as the execution subject to illustrate the various embodiments.

[0033] This application presents a method for determining eyeglass fitting parameters according to a first embodiment. Please refer to [link / reference]. Figure 1 The method for determining the prescription parameters for eyeglasses may include steps S10 to S40: Step S10: Obtain the three-dimensional digital head model of the target user. The three-dimensional digital head model includes at least the continuous curved surface information of the target user's nose bridge support area, the bilateral ear hook area, and the bilateral temple contact area. It should be noted that the target user is the user who is about to be fitted with glasses. A 3D digital head model refers to a 3D mesh model or point cloud model obtained through 3D scanning and reconstruction technology that reflects the geometry of the user's head, face, and ear areas. Continuous surface information means that each region in the 3D digital head model is presented as a continuous triangular patch or point cloud surface without breaks, which can realistically reflect the undulations and curvature changes of the corresponding anatomical regions. The nasal bridge support area refers to the anatomical area on the user's nasal bridge that contacts and supports the nose pads of the glasses frame, usually located on both sides of the middle of the nasal bridge. The bilateral postauricular hook area refers to the groove-like area behind the user's left and right auricles, at the junction of the ear root and the side of the skull; it is a key anatomical location for the hooking and support of the bent ends of the temples. The bilateral temple contact area refers to the strip-like area extending from the user's preauricular temporal region through the upper part of the auricle to the postauricular hook area; it is the potential path range for the temples to contact the sides of the head when worn. In practical use, the three-dimensional digital head model may also include binocular optical center reference areas, etc. This embodiment does not make specific limitations on this. The binocular optical center reference area refers to the three-dimensional spatial area where the pupil and corneal apex of the target user are located, which is used to provide optical reference for subsequently determining the position of the pupil center and the position of the corneal apex.

[0034] In one feasible implementation, step S10 may include steps S11 to S13: Step S11: Obtain multi-view 3D scan data covering at least the frontal facial area and the bilateral behind-the-ear areas of the target user; It should be noted that multi-view 3D scan data refers to 3D point cloud or depth image data obtained by collecting data from the same object from multiple different angles. While there are differences in the viewpoints between the data, the covered areas overlap, and these data are used for subsequent stitching to form a complete 3D model. The frontal facial region refers to the area corresponding to the target user's frontal face, which at least covers the bridge of the nose and the area around the eyes. The bilateral postauricular region refers to the area at the junction of the left and right auricles and the sides of the skull, including the anatomical location of the postauricular fossa.

[0035] When acquiring multi-view 3D scan data covering at least the frontal facial area and the bilateral behind-the-ear areas of the target user, at least three scanning modules can be used to simultaneously project structured light (which can be Gray code, phase-shifted fringes, sine fringes, or combinations thereof) from three directions: the frontal face, the left ear side, and the right ear side, and acquire depth images. The fields of view of each scanning module overlap in adjacent areas to ensure the feasibility of subsequent registration. Alternatively, a single scanning module can be used, acquiring depth images sequentially from multiple angles such as the front, left, and right sides via a mechanical rotation mechanism or handheld movement. During acquisition, the target user's head posture must remain unchanged. This embodiment does not specifically limit the implementation method of step S11.

[0036] In practical applications, a facial and bilateral auricular 3D scanning testing system can be constructed to acquire multi-view 3D scanning data. This facial and bilateral auricular 3D scanning testing system can be used for, for example... Figure 2 The structure shown may include: a top front scanning module, a left ear-side scanning module, a right ear-side scanning module, a bottom supplementary scanning module, a positioning support component, an optical projection component, an imaging component, an illumination component, a control and computing component, a display interactive terminal, and a frame database.

[0037] The top frontal scanning module is located directly above the target user and is used to collect 3D scan data of the target user's frontal face, bridge of the nose, eyes, and forehead. The left ear-side scanning module is mounted on the left movable arm or adjustable bracket and is used to collect 3D scan data of the target user's left auricle, left postauricular region, left temporal region, and potential support path area of ​​the left temple. The right ear-side scanning module is mounted on the right movable arm or adjustable bracket and is used to collect 3D scan data of the target user's right auricle, right postauricular region, right temporal region, and potential support path area of ​​the right temple. The bottom supplementary scanning module is located below or behind the target user and is used to supplement the collection of 3D scan data of the shadow area behind the ear, the jawline, and locally occluded areas.

[0038] The positioning support component may include a chin rest, forehead rest, or posture guide to stabilize the target user's head posture during scanning, thereby improving the consistency of 3D scan data from different viewpoints. The optical projection component projects a structured light pattern onto the measured area, which may include at least one of coded light, striped light, or sinusoidal stripes. The imaging component acquires image information reflected from the measured area; the imaging component may employ a dual-camera, binocular, or multi-camera simultaneous acquisition structure. The illumination component provides ring or directional supplemental lighting to reduce the impact of shadows on scan quality in the target user's postauricular and auricular retraction areas.

[0039] The control and calculation components are used to control the acquisition timing of each scanning module, and to complete the filtering, registration, fusion, and construction of the 3D digital head model of the multi-view 3D scanning data. They can also be used to execute relevant steps in the lens fitting parameter determination method provided in any embodiment of this application. The display and interactive terminal is used to display the scanning process, the determined lens fitting parameter results, and the virtual try-on effect of different candidate glasses. The frame database is used to store parametric 3D models, size information, and material properties of various candidate glasses.

[0040] Step S12: Filter the multi-view 3D scanning data and register the filtered multi-view 3D scanning data to a preset coordinate system; It should be noted that filtering can include identifying and removing noise points, outliers, and stray data that are clearly not part of the scanned object in multi-view 3D scanning data. The filtered multi-view 3D scanning data is then registered to a preset coordinate system. This involves calculating the spatial transformation relationship between multiple point cloud data collected from different perspectives to transform them into the same coordinate system, ensuring that the point cloud data are precisely aligned in space.

[0041] When filtering multi-view 3D scanning data and registering the filtered multi-view 3D scanning data to a preset coordinate system, a filtering algorithm based on neighborhood distance statistics can be used to remove outliers from the multi-view 3D scanning data. Then, the geometric features of each point cloud data in the multi-view 3D scanning data are extracted for coarse registration, and then a fine registration is performed using an iterative nearest-point algorithm to register the filtered multi-view 3D scanning data to the preset coordinate system. Alternatively, a filtering algorithm based on a radius threshold can be used to remove sparse points in the multi-view 3D scanning data where the number of neighboring points within a specified radius is less than a threshold. Then, using pre-pasted or projected marker points on the user's face as registration references, the transformation matrix between each viewpoint is calculated, and the filtered multi-view 3D scanning data is registered to the preset coordinate system accordingly. This embodiment does not specifically limit the implementation of step S12.

[0042] Step S13: Based on the registered multi-view 3D scan data, construct a 3D digital head model of the target user.

[0043] When constructing a 3D digital head model of a target user based on registered multi-view 3D scanning data, the registered multi-view 3D scanning data can be fused, hole repaired, meshed reconstructed, and smoothed to generate a 3D digital head model of the target user.

[0044] In this embodiment, firstly, multi-view 3D scan data covering at least the frontal and bilateral behind-the-ear regions of the target user's face is acquired to ensure the spatial integrity of the data required for subsequent modeling. Then, the multi-view 3D scan data is filtered to effectively remove noise interference and unify the scattered multi-view data under the same spatial reference frame. Subsequently, based on the registered multi-view 3D scan data, a 3D digital head model of the target user is constructed, resulting in a geometric model that can simultaneously reflect the complete surface information of the nasal bridge support area, the bilateral behind-the-ear hanging point area, and the bilateral temple contact area. This provides an accurate and complete 3D head and face data foundation for subsequent extraction of key features and construction of fitting constraints, thereby ensuring the accuracy of the subsequently determined fitting parameters.

[0045] Step S20: Extract key features from the 3D digital head model and construct eyeglass fitting constraints based on the key features. The key features include at least the key features of the bridge of the nose and the key features of both ears. The eyeglass fitting constraints include at least the bridge of the nose support constraints and the ear hanging point path constraints. It should be noted that key features refer to anatomical feature points or regions directly related to eyeglass wearing that are identified and located from the 3D digital head model. Key features of the bridge of the nose may include, but are not limited to, the apex of the bridge of the nose and / or the boundary of the nose pad contact area, etc., and this embodiment does not specifically limit them. Key features of both ears may include, but are not limited to, the root of the ear, the tragus, the highest point of the auricle and / or the transition point behind the ear, etc., and this embodiment does not specifically limit them. In actual use, key features may also include key features of the eyes (such as the center of the pupil, the outline of the brow bone, the outer contour of the cheekbone, etc.) and / or facial reference line features (such as the midline of the face, the horizontal reference line, the frame alignment reference line, etc.), etc., and this embodiment does not specifically limit them.

[0046] Additionally, it should be noted that lens fitting constraints refer to the geometric conditions used to limit the spatial relationship between the lens frame and the head and face during the lens frame posture optimization process. The nose bridge support constraint limits the fit between the nose pad area and the nose bridge support area of ​​the lens frame. The ear hook point path constraint limits the path matching relationship between the bent section of the temple and the ear hook point area of ​​the lens frame. In practical use, lens fitting constraints may also include optical alignment constraints, comfort constraints, and / or appearance constraints, etc. This embodiment does not specifically limit these. Specifically, the optical alignment constraint limits the relative positional relationship between the optical center of the candidate lens and the pupil center of the target user, so that the optical center of the lens meets the preset alignment accuracy requirements with the pupil center under the optimized wearing posture; the comfort constraint limits the force distribution state of the nose pad and nose bridge support area, and the temple and ear hook point area of ​​the candidate lens, so that the force on each contact area is within a preset comfort range under the optimized wearing posture; the appearance constraint limits the symmetry of the candidate lens relative to the midline of the target user's face and the proportional coordination relative to the brow bone and cheekbone contours under the optimized wearing posture.

[0047] When extracting key features from a 3D digital head model, curvature analysis can be performed on the surface of the 3D digital head model. The apex of the nose bridge and the boundary of the nose pad contact area can be located based on the Gaussian curvature and mean curvature features of the nose bridge region; the root of the ear and the transition point behind the ear can be located based on the groove-like surface features of the area behind the ear; and the tragus point and the highest point of the auricle can be located based on the protruding features of the auricle. Alternatively, a 2D rendering of the 3D digital head model can be input into a pre-trained 3D keypoint detection network, which outputs the coordinates of each key feature. This 3D keypoint detection network is trained using a large amount of 3D head model data with manually annotated key features as the training set.

[0048] The nose bridge support constraint can be configured to require that the gap between the nose pad surface of the frame and the nose bridge support area surface be less than a preset threshold; the ear hanging point path constraint can be configured to minimize the deviation between the spatial orientation of the temple bend and the hanging point path fitted to the ear hanging point area.

[0049] Step S30: Based on the lens fitting constraints, perform pose optimization on the original 3D model of the candidate glasses to obtain the target 3D model of the candidate glasses; It should be noted that the original 3D model of the candidate glasses refers to the initial 3D model of the frame to be evaluated before any adjustment of the wearing posture. This model may include, but is not limited to, the geometric information of components such as the lens rim, bridge, nose pads, temple base, temple bends, and temple ends. This embodiment does not impose specific limitations on this. Posture optimization refers to the process of adjusting the position and orientation of the original 3D model in 3D space to meet preset constraints. The target 3D model refers to the 3D model of the frame in digital space, after posture optimization, positioned at a location and angle corresponding to the user's actual wearing posture.

[0050] In one feasible implementation, step S30 may include S31~S32: Step S31: Based on the eyeglass fitting constraints, construct the objective function, which includes at least a nose bridge fit error term and an ear path deviation term; It should be noted that the objective function evaluates the degree of deviation between the current posture of the eyeglass frame and the ideal wearing posture. The nose bridge fit error term refers to the error component in the objective function used to measure the fit between the nose pad area of ​​the eyeglass frame and the nose bridge support area in the 3D digital head model; the greater the fit deviation, the larger the value of this error term. The ear path deviation term refers to the error component in the objective function used to measure the path deviation between the bent section of the temple of the eyeglass frame and the behind-the-ear hook point area in the 3D digital head model; the greater the path deviation, the larger the value of this error term. In practical applications, the objective function may also include an optical center deviation term, a left-right symmetry penalty term, and a comfort penalty term. This embodiment does not specifically limit these. The optical center deviation term refers to the error component in the objective function used to measure the alignment deviation between the optical center of the candidate glasses lens and the pupil center of the target user. The larger the deviation, the larger the value of the optical center deviation term. The left-right symmetry penalty term refers to the penalty component in the objective function used to measure the degree of left-right symmetry of the candidate glasses relative to the midline of the target user's face in the wearing posture. The greater the difference between the left and right postures, the larger the value of this penalty term. The comfort penalty term refers to the penalty component in the objective function used to measure the estimated pressure or penetration degree of the nose pads and temples of the candidate glasses on the contact area of ​​the target user in the wearing posture. The more concentrated the pressure or the deeper the penetration, the larger the value of this penalty term.

[0051] When constructing the objective function based on the eyeglass fitting constraints, we can first construct the nose bridge fit error term based on the nose bridge support constraint, and construct the ear side path deviation term based on the ear hanging point path constraint; then we can perform weighted fusion processing on the nose bridge fit error term and the ear side path deviation term to obtain the objective function.

[0052] Step S32: With minimizing the function value of the objective function as the optimization objective, the pose parameters of the original 3D model are iteratively optimized to obtain the target 3D model.

[0053] It should be noted that the pose parameters of the original 3D model refer to a set of parameters describing the position and orientation of the candidate glasses' original 3D model in 3D space. These typically include translational components along the X, Y, and Z coordinate axes and rotational components around these axes. Iterative optimization refers to the process of starting from initial pose parameters, repeatedly calculating the objective function value under the current pose, and updating the pose parameters based on its gradient or trend, gradually approaching the optimal pose that minimizes the objective function value.

[0054] When iteratively optimizing the pose parameters of the original 3D model with the goal of minimizing the objective function value, to obtain the target 3D model, the gradient of the objective function with respect to each pose parameter can be calculated. The pose parameters are then updated along the negative gradient direction with a preset step size. This process is repeated until the objective function value converges below a preset threshold or reaches a preset number of iterations. Alternatively, multiple candidate poses can be initialized as particles within the feasible space of the pose parameters. Each particle updates its search direction and velocity based on its own historical best position and the global best position of the group. After multiple iterations, the global best pose is used as the target 3D model. This embodiment does not specifically limit the implementation method of step S32.

[0055] In this embodiment, the lens fitting constraints are first quantified into an objective function that includes a nose bridge fit error term and an ear path deviation term, so that the quality of the lens frame wearing posture can be measured by a clear mathematical index. Then, the pose parameters are iteratively optimized with the goal of minimizing the function value of the objective function. This drives the lens frame posture to automatically adjust in digital space to the optimal state where the nose bridge fits well and the deviation between the temple path and the ear hook path is minimized. This ensures that the generated target 3D model can accurately reflect the spatial posture of the lens frame under the actual wearing conditions of the user's face, thus guaranteeing the accuracy of the lens fitting parameters determined subsequently.

[0056] This embodiment does not specifically limit the implementation of step S30. For example, in other feasible implementations, the original three-dimensional model of the candidate glasses can be optimized for posture using methods such as rule solving, constraint optimization, particle swarm optimization, genetic algorithms, machine learning regression models, or comfort models based on finite element approximation to obtain the target three-dimensional model of the candidate glasses.

[0057] Step S40: Determine the fitting parameters of the candidate glasses based on the target 3D model and the 3D digital head model.

[0058] It should be noted that the lens fitting parameters refer to a set of quantitative indicators that describe the spatial posture and optical center alignment of the glasses when they are actually worn on the user's face. These parameters may include, but are not limited to, tilt angle, mirror angle, lens-to-eye distance, pupillary distance and / or pupillary height. This embodiment does not make specific limitations on these parameters.

[0059] In one feasible implementation, step S40 may include steps S41-S42: Step S41: Map the target 3D model to the coordinate system of the 3D digital head model; It should be noted that mapping the target 3D model to the coordinate system of the 3D digital head model means transforming the target 3D model from its own model coordinate system to the coordinate system of the 3D digital head model through coordinate transformation, so that the two are in the same spatial reference system for subsequent measurement.

[0060] Step S42: Based on the spatial geometric relationship between the mapped target 3D model and the 3D digital head model, determine the fitting parameters of the candidate glasses; Among them, the lens fitting parameters include frame wearing posture parameters and / or optical alignment parameters. Frame wearing posture parameters are used to characterize the spatial posture of the candidate glasses on the target user's face, and optical alignment parameters are used to characterize the alignment relationship between the optical center of the candidate glasses lens and the target user's pupil.

[0061] It should be noted that spatial geometric relationship refers to the quantifiable geometric association between the mapped target 3D model and the 3D digital head model in a unified coordinate system. This may include, but is not limited to: the angle between a specific plane in the target 3D model and a specific plane in the 3D digital head model; the spatial distance between a specific plane in the target 3D model and a specific point in the 3D digital head model; and the projection position of a specific point in the 3D digital head model onto a specific plane in the target 3D model. Frame wearing posture parameters refer to a class of parameters in the lens fitting parameters used to characterize the spatial posture of the candidate glasses on the target user's face, reflecting spatial attributes such as the tilt angle, degree of coverage, and spatial distance of the frame relative to the user's face. Optical alignment parameters refer to a class of parameters in the lens fitting parameters used to characterize the alignment relationship between the optical center of the candidate glasses lens and the target user's pupil, reflecting the relative positional relationship between the optical center of the lens and the pupil on the lens plane.

[0062] In this embodiment, by mapping the target 3D model to the coordinate system of the 3D digital head model, the posture-optimized frame model and the user's head model are placed in a unified spatial reference system, providing a coordinate benchmark for the subsequent quantitative calculation of spatial geometric relationships. Then, based on the spatial geometric relationship between the two after mapping, the lens fitting parameters are determined separately as frame wearing posture parameters and optical alignment parameters. This makes the determination of lens fitting parameters no longer an independent and isolated measurement step, but rather an integrated derivation from the geometric relationship between the frame and the head and face in a unified coordinate system. This ensures both strict consistency between the lens fitting parameters and the posture optimization results, and allows the determined lens fitting parameters to comprehensively describe the wearing state of the candidate glasses on the target user's face from both spatial posture and optical alignment dimensions.

[0063] Furthermore, in a feasible implementation, when the lens fitting parameters include frame wearing posture parameters, the frame wearing posture parameters include forward tilt angle, lens angle, and / or lens-to-eye distance; step S42 may include steps S421~S423: Step S421: Determine the forward tilt angle of the candidate glasses based on the angle between the lens plane normal vector of the mapped target 3D model and the facial reference plane in the 3D digital head model. It should be noted that the facial reference plane refers to a reference plane determined on a 3D digital head model to characterize the overall orientation of the target user's face. It is typically fitted based on the facial midline, brow ridge, or forehead region, and represents the coronal plane orientation of the user's head in a natural, direct viewing posture. The lens plane normal vector is a unit direction vector perpendicular to the plane of the lens, used to characterize the lens's orientation in space. The tilt angle is the angle of inclination of the lens plane relative to the facial reference vertical plane (i.e., a plane perpendicular to both the facial reference plane and the ground), used to characterize the degree to which the glasses tilt forward when worn.

[0064] And / or, in step S422, the mirror angle of the candidate glasses is determined based on the angle between the normal vector of the left mirror plane and the normal vector of the right mirror plane of the mapped target 3D model in the top view direction. It should be noted that the left lens plane normal vector refers to the unit direction vector perpendicular to the plane containing the left lens ring, and the right lens plane normal vector refers to the unit direction vector perpendicular to the plane containing the right lens ring. The mirror angle refers to the enveloping angle formed by the left and right lens planes in the top-down view, used to characterize the degree of horizontal curvature of the front of the frame.

[0065] And / or, in step S423, calculate the spatial distance from the lens plane of the mapped target 3D model to the corneal vertex in the 3D digital head model to obtain the lens-to-eye distance of the candidate glasses.

[0066] It should be noted that the corneal apex refers to the most prominent point on the anterior surface of the cornea of ​​the target user, located in front of the center of the pupil. The lens-to-eye distance is the spatial distance from the posterior surface of the lens or the reference plane of the lens ring to the corneal apex, used to reflect the distance between the lens and the eyeball.

[0067] In another feasible implementation, when the lens fitting parameters include optical alignment parameters, the optical alignment parameters include pupillary distance and / or pupillary height; step S42 may include step S424: Step S424: Based on the mapping position of the pupil center in the 3D digital head model on the lens plane of the mapped target 3D model, determine the interpupillary distance and / or pupil height corresponding to the candidate glasses.

[0068] It should be noted that the pupil center refers to the geometric center point of the target user's pupil in three-dimensional space. The lens rim plane refers to the fitted plane defined by a single lens rim of the frame, used to characterize the spatial position of the lens within the frame. The pupillary distance is the horizontal distance between the centers of the left and right pupils, which can also be decomposed into the left monocular pupillary distance and the right monocular pupillary distance. The pupillary height is the vertical positional parameter of the pupil center relative to the lower edge of the frame or the lens rim baseline.

[0069] When determining the pupillary distance and pupillary height of candidate glasses based on the mapping position of the pupil center on the lens plane of the mapped target 3D model, the left pupil center and the right pupil center can be vertically projected onto the corresponding left lens plane and right lens plane, respectively. The pupillary distance is determined based on the horizontal distance between the two projection points, and the pupillary height is determined based on the vertical distance from the projection point to the lower edge of the frame.

[0070] This embodiment does not specifically limit the implementation of step S40. For example, in other feasible implementations, a mapping table of lens fitting parameters corresponding to different posture offsets can be established in advance. Thus, after obtaining the target 3D model, its offset relative to the initial pose can be calculated, and the corresponding lens fitting parameters can be quickly determined by looking up the table.

[0071] As described above, the technical solution provided in this embodiment acquires a three-dimensional digital head model containing complete surface information of at least the nose bridge support area, the bilateral ear hook point areas, and the bilateral temple contact areas. From this model, key features of the nose bridge and bilateral ear sides are extracted, and nose bridge support constraints and ear hook point path constraints are constructed to optimize the posture of the original three-dimensional model of the candidate glasses. This ensures that the frame posture optimization process is jointly constrained by the real geometric conditions of the nose bridge and ears, thereby reconstructing a target three-dimensional model in digital space that is highly consistent with the actual wearing state. Then, based on the precise spatial relationship between this target three-dimensional model and the digital head model, the fitting parameters of the candidate glasses can be accurately determined. Furthermore, the entire process from acquiring the three-dimensional digital head model to determining the fitting parameters is completed automatically, eliminating the need for repeated trial fittings and manual adjustments, thus effectively improving the efficiency of determining the fitting parameters.

[0072] Therefore, the technical solution provided in this embodiment can accurately and efficiently determine the fitting parameters of eyeglasses.

[0073] Based on the first embodiment described above, a second embodiment of the method for determining the lens fitting parameters of the eyeglasses of this application is proposed. In the second embodiment, before step S20, the method for determining the lens fitting parameters may further include steps S201 to S202: Step S201: Establish a wearing coordinate system on the three-dimensional digital head model; It should be noted that the wearing coordinate system refers to a three-dimensional rectangular coordinate system established on a three-dimensional digital head model to uniformly describe the spatial relationship between the glasses frame and the head and face.

[0074] When establishing a wearing coordinate system on a 3D digital head model, the midpoint between the left and right tragus points of the target user can be used as the origin, with the left-right direction as the X-axis, the up-down direction as the Y-axis, and the front-back direction as the Z-axis. Alternatively, the geometric center of the bounding box of the 3D digital head model can be used as the origin, with the intersection of the midline sagittal plane of the face and the horizontal plane as the Z-axis, the direction perpendicular to the horizontal plane as the Y-axis, and the direction perpendicular to both the Y-axis and Z-axis as the X-axis.

[0075] Step S202: Based on the wearing coordinate system, establish the wearing reference geometric elements of the three-dimensional digital head model. The wearing reference geometric elements include at least the front support reference surface of the frame and the reference line of the ear loop constraint path of the temple. Among them, the front support reference plane of the frame provides a reference reference plane for the nose bridge support constraint calculation, and the ear hook constraint path reference line of the temple constitutes the constraint target path of the ear hook point path constraint.

[0076] It should be noted that the wearing reference geometric elements refer to geometric elements established in the wearing coordinate system that provide spatial reference for the construction of subsequent eyeglass fitting constraints. These may include, but are not limited to, reference planes, reference lines, and reference points, etc., and this embodiment does not specifically limit them. The front support reference plane of the frame refers to a spatial curved surface or plane fitted from the nose bridge support area in the three-dimensional digital head model, which is used as a reference reference plane for nose pad fitting in the nose bridge support constraint. The temple ear hook constraint path reference line refers to a spatial curve fitted from the ear hook point area in the three-dimensional digital head model, which is used as the constraint target path for the temple bending segment in the ear hook point path constraint.

[0077] In practical use, the reference geometry elements for wearing the device may also include optical center reference lines, posture correction reference lines, etc. This embodiment does not specifically limit these. The optical center reference line is a straight line in space determined based on the line connecting the centers of the two pupils of the target user. It is used to provide a reference for the direction of the line of sight for constructing optical alignment constraints. The posture correction reference line is a straight line in space determined based on the midline of the target user's face and the symmetry between the two ears. It is used to correct the posture of the three-dimensional digital head model before extracting key features, so as to eliminate the posture deviation caused by slight head rotation during scanning.

[0078] In this embodiment, a wearing coordinate system is first established on the three-dimensional digital head model to provide a unified spatial reference framework for all subsequent geometric calculations, so that the frame posture optimization and parameter measurement are performed in the same coordinate system. Then, based on the wearing coordinate system, wearing reference geometric elements including the front support reference plane of the frame and the ear hook constraint path reference line of the temple are established. This provides a clear fit calculation reference for the bridge of the nose support constraint, and at the same time provides a clear constraint target path for the ear hook point path constraint. Thus, the subsequent construction of the lens fitting constraint has a clear spatial definition and quantitative calculation basis, effectively ensuring the accuracy of the lens fitting parameters determined later.

[0079] Based on the first and / or second embodiments described above, a third embodiment of the method for determining the fitting parameters of eyeglasses according to this application is proposed. In the third embodiment, the bilateral ear-side key features include the left ear-side key features and the right ear-side key features; step S30 may include steps S301 to S302: Step S301: Based on the key features of the left ear and the key features of the right ear, determine the left and right ear position difference information of the target user; It should be noted that the key features of the left ear side refer to anatomical landmarks extracted from the left auricle and postauricular region of the 3D digital head model that are directly related to the wearing of the left temple of the glasses. These may include, but are not limited to, the left ear root point, the left tragus point, the highest point of the left auricle, and the left postauricular transition point. This embodiment does not specifically limit these features. The key features of the right ear side refer to anatomical landmarks extracted from the right auricle and postauricular region of the 3D digital head model that are directly related to the wearing of the right temple of the glasses. These include the right ear root point, the right tragus point, the highest point of the right auricle, and the right postauricular transition point. The left and right ear position difference information refers to the quantitative information obtained by comparing the spatial positions of the key features of the left and right ears, describing the differences in height, abduction angle, and anterior-posterior position of the target user's left and right ears.

[0080] When determining the left and right ear position difference information of the target user based on the key features of the left and right ears, the spatial coordinates of each anatomical landmark in the key features of the left ear can be compared one by one with the spatial coordinates of the corresponding anatomical landmark in the key features of the right ear. The height difference and anterior-posterior position difference between the corresponding points are calculated, and these differences are combined to form the left and right ear position difference information. Alternatively, a path curve for the left ear hanging point can be fitted based on the key features of the left ear, and a path curve for the right ear hanging point can be fitted based on the key features of the right ear. The overall offset and local morphological differences of the two curves in space can be compared to obtain the left and right ear position difference information. This embodiment does not specifically limit the implementation of step S301.

[0081] Step S302: Based on the lens fitting constraints and the left and right ear position difference information, the original three-dimensional model of the candidate glasses is optimized for pose to obtain the target three-dimensional model of the candidate glasses.

[0082] When optimizing the pose of the original 3D model of the candidate glasses based on the lens fitting constraints and the left and right ear position differences, to obtain the target 3D model of the candidate glasses, the left ear hook point path constraints and right ear hook point path constraints can be included as two independent error terms in the objective function. The allowable ranges for the two error terms can be set according to the left and right ear position differences, and the optimal fitting poses for the left and right temples can be solved simultaneously through iterative optimization. Alternatively, preliminary pose optimization can be performed first using a symmetry assumption. After obtaining the initial pose, the required pose compensation amounts for the left and right temples can be calculated based on the left and right ear position differences, and the initial poses can be adjusted independently for the left and right sides to obtain the target 3D model. This embodiment does not specifically limit the implementation method of step S302.

[0083] In this embodiment, key features of the left and right ears are first analyzed to extract left and right ear position difference information that objectively reflects the geometric position difference between the left and right ears of the target user. This makes subsequent posture optimization no longer based on the ideal assumption of left-right symmetry. Then, the left and right ear position difference information is introduced into the lens fitting constraints so that the left and right temples can be adapted to their respective behind-the-ear hook paths. This allows the generated target 3D model to truly reflect the asymmetrical wearing posture caused by the left and right ear position difference, further improving the consistency between the target 3D model and the actual wearing state of the target user, and effectively ensuring the accuracy of the lens fitting parameters determined subsequently.

[0084] Based on the first, second, and / or third embodiments described above, a fourth embodiment of the method for determining the lens fitting parameters of the eyeglasses of this application is proposed. In the fourth embodiment, before step S30, the method for determining the lens fitting parameters may further include steps S01 to S02: Step S01: Based on the key features of the bridge of the nose and the key features of both ears, register the original 3D model of the candidate glasses with the 3D digital head model so that the nose pad area of ​​the original 3D model is aligned with the bridge of the nose support area, and the temple path of the original 3D model is aligned with the hanging point area behind both ears. It should be noted that registering the original 3D model of the candidate glasses with the 3D digital head model refers to adjusting the original 3D model of the candidate glasses from its own initial coordinate system to a position and orientation roughly aligned with the corresponding anatomical region in the 3D digital head model through spatial transformation, providing a reasonable initial posture for subsequent posture optimization. The nose pad area refers to the area on the original 3D model of the candidate glasses where the components come into contact with the target user's nose bridge, typically including the curved surfaces of the left and right nose pads. The temple path refers to the spatial path of the temples in the original 3D model of the candidate glasses, extending from the lens rim connection point through the bend to the end; it is the continuous geometric path through which the temples contact the sides of the head and behind the ears when worn.

[0085] When registering the original 3D model of the candidate glasses with the 3D digital head model based on the key features of the bridge of the nose and the key features of both ears, the apex of the bridge of the nose and the left and right tragus points of the key features of both ears can be used as three sets of corresponding points. The rotation and translation matrix required for the original 3D model to align with the 3D digital head model from its initial pose can be calculated, transforming the original 3D model to a position that is basically aligned with the bridge of the nose support area and the ear hook area. Alternatively, the surface shape features of the bridge of the nose support area and the path curve features of the ear hook area can be extracted, and the corresponding area with the highest matching degree with the above features can be searched in the original 3D model. Based on this, the spatial transformation parameters of the original 3D model can be determined, and the registration can be completed. This embodiment does not specifically limit the implementation method of step S01.

[0086] Step S02: After registering the original 3D model of the candidate glasses with the 3D digital head model, perform the step of posing optimization of the original 3D model of the candidate glasses according to the lens fitting constraints.

[0087] In this embodiment, by adding a registration step before posture optimization, the original 3D model of the candidate glasses is pre-adjusted to an initial state where the nose pad area is aligned with the nose bridge support area and the temple path is aligned with the hanging points behind both ears. This allows the subsequent posture optimization process to start iteratively from a starting point that is close to the target wearing position, thereby narrowing the optimization search range, reducing the time required for iteration convergence, and reducing the risk of optimization getting trapped in local suboptimal solutions. This improves the efficiency of acquiring the target 3D model and the accuracy of posture, thereby further improving the accuracy and efficiency of determining the glasses fitting parameters.

[0088] Based on the first, second, third, and / or fourth embodiments described above, a fifth embodiment of the method for determining the fitting parameters of eyeglasses according to this application is proposed. In the fifth embodiment, after step S40, the method for determining the fitting parameters of eyeglasses may further include steps S50 to S70: Step S50: Overlay and render the target 3D model of the candidate glasses onto the 3D digital head model to generate a trial wearing effect image of the candidate glasses. The trial wearing effect image includes at least one frame of close-up view of the temple fitting relationship between the temple of the candidate glasses and the ear hook area in the 3D digital head model. It should be noted that overlay rendering refers to the process of placing the target 3D model of the candidate glasses onto the corresponding parts of the 3D digital head model in a 3D virtual space according to its spatial position and angle determined after posture optimization, and generating a 2D image or 3D visualization through computer graphics rendering technology. The try-on effect image refers to a visualization image generated through overlay rendering to show the wearing effect of the candidate glasses on the target user's head and face. It can be a static image, a dynamic sequence of frames, or an interactively rotatable 3D view, etc., and this embodiment does not specifically limit this. The temple fit close-up view refers to a magnified view in the try-on effect image specifically used to show the fit between the bent section of the temple of the candidate glasses and the ear hook area in the 3D digital head model. Its shooting angle differs from the front view, usually showing it from the side rear or side upper of the target user to clearly present the contact or gap state between the temple and the ear hook area.

[0089] Step S60: Based on the wearing posture data of the target 3D model of the candidate glasses relative to the 3D digital head model, generate the wearing matching score corresponding to the candidate glasses; It should be noted that wearing posture data refers to quantitative data describing the spatial position, orientation, and geometric matching relationship between the target 3D model of the candidate glasses and various anatomical regions of the head and face in the 3D digital head model. This data may include, but is not limited to, size matching data, wearing comfort data, optical adaptation data, and appearance adaptation data. This embodiment does not impose specific limitations on this. Wearing matching score refers to a quantitative index calculated based on wearing posture data using preset scoring rules, used to comprehensively evaluate the degree of matching between the candidate glasses and the target user's head and face. The score reflects the comprehensive performance of the candidate glasses in multiple dimensions, including size matching, wearing comfort, optical adaptation, and appearance adaptation.

[0090] In one feasible implementation, step S60 may include steps S61-S62: Step S61: Based on the wearing posture data of the target 3D model of the candidate glasses relative to the 3D digital head model, determine the wearing sub-scores corresponding to the candidate glasses. Each wearing sub-score includes at least the size matching score, wearing comfort score, optical adaptation score, and appearance adaptation score. It should be noted that the wearing sub-score refers to a quantitative score obtained by independently evaluating the degree of matching between the candidate glasses and the target user's head and face in a specific dimension based on wearing posture data. The size matching score is used to evaluate the fit between the overall size of the frame and the target user's face; the wearing comfort score is used to evaluate the comfort of each contact area of ​​the frame when worn; the optical fit score is used to evaluate the alignment accuracy between the optical center of the lens and the target user's pupil; and the appearance fit score is used to evaluate the matching between the appearance of the frame and the target user's face shape.

[0091] In one feasible implementation, the wearing posture data includes at least size matching data, wearing comfort data, optical adaptation data, and appearance adaptation data, and step S61 may include steps S611 to S614: Step S611: Based on the size matching data of the target 3D model of the candidate glasses relative to the 3D digital head model, determine the size matching score of the candidate glasses. The size matching data includes at least the difference between the frame width of the candidate glasses and the face width in the 3D digital head model, the difference between the frame height and the face height in the 3D digital head model, and the difference between the bridge width and the width of the bridge support area in the 3D digital head model. It should be noted that the size matching data is a quantitative measure of the difference between the candidate eyeglasses' frame geometry and the corresponding facial geometry in the 3D digital head model. The difference between the frame width and the face width in the 3D digital head model refers to the difference between the horizontal distance between the outermost edges of the left and right lens rims of the candidate eyeglasses and the horizontal distance between the widest points of the corresponding cheekbones or sides of the face in the 3D digital head model. The difference between the frame height and the face height in the 3D digital head model refers to the difference between the vertical distance between the upper and lower edges of the candidate eyeglasses' lens rims and the vertical distance from the brow bone to the lower edge of the cheekbone in the 3D digital head model. The difference between the bridge width and the width of the bridge support area in the 3D digital head model refers to the difference between the inner distance between the left and right nose pads of the candidate eyeglasses and the width distance between the two boundaries of the bridge support area in the 3D digital head model.

[0092] Step S612: Determine the wearing comfort score of the candidate glasses based on the wearing comfort data of the candidate glasses. The wearing comfort data includes the path deviation between the temple bending section in the target 3D model of the candidate glasses and the ear hook area in the 3D digital head model, as well as the fitting gap between the nose pad area in the target 3D model of the candidate glasses and the nose bridge support area in the 3D digital head model. It should be noted that wearing comfort data refers to quantitative data reflecting the degree of fit and force between the various contact areas of the candidate glasses and the target user's head and face under different wearing postures. Path deviation refers to the spatial distance between the spatial travel curve of the temple bending section in the target 3D model of the candidate glasses and the fitted path curve of the ear-mounted area in the 3D digital head model. It is used to measure whether the temples travel correctly along the ear-mounted path. Fit gap refers to the normal distance between the nose pad surface in the target 3D model of the candidate glasses and the nose bridge support area surface in the 3D digital head model. It is used to measure whether the nose pad fits tightly against the nose bridge support area.

[0093] Step S613: Determine the optical adaptation score of the candidate glasses based on the optical adaptation data of the candidate glasses. The optical adaptation data includes at least the relative positional deviation between the optical center of the lens of the candidate glasses and the center of the pupil in the three-dimensional digital head model. It should be noted that optical adaptation data refers to quantitative data reflecting the spatial alignment between the optical center of the candidate glasses lens and the pupil of the target user. Relative position deviation refers to the horizontal and vertical offset between the coordinates of the optical center of the candidate glasses lens in three-dimensional space and the coordinates of the pupil center in the three-dimensional digital head model.

[0094] Step S614: Determine the appearance adaptation score of the candidate glasses based on the appearance adaptation data of the candidate glasses. The appearance adaptation data includes at least the degree of coordination between the frame shape of the candidate glasses and the facial contour and / or eyebrow and eye ratio in the three-dimensional digital head model.

[0095] It should be noted that appearance adaptation data refers to quantitative data reflecting the degree of harmony between the frame style of candidate eyeglasses and the facial aesthetic features of the target user. Frame style refers to the overall design style of the candidate eyeglasses, which may include geometric attributes such as lens shape, frame type, and line direction. Facial contour refers to the outer contour line of the target user's face in the 3D digital head model, which may include cheek contour, jawline, etc. Eyebrow-eye ratio refers to the vertical distance between the target user's eyebrows and eyes in the 3D digital head model, relative to the overall height of the face. Harmony refers to the degree of visual matching between the frame style of the candidate eyeglasses and the facial contour and / or eyebrow-eye ratio in the 3D digital head model, which can be quantified through preset aesthetic matching rules or a harmony model trained on samples.

[0096] In this embodiment, the wearing posture data is broken down into specific quantifiable data items according to four dimensions: size matching, wearing comfort, optical adaptation, and appearance adaptation. Based on the specific data items of each dimension, corresponding wearing sub-scores are determined independently. This ensures that the generation of each wearing sub-score has clear underlying data basis and traceable calculation path, thereby ensuring that each wearing sub-score can objectively and accurately reflect the degree of matching between the candidate glasses and the target user in the corresponding dimension. This provides a reliable sub-item basis for the subsequent weighted fusion of sub-scores and the generation of a comprehensive wearing matching score.

[0097] Step S62: Perform weighted fusion processing on the size matching score, wearing comfort score, optical adaptation score and appearance adaptation score corresponding to the candidate glasses to generate the wearing matching score of each candidate glasses.

[0098] The size matching score, wearing comfort score, optical fit score, and appearance fit score of the candidate glasses are weighted and fused. This involves combining the scores into a single overall score based on the weight coefficients assigned to each sub-score. The weight coefficients reflect the importance of different evaluation dimensions in the overall recommendation process.

[0099] In this embodiment, by converting wearing posture data into corresponding wearing sub-scores according to four dimensions—size, comfort, optics, and appearance—the matching degree between candidate glasses and target users in multiple dimensions is independently quantified and evaluated. Then, by weighted fusion processing of each wearing sub-score, the evaluation results of multiple dimensions are integrated into a unified wearing matching score. This allows users to intuitively compare the overall matching level of different candidate glasses without having to compare data from multiple dimensions one by one, thereby improving the accuracy of glasses recommendations and decision-making efficiency.

[0100] Step S70: Display the trial effect images and matching scores of each candidate pair of glasses on the glasses recommendation interface.

[0101] It should be noted that "associated display" refers to establishing a clear visual correspondence between the trial-wearing effect images of the same candidate glasses and their corresponding wearing matching scores within the same glasses recommendation interface, allowing users to simultaneously view the wearing effect and quantitative score of the candidate glasses. The glasses recommendation interface refers to the interactive interface used to display the trial-wearing effect and recommendation information of candidate glasses to users. It can be a local application interface, a web page interface, or an augmented reality overlay interface, etc., and this embodiment does not specifically limit it.

[0102] In this embodiment, by generating a virtual try-on effect image for the candidate glasses that includes at least a close-up view of the temple fitting, the fit between the temple and the area behind the ear is included in the display scope, enriching the display dimensions of the virtual try-on and improving the comprehensiveness of the virtual try-on effect. At the same time, a wearing matching score is generated based on the wearing posture data of the target 3D model relative to the 3D digital head model, so that the score is directly related to the actual wearing posture of the frame on the user's head and face, rather than relying on appearance attributes or manually entered preferences, thereby improving the accuracy of the glasses recommendation.

[0103] Based on the fifth embodiment described above, a sixth embodiment of the method for determining the fitting parameters of eyeglasses according to this application is proposed. In the sixth embodiment, the method for determining the fitting parameters of eyeglasses may further include: Extract the facial geometry from the 3D digital head model. The facial geometry includes at least the target user's face width and interpupillary distance. Based on facial geometry, glasses that fit the 3D digital head model are matched from a preset glasses library and used as candidate glasses.

[0104] It should be noted that facial geometric dimensions refer to the quantitative data extracted from the 3D digital head model used to characterize the dimensional features of key facial regions of the target user. Facial width refers to the horizontal distance between the cheekbones or the widest points of the facial contour on the left and right sides of the target user's face in the 3D digital head model. Interpupillary distance refers to the horizontal distance between the centers of the left and right pupils of the target user in the 3D digital head model.

[0105] Additionally, it should be noted that the preset eyeglasses library refers to a pre-established database that stores parametric 3D models of various eyeglasses and their corresponding size attributes. The size attributes of each type of eyeglasses include at least the frame width, bridge width, and optical center distance between the lenses. Matching eyeglasses to the 3D digital head model in the preset eyeglasses library based on facial geometry essentially involves comparing the facial geometry with the size attribute information of each eyeglass in the preset eyeglasses library, and selecting eyeglasses whose size differences are within a preset acceptable range.

[0106] When matching glasses adapted to a 3D digital head model from a preset glasses library based on facial geometry, and using these glasses as candidate glasses, the differences between the frame width and face width, the bridge width and preset bridge support area width, and the optical center distance between the lenses and pupillary distance can be calculated for each pair of glasses in the preset glasses library. Glasses whose differences all meet preset threshold conditions are determined as candidate glasses. Alternatively, the comprehensive deviation values ​​of the frame width and face width, bridge width and preset bridge support area width, and optical center distance between the lenses and pupillary distance can be calculated for each pair of glasses in the preset glasses library, and they can be sorted from smallest to largest according to the comprehensive deviation values. The preset number of glasses with the highest comprehensive deviation values ​​are determined as candidate glasses. This embodiment does not specifically limit the implementation method of step S102.

[0107] In this embodiment, facial geometric dimensions such as the target user's face width and interpupillary distance are extracted from the 3D digital head model to convert the geometric information of the head model into quantitative indicators that can be used for size matching and screening. By matching these quantitative indicators in a preset glasses library, glasses that are obviously unsuitable in size are excluded in advance, and only glasses that are initially adapted to the target user's facial geometric dimensions are retained as candidate glasses. This narrows down the range of glasses that need to be individually optimized for posture, determined for lens fitting parameters, and virtual try-on demonstrations. This improves the overall recommendation efficiency and the efficiency of determining lens fitting parameters while ensuring the quality of recommendations.

[0108] This application also provides a device for determining eyeglass fitting parameters. Please refer to... Figure 3 The device for determining the fitting parameters of eyeglasses may include: The digital head model acquisition module 10 is used to acquire the three-dimensional digital head model of the target user. The three-dimensional digital head model includes at least the continuous curved surface information of the target user's nose bridge support area, the bilateral ear hook area and the bilateral temple contact area. The feature extraction module 20 is used to extract key features from the three-dimensional digital head model and construct eyeglass fitting constraints based on the key features. The key features include at least the key features of the bridge of the nose and the key features of both ears. The eyeglass fitting constraints include at least the bridge of the nose support constraints and the ear hanging point path constraints. The posture optimization module 30 is used to optimize the posture of the original 3D model of the candidate glasses according to the lens fitting constraints, so as to obtain the target 3D model of the candidate glasses. The lens fitting parameter determination module 40 is used to determine the lens fitting parameters of the candidate glasses based on the target 3D model and the 3D digital head model.

[0109] In one embodiment, the attitude optimization module 30 is further configured to: Based on the constraints of eyeglass fitting, an objective function is constructed, which includes at least a nasal bridge fit error term and an ear path deviation term; With minimizing the function value of the objective function as the optimization objective, the pose parameters of the original 3D model are iteratively optimized to obtain the target 3D model.

[0110] In one embodiment, the eyeglass fitting parameter determination module 40 is further configured to: Map the target 3D model to the coordinate system of the 3D digital head model; Based on the spatial geometric relationship between the mapped target 3D model and the 3D digital head model, the fitting parameters of the candidate glasses are determined. Among them, the lens fitting parameters include frame wearing posture parameters and / or optical alignment parameters. Frame wearing posture parameters are used to characterize the spatial posture of the candidate glasses on the target user's face, and optical alignment parameters are used to characterize the alignment relationship between the optical center of the candidate glasses lens and the target user's pupil.

[0111] In one embodiment, when the lens fitting parameters include frame wearing posture parameters, the frame wearing posture parameters include forward tilt angle, lens angle and / or lens-to-eye distance; The lens fitting parameter determination module 40 is also used for: The forward tilt angle of the candidate glasses is determined based on the angle between the lens plane normal vector of the mapped target 3D model and the facial reference plane in the 3D digital head model. And / or, based on the angle between the normal vectors of the left and right mirror planes of the mapped target 3D model in the top-view direction, determine the mirror angle of the candidate glasses; And / or, calculate the spatial distance from the lens plane of the mapped target 3D model to the corneal vertex in the 3D digital head model to obtain the lens-to-eye distance of the candidate glasses.

[0112] In one embodiment, when the lens fitting parameters include optical alignment parameters, the optical alignment parameters include pupillary distance and / or pupillary height; The lens fitting parameter determination module 40 is also used for: Based on the mapping position of the pupil center in the 3D digital head model on the lens plane of the mapped target 3D model, the interpupillary distance and / or pupil height corresponding to the candidate glasses are determined.

[0113] In one embodiment, the digital head model acquisition module 10 is further configured to: Acquire multi-view 3D scan data covering at least the frontal facial area and the area behind both ears of the target user; The multi-view 3D scanning data is filtered and then registered to a preset coordinate system. Based on the registered multi-view 3D scan data, a 3D digital head model of the target user is constructed.

[0114] In one embodiment, the eyeglass fitting parameter determination device further includes a wearing reference construction module 50, used for: Establish a wearing coordinate system on a 3D digital head model; Based on the wearing coordinate system, the wearing reference geometric elements of the three-dimensional digital head model are established. The wearing reference geometric elements include at least the front support reference surface of the frame and the reference line of the ear hook constraint path of the temple. Among them, the front support reference plane of the frame provides a reference reference plane for the nose bridge support constraint calculation, and the ear hook constraint path reference line of the temple constitutes the constraint target path of the ear hook point path constraint.

[0115] In one embodiment, the bilateral ear-side key features include left ear-side key features and right ear-side key features; the pose optimization module 30 is further configured to: Based on the key features of the left and right ears, the left and right ear position differences of the target user are determined; Based on the lens fitting constraints and the difference in left and right ear positions, the original 3D model of the candidate glasses is optimized for pose to obtain the target 3D model of the candidate glasses.

[0116] In one embodiment, the attitude optimization module 30 is further configured to: Based on the key features of the bridge of the nose and the key features of both ears, the original 3D model of the candidate glasses is registered with the 3D digital head model so that the nose pad area of ​​the original 3D model is aligned with the bridge of the nose support area, and the temple path of the original 3D model is aligned with the hanging point area behind both ears. After registering the original 3D model of the candidate glasses with the 3D digital head model, the step of optimizing the pose of the original 3D model of the candidate glasses according to the lens fitting constraints is performed.

[0117] The eyeglass fitting parameter determination device provided in this application adopts the eyeglass fitting parameter determination method in the above embodiments, and can accurately and efficiently determine the eyeglass fitting parameters. Compared with the prior art, the beneficial effects of the eyeglass fitting parameter determination device provided in this application are the same as the beneficial effects of the eyeglass fitting parameter determination method provided in the above embodiments, and other technical features in the eyeglass fitting parameter determination device are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0118] This application also provides an electronic device, which may include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the eyeglass fitting parameter determination method in the above embodiments.

[0119] The following is for reference. Figure 4 It shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of this application. Figure 4 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0120] like Figure 4 As shown, the electronic device may include a processing unit 101 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory 102 or a program loaded from storage device 103 into random access memory 104. Random access memory 104 also stores various programs and data required for the operation of the electronic device. The processing unit 101, read-only memory 102, and random access memory 104 are interconnected via bus 105. Input / output interface 106 is also connected to bus 105. Typically, the following systems can be connected to input / output interface 106: input devices 107 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 108 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 103 including, for example, magnetic tape, hard disks, etc.; and communication devices 109. Communication device 109 allows the electronic device to communicate wirelessly or wiredly with other devices to exchange data. Although the diagrams show electronic devices with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented alternatively.

[0121] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 103, or installed from read-only memory 102. When the computer program is executed by processing device 101, it performs the functions defined in the methods of the embodiments of this application.

[0122] The electronic device provided in this application uses the eyeglasses fitting parameter determination method described in the above embodiments, which can accurately and efficiently determine the eyeglasses fitting parameters. Compared with the prior art, the beneficial effects of the electronic device provided in this application are the same as those of the eyeglasses fitting parameter determination method described in the above embodiments, and other technical features of the electronic device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0123] It should be understood that various parts of the embodiments of this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0124] The above description is merely a specific implementation of the embodiments of this application, but the protection scope of the embodiments of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the protection scope of the embodiments of this application. Therefore, the protection scope of the embodiments of this application should be determined by the protection scope of the above claims.

[0125] This application also provides a computer-readable storage medium storing a computer program that can run on a processor. The computer program is used to execute the method for determining eyeglass fitting parameters in the above embodiments.

[0126] The computer-readable storage medium provided in this application embodiment may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0127] The aforementioned computer-readable storage medium may be included in an electronic device or may exist independently without being assembled into an electronic device.

[0128] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by an electronic device, cause the electronic device to: acquire a three-dimensional digital head model of a target user, the three-dimensional digital head model including at least continuous surface information of the target user's nose bridge support area, bilateral ear hook point areas, and bilateral temple contact areas; extract key features from the three-dimensional digital head model, and construct fitting constraints based on the key features, the key features including at least nose bridge key features and bilateral ear key features, the fitting constraints including at least nose bridge support constraints and ear hook point path constraints; optimize the posture of the original three-dimensional model of the candidate glasses according to the fitting constraints to obtain the target three-dimensional model of the candidate glasses; and determine the fitting parameters of the candidate glasses according to the target three-dimensional model and the three-dimensional digital head model.

[0129] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0130] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0131] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0132] The computer-readable storage medium provided in this application embodiment stores computer-readable program instructions for executing the above-described method for determining the lens fitting parameters of eyeglasses, enabling accurate and efficient determination of the lens fitting parameters. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application embodiment are the same as the beneficial effects of the method for determining the lens fitting parameters of eyeglasses provided in the above embodiments, and will not be repeated here.

[0133] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the method for determining eyeglass fitting parameters as described above.

[0134] The computer program product provided in this application can accurately and efficiently determine the lens fitting parameters of eyeglasses. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the lens fitting parameter determination method provided in the above embodiments, and will not be repeated here.

[0135] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for determining the fitting parameters of eyeglasses, characterized in that, The method includes: Obtain a three-dimensional digital head model of the target user, wherein the three-dimensional digital head model includes at least the continuous curved surface information of the target user’s nose bridge support area, bilateral ear hook area and bilateral temple contact area; Key features are extracted from the three-dimensional digital head model, and eyeglass fitting constraints are constructed based on the key features. The key features include at least key features of the bridge of the nose and key features of both ears. The eyeglass fitting constraints include at least key features of the bridge of the nose and key features of both ears. Based on the eyeglass fitting constraints, the original 3D model of the candidate eyeglasses is subjected to pose optimization to obtain the target 3D model of the candidate eyeglasses; Based on the target 3D model and the 3D digital head model, determine the fitting parameters for the candidate glasses.

2. The method as described in claim 1, characterized in that, The step of optimizing the pose of the original 3D model of the candidate glasses based on the lens fitting constraints to obtain the target 3D model of the candidate glasses includes: Based on the aforementioned eyeglass fitting constraints, an objective function is constructed, which includes at least a nasal bridge fit error term and an ear path deviation term; With minimizing the function value of the objective function as the optimization objective, the pose parameters of the original 3D model are iteratively optimized to obtain the target 3D model.

3. The method as described in claim 1, characterized in that, The step of determining the fitting parameters of the candidate glasses based on the target 3D model and the 3D digital head model includes: Map the target 3D model to the coordinate system of the 3D digital head model; Based on the spatial geometric relationship between the mapped target 3D model and the 3D digital head model, the lens fitting parameters of the candidate glasses are determined; The fitting parameters include frame wearing posture parameters and / or optical alignment parameters. The frame wearing posture parameters are used to characterize the spatial posture of the candidate glasses on the target user's face, and the optical alignment parameters are used to characterize the alignment relationship between the optical center of the candidate glasses lens and the pupil of the target user.

4. The method as described in claim 3, characterized in that, When the lens fitting parameters include the lens wearing posture parameters, the lens wearing posture parameters include the forward tilt angle, the mirror angle, and / or the distance between the lens and the eye. The step of determining the fitting parameters of the candidate glasses based on the spatial geometric relationship between the mapped target 3D model and the 3D digital head model includes: The forward tilt angle of the candidate glasses is determined based on the angle between the lens plane normal vector of the mapped target 3D model and the facial reference plane in the 3D digital head model. And / or, based on the angle between the left and right lens plane normal vectors of the mapped target 3D model in the top-view direction, determine the mirror angle of the candidate glasses; And / or, calculate the spatial distance from the lens plane of the mapped target 3D model to the corneal vertex in the 3D digital head model to obtain the lens-to-eye distance of the candidate glasses.

5. The method as described in claim 3, characterized in that, When the lens fitting parameters include the optical alignment parameters, the optical alignment parameters include interpupillary distance and / or pupillary height; The step of determining the fitting parameters of the candidate glasses based on the spatial geometric relationship between the mapped target 3D model and the 3D digital head model includes: Based on the mapping position of the pupil center in the three-dimensional digital head model on the lens plane of the mapped target three-dimensional model, the interpupillary distance and / or pupil height corresponding to the candidate glasses are determined.

6. The method as described in claim 1, characterized in that, The step of obtaining the target user's three-dimensional digital head model includes: Acquire multi-view 3D scan data covering at least the frontal facial region and the bilateral behind-ear regions of the target user; The multi-view 3D scanning data is filtered, and the filtered multi-view 3D scanning data is registered to a preset coordinate system; Based on the registered multi-view 3D scan data, a 3D digital head model of the target user is constructed.

7. The method according to any one of claims 1 to 6, characterized in that, Before the step of extracting key features from the 3D digital head model, the method further includes: Establish a wearing coordinate system on the three-dimensional digital head model; Based on the wearing coordinate system, the wearing reference geometric elements of the three-dimensional digital head model are established. The wearing reference geometric elements include at least the front support reference surface of the frame and the ear hook constraint path reference line of the temple. The front support reference surface of the frame provides a reference surface for the nose bridge support constraint to calculate the nose bridge fit, and the ear hook constraint path reference line of the temple constitutes the constraint target path of the ear hook point path constraint.

8. The method according to any one of claims 1 to 6, characterized in that, The bilateral auricular key features include left auricular key features and right auricular key features; The step of optimizing the pose of the original 3D model of the candidate glasses based on the lens fitting constraints to obtain the target 3D model of the candidate glasses includes: Based on the key features of the left ear and the key features of the right ear, the left and right ear position difference information of the target user is determined; Based on the lens fitting constraints and the left and right ear position difference information, the original three-dimensional model of the candidate glasses is optimized for pose to obtain the target three-dimensional model of the candidate glasses.

9. The method according to any one of claims 1 to 6, characterized in that, Before the step of optimizing the pose of the original 3D model of the candidate glasses based on the lens fitting constraints, the method further includes: Based on the key features of the bridge of the nose and the key features of both ears, the original three-dimensional model of the candidate glasses is registered with the three-dimensional digital head model so that the nose pad area of ​​the original three-dimensional model is aligned with the bridge of the nose support area, and the temple path of the original three-dimensional model is aligned with the hanging point area behind both ears. After registering the original 3D model of the candidate glasses with the 3D digital head model, the step of optimizing the pose of the original 3D model of the candidate glasses according to the lens fitting constraints is performed.

10. A device for determining the fitting parameters of eyeglasses, characterized in that, The device for determining the fitting parameters of the eyeglasses includes: The digital head model acquisition module is used to acquire a three-dimensional digital head model of the target user. The three-dimensional digital head model includes at least the continuous curved surface information of the target user's nose bridge support area, the bilateral ear hook area, and the bilateral temple contact area. The feature extraction module is used to extract key features from the three-dimensional digital head model and construct eyeglass fitting constraints based on the key features. The key features include at least key features of the bridge of the nose and key features of both ears. The eyeglass fitting constraints include at least key features of the bridge of the nose and key features of both ears. The posture optimization module is used to optimize the posture of the original 3D model of the candidate glasses according to the lens fitting constraints, so as to obtain the target 3D model of the candidate glasses. The lens fitting parameter determination module is used to determine the lens fitting parameters of the candidate glasses based on the target 3D model and the 3D digital head model.

11. 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, the computer program being configured to implement the method for determining the fitting parameters of eyeglasses as described in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method for determining eyeglass fitting parameters as described in any one of claims 1 to 9.

Images