Method, medium and device for determining a profile of a distribution comb based on three-dimensional data acquisition

Abstract

The present application relates to the field of data processing, and provide a kind of based on three-dimensional data acquisition distribution comb profile determination method, medium and equipment.The profile curve of the specific region of the head of the user obtained is clustered, centroid curve is generated, and is divided into sub-section centroid curve according to preset interval, and the section curve with similarity up to standard in corresponding cluster is selected as fitting candidate curve.A multi-objective optimization function containing curvature continuity, second derivability and anatomical fitness is established, and dynamic programming algorithm is used to generate initial profile point sequence by globally optimal combination of fitting candidate curve, and form the profile curve of the comb adhering to the scalp side after smoothing optimization.The present application divides user head type characteristic category by cluster analysis, generates initial hash point set with cluster center, optimizes curve fitting degree in combination with standardization smoothing algorithm, and finally outputs standard curvature template adapted to corresponding group.

Description

Technical Field

[0001] This invention relates to the field of data processing, and in particular to a method, medium, and device for determining the profile of a distribution comb based on three-dimensional data acquisition. Background Technology

[0002] In dermatological clinical practice, the treatment of various hair loss and scalp diseases often requires direct application to specific areas of the scalp, such as topical medication, scalp laser treatment, or injections. However, due to the wide variety of patients' daily hairstyles, it is often impossible to shave all the hair for ease of treatment. Furthermore, the hair covering prevents the corresponding scalp from being exposed. In actual clinical treatment, doctors usually need to use a parting comb or similar tool to separate the hair to clearly expose the scalp area to be treated, allowing for targeted diagnostic and treatment procedures.

[0003] Current hair parting devices suffer from significant structural adaptability issues. Due to variations in user age and gender, head shapes differ considerably. This makes it difficult for the inherent curvature of the parting plate's contact surface with the scalp to achieve a proper fit to specific head shapes, resulting in two dual technical defects: first, some hair cannot be effectively parted, preventing complete exposure of the target scalp area; second, the parting plate struggles to firmly hold the hair on either side of the parting, leading to hair rebound and covering the treatment area during treatment. These two interacting defects severely restrict the convenience and efficiency of the treatment procedure. Summary of the Invention

[0004] To address the aforementioned technical problems, the technical solution adopted by this invention is as follows:

[0005] According to one aspect of the present invention, a method for determining the profile of a distribution comb based on three-dimensional data acquisition is provided, the method comprising the following steps:

[0006] The contour curves of specific head shapes of different users are obtained by 3D point cloud scanning technology. The contour curves are composed of a discrete coordinate point sequence, and the topological consistency of coordinate points is maintained between each contour curve.

[0007] All contour curves are clustered to generate centroid curves for each cluster. The centroid curves represent the cluster centers of the clusters.

[0008] Based on the preset segmentation interval, the centroid-like curve is divided into several segment centroid curves.

[0009] Based on the similarity between the centroid curve of each segment and the corresponding segment curve of each contour curve in its cluster, at least one candidate fitting curve is determined for each segment's centroid curve. The candidate fitting curve is the segment curve in the cluster containing the centroid curve of the segment whose similarity to it is greater than a preset threshold.

[0010] A multi-objective optimization function is established, which includes indices of curvature continuity, second-order differentiability, and anatomical fit. A dynamic programming algorithm is used to perform a global optimal combination of all fitting candidate curves corresponding to the centroid-like curve to generate an initial contour point sequence.

[0011] The smoothness of the contour curve formed by the initial contour point sequence is optimized to generate the contour curve corresponding to the side of the scalp where the comb is attached.

[0012] According to a second aspect of the present invention, a non-transitory computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the above-described method for determining the profile of a distribution comb based on three-dimensional data acquisition.

[0013] According to a third aspect of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method for determining the profile of a distribution comb based on three-dimensional data acquisition.

[0014] This invention has at least one of the following beneficial effects:

[0015] This invention collects forehead and head shape curve data from different users, and classifies the contour curves using cluster analysis to ensure that each classification corresponds to the head shape curve characteristics of the corresponding user group. For each cluster, an initial set of head shape curve hash points (i.e., an initial contour point sequence) is generated based on its cluster center. Then, a standardized curve smoothing algorithm is used to optimize the curve formed by these hash points. The iteratively smoothed contour curve effectively improves its fit with all head shape curves within the corresponding cluster. Finally, the optimized contour curve is used as the standard curvature template for the scalp side of the corresponding hair comb for that user group. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1This is a schematic diagram of the structure of the comb when the distribution angle is set on the distribution tooth plate in one embodiment of this application.

[0018] Figure 2 This is a schematic diagram of the comb structure when the distribution angle is set on the fixed frame in another embodiment of this application.

[0019] Figure 3 This is a schematic diagram of the distribution comb when the distribution tooth plate is opened, according to another embodiment of this application.

[0020] Figure 4 This is a schematic diagram of the closed state of the first opening and closing unit and the second opening and closing unit in another embodiment of this application.

[0021] Figure 5 This is a schematic diagram of the opening state of the first opening / closing unit and the second opening / closing unit in another embodiment of this application.

[0022] Figure 6 This is a structural schematic diagram illustrating the motion principle of the toothed plate in another embodiment of this application.

[0023] Figure 7 This is a schematic diagram of the structure of a comb when the finger loop is in another form in another embodiment of this application.

[0024] Figure 8 This is a schematic diagram of the structure of the comb when the two distribution angles are respectively set on the two distribution tooth plates in one embodiment of this application;

[0025] Figure 9 This is a flowchart illustrating a method for determining the profile of a distribution comb based on three-dimensional data acquisition, according to one embodiment of this application.

[0026] Figure Labels

[0027] 10. Distributing tooth plate; 101. First hinge point; 102. Third hinge point; 11. Distributing tooth; 12. Distributing angle; 13. Finger loop; 20. Fixing frame; 201. Second hinge point; 202. Fourth hinge point; 21. First opening / closing drive rod; 211. First opening / closing drive end; 212. First opening / closing connection end; 22. Second opening / closing drive rod; 221. Second opening / closing drive end; 222. Second opening / closing connection end. Detailed Implementation

[0028] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] As one possible embodiment of the present invention, such as Figure 9 The diagram illustrates a method for determining the profile of a distribution comb based on 3D data acquisition. The method includes the following steps:

[0030] S100: Contour curves of specific head shapes for different users are obtained through 3D point cloud scanning technology. The contour curves are composed of a sequence of discretized coordinate points, and the topological consistency of coordinate points is maintained between each contour curve.

[0031] Specifically, the 3D point cloud scanning uses non-contact laser triangulation technology and achieves multi-view point cloud registration through an iterative nearest point algorithm to improve the accuracy of the contour.

[0032] In this case, the segmentation and selection of user groups can be determined based on the morphological representation of specific head shape regions within heterogeneous user groups. For example, in the analysis of head contour features of specific graphic regions, significant morphological differences were found between men and women, and samples in the 15-20 and 20-25 age ranges also exhibited different contour features. Based on the above combination of morphological differences, the user group can be precisely divided into four typical categories: 15-20 year old males, 15-20 year old females, 20-25 year old males, and 20-25 year old females.

[0033] After acquiring the regional contour using 3D point cloud scanning technology, point cloud data along multiple specific preset paths within the contour region can be extracted, generating a set of points corresponding to each preset path. This yields the contour curve described in step S100. To ensure topological consistency of coordinate points among the contour curves (i.e., the same number and distribution of points), the point sets need to undergo standardized preprocessing operations in steps S101 and S102.

[0034] S100 includes:

[0035] S101: Resample the discretized coordinate point sequence of the initially acquired contour curve to ensure that all the final acquired contour curves have the same number and distribution of coordinate points.

[0036] S102: Normalize the coordinate points to eliminate scale differences.

[0037] S200: Cluster all contour curves to generate the centroid curve for each cluster. The centroid curve represents the cluster center of each cluster.

[0038] Clustering can be performed using the K-Means clustering algorithm.

[0039] Specifically, when using the K-Means clustering algorithm for clustering, it can be processed in the following two ways:

[0040] Firstly

[0041] S211: Based on the hash values ​​of the point coordinates corresponding to the standardized preprocessed contour curve, perform vector transformation processing to generate the high-dimensional curve vector corresponding to the contour curve.

[0042] After standardization preprocessing S101 and S102, the contour curves will be uniformly composed of a set of discrete points of equal number and consistent spatial location (i.e., each line can be represented as a fixed-length point sequence). This processing mechanism ensures that each contour line can be characterized as a point sequence structure with strict correspondence, and its sequence length remains constant. Based on the above premise, the core operation of vector transformation in this step can be defined as: transforming a fixed-length discrete point sequence into a continuous vector representation in a high-dimensional space through a specific mathematical mapping relationship.

[0043] Specifically, the following example illustrates this step:

[0044] Suppose there are N contour curves, each composed of M two-dimensional points L = [(x1, y1, z1), (x2, y2, z2), ..., (x m , y m , z m If we consider the given information, we can directly convert it into a 3M-dimensional vector V = (x1, y1, z1, x2, y2, z2, ..., x). m , y m , z m ).

[0045] S212: Determine the value of K and use the K-Means clustering algorithm to cluster all high-dimensional curve vectors.

[0046] In this embodiment, the K value can be preset manually. It should be noted that during the user's head shape contour curve acquisition in stage S100, a classification based on the differences in user groups has already been performed. Therefore, the K value can be adjusted based on the existing classification system to achieve optimized parameter configuration.

[0047] All vectors obtained after S211 processing are input into the standard K-Means algorithm for clustering. This yields K cluster centers, each a 3M-dimensional vector. These 3M-dimensional vectors are then converted into a point array of lines, resulting in a centroid curve. This centroid curve may not be a real-world line, but rather an "average line" composed of scattered points, its shape reflecting the overall trend of the lines within the cluster.

[0048] Secondly

[0049] S221: For the standardized preprocessed contour curve data, a similarity matrix is ​​constructed using dynamic time-normalized distance.

[0050] Dynamic Time Warping (DTW) is a method for measuring the similarity between two time series, particularly suitable for curve data with inconsistent lengths or local deformations. In this step, DTW is used to calculate the similarity between standardized preprocessed contour curves. Specifically, each contour curve is treated as a sequence of points, and its point coordinates are mapped to high-dimensional vectors. DTW is then used to calculate the distance between each pair of curves, ultimately forming a similarity matrix.

[0051] The advantage of this method is that it can effectively handle nonlinear deformation problems in curves, thereby improving the accuracy of clustering results.

[0052] In this use case, the nonlinear deformation in the curve mainly refers to the irregular changes in the contour curve that occur during the data acquisition process due to physiological differences between individuals. This is caused by individual differences in specific head shape areas of the user's head, resulting in a certain degree of distortion or deformation in the shape of the acquired contour curve. These deformations may originate from differences in the user's age, gender, or other physiological characteristics, and may lead to inconsistencies in the length of the contour curve or changes in local shape within the same age group or gender group.

[0053] When using 3D point cloud scanning technology to acquire contour curves of specific head shapes from different users, even with standardized preprocessing (such as resampling and normalization) to ensure topological consistency of coordinate points across contour curves, it is still difficult to completely eliminate natural variations between individuals. For example, in some cases, even two people belonging to the same user group (e.g., both males aged 20-25) may have subtle differences in their skull structures. Often, because the acquisition areas are prone to lesions and other physiological changes, some users may have acne or other physiological changes in that scalp area, resulting in numerous irregular protrusions on the contour curves. This can lead to subtle differences in skull structures within the same group, which will be reflected in the contour curves as non-linear stretching or compression.

[0054] The DTW method used in this step effectively handles this type of problem because it allows comparing the similarity between two sequences without strictly requiring their time axes to be aligned. This means that even if the overall lengths of the two curves are different or a portion of them has undergone local deformation, DTW can still find an optimal matching path to measure the distance between the two curves. The similarity matrix constructed in this way can more accurately capture the actual degree of similarity between different contour curves, thereby improving the quality and accuracy of subsequent clustering analysis.

[0055] S222: The optimal number of clusters k is determined by the elbow rule, and the calculation index is a weighted objective function of the silhouette coefficient and the sum of squared intra-cluster distances.

[0056] The elbow rule is a commonly used optimization method in cluster analysis to determine the optimal number of clusters (k value). In this step, the objective function incorporates a weighted evaluation metric combining the silhouette coefficient and the sum of squared intra-cluster distances.

[0057] The silhouette coefficient reflects the degree of closeness between a sample and other samples in its cluster, as well as the degree of separation from samples in other clusters. The value ranges from [-1, 1], and the closer the value is to 1, the better the clustering effect.

[0058] The sum of squared intra-cluster distances measures the compactness of the sample distribution within the same cluster; the smaller the value, the higher the intra-cluster consistency.

[0059] By calculating the objective function values ​​for different k values ​​and plotting an elbow plot, the optimal k value is found when the change in the objective function value becomes relatively flat. This method ensures that the clustering results have high internal consistency while avoiding overfitting.

[0060] Alternatively, this step can be replaced by the method in S212.

[0061] S223: During the iteration process, the centroid update adopts the weighted Fréchet mean method, and the weight coefficient is determined by the reciprocal of the Hausdorff distance between the curve and the current centroid curve.

[0062] In the traditional K-Means algorithm, the centroid is usually updated using the arithmetic mean method. However, for curve data, this method may not accurately reflect the shape characteristics. Therefore, this step introduces the weighted Fréchet mean method to update the centroid curve.

[0063] Fréchet means is a statistical method for non-Euclidean spatial data, particularly suitable for curve or path data. The weighting coefficients are determined by the reciprocal of the Hausdorff distance between the curve and the current centroid curve. This weighting method ensures that curves closer to the centroid have a greater influence on the new centroid, thus improving the robustness of centroid updates. This improvement significantly enhances the clustering process's adaptability to complex curve data.

[0064] S224: The termination condition is set to the average displacement of the centroid of the class after three consecutive iterations being less than 0.1 mm.

[0065] To ensure the convergence and stability of the clustering results, this step sets a strict termination condition: the algorithm stops running when the average displacement of all centroids in three consecutive iterations is less than 0.1 mm.

[0066] The average displacement refers to the change in the centroid curve during each iteration, typically measured by Euclidean distance or Hausdorff distance. Setting a threshold of 0.1mm is based on the requirements of practical applications, ensuring that the generated centroid-like curves meet the high-precision requirements of scalp adaptation. This termination condition not only guarantees algorithm efficiency but also avoids a decrease in clustering quality due to premature convergence.

[0067] The above steps, by introducing dynamic time-warped distance, the elbow rule, the weighted Fréchet mean method, and strict termination conditions, significantly improve the accuracy and robustness of contour curve clustering. These techniques work together to enable the generated centroid curves to better reflect the head shape characteristics of the user group, providing reliable data support for subsequent comb design.

[0068] S300: Based on a preset segmentation interval, the centroid-like curve is divided into several segmented centroid curves.

[0069] S300 includes:

[0070] S301: Based on the anatomical features of specific head shapes, a segmented centroid curve is created by dividing the centroid-like curve into N continuous segments. The boundary points of each segment maintain curvature continuity constraints.

[0071] Specifically, this method first rationally divides the centroid-like curve based on anatomical feature points of the head (such as contour points corresponding to different functional areas of the skull), forming multiple segmented centroid curves. These segments not only reflect the local morphological features of the head but also ensure a smooth transition of the overall curve through strict mathematical constraints. In particular, to ensure that the contour curve of the final generated comb conforming to the scalp has good geometric continuity, the boundary points between the segments are required to satisfy curvature continuity constraints, that is, the curvature change of adjacent segments at the connection point must be consistent.

[0072] In addition, the centroid-like curve can be segmented in this step by using equal arc lengths.

[0073] S400: Based on the similarity between the centroid curve of each segment and the corresponding segment curve of each contour curve in its cluster, determine at least one fitting candidate curve corresponding to the centroid curve of each segment. The fitting candidate curve is the segment curve in the cluster where the centroid curve of the segment is located, and whose similarity to it is greater than a preset threshold.

[0074] The S400 includes:

[0075] S401: Based on the hash values ​​of the point coordinates corresponding to the centroid curves and contour curves of the respective segments, perform vector transformation processing to generate high-dimensional curve vectors corresponding to the centroid curves and contour curves of the respective segments.

[0076] S402: Use cosine similarity to obtain the similarity between the high-dimensional curve vector corresponding to the centroid curve of a segment and the high-dimensional curve vector corresponding to any corresponding segment curve.

[0077] S403: If the similarity is greater than the preset similarity threshold, or the similarity ranking is among the top n, then the segment curve corresponding to the similarity is determined as the fitting candidate curve corresponding to the centroid curve of the segment. n can be 3.

[0078] S500: Establish a multi-objective optimization function that includes curvature continuity, second-order differentiability and anatomical fit indices, and use dynamic programming algorithm to perform a global optimal combination of all fitting candidate curves corresponding to the centroid curve to generate an initial contour point sequence.

[0079] Although the cluster center curve (i.e., the centroid curve) in S200 represents the overall characteristics of the cluster, it has an "average" property. Therefore, due to the influence of the curves at the edges of the cluster, there may be local unevenness or abnormal shape trends in the centroid curve. In other words, the centroid curve is not necessarily a true curve that perfectly matches the user's head shape.

[0080] Therefore, to further improve the contour curve of the comb that fits the scalp, this step requires adapting to different users by starting with the centroid curve of each segment and finding candidate fitting curves (real head shape curves) that are highly similar to it. These candidate fitting curves are closer to actual user data and can better reflect the actual head shape characteristics of that area.

[0081] Curvature continuity: Curvature continuity ensures that the generated contour curves transition smoothly at connection points, avoiding sharp angles or unnatural bends. This is especially important for designs that fit the scalp, as discontinuous curvature can lead to discomfort or prevent effective styling.

[0082] Second-order differentiability: Second-order differentiability ensures that the curve is not only continuous in position and direction, but also remains smooth in curvature changes. This property is crucial for generating comfortable and efficient distribution combs, as it directly affects the stability and comfort of the distribution comb during use.

[0083] Anatomical fit: The anatomical fit index takes into account the anatomical features of specific areas of the head, ensuring that the generated contour curve can better match the head shape of different users. This step, by combining actual anatomical data, improves the applicability of the parting comb to different user groups.

[0084] To achieve these goals, a dynamic programming algorithm is employed to perform a globally optimal combination of all candidate fitting curves corresponding to the centroid-like curve. This approach can find the best path or combination among multiple possible solutions. This process considers not only the local fit of individual curves but also the overall smoothness and physiological structure matching, thereby obtaining a better solution.

[0085] In addition, the number of candidate curves for fitting is extremely limited in this case. Therefore, an exhaustive method can be used to systematically evaluate the smoothness index of all combinations, thereby accurately selecting the optimal curve combination scheme.

[0086] S600: Optimize the smoothness of the contour curve formed by the initial contour point sequence to generate the contour curve corresponding to the side of the distribution comb that fits the scalp.

[0087] like Figure 1 As shown, the contour curve corresponding to the side of the comb that fits against the scalp in this embodiment can be the curve formed by the tips of multiple parting teeth 11 provided on the parting tooth plate 10 near the hair, or the contour curve corresponding to the cross section of the mounting surface of the multiple parting teeth 11.

[0088] S600 includes:

[0089] S601: Using a non-uniform rational B-spline curve, the second derivative continuity of the contour curve formed by the initial contour point sequence is optimized to generate the contour curve corresponding to the side of the distribution comb that fits against the scalp.

[0090] In this invention, the initial contour point sequence may contain certain noise or irregularities, and direct use may lead to misfitting of the comb to the scalp. Therefore, a non-uniform rational B-spline curve is used to optimize the second derivative continuity of the contour curve formed by the initial contour point sequence, so as to effectively improve the smoothness and adaptability of the contour curve, thereby ensuring that the comb fits the user's scalp better in actual use.

[0091] As another possible embodiment of the present invention, such as Figures 1 to 8 As shown, a distribution comb is also provided, comprising:

[0092] A parallel opening and closing mechanism and two distributing toothed plates 10. The two distributing toothed plates 10 are respectively connected to the two opening and closing control ends of the parallel opening and closing mechanism.

[0093] like Figures 1 to 3 and Figure 5 As shown, the parallel opening and closing mechanism includes a fixed frame 20, a first opening and closing unit, and a second opening and closing unit, both of which are rotatably mounted within the fixed frame 20.

[0094] The mounting bracket 20 has a C-shaped structure, and both the first and second opening / closing units are located within the internal space of the mounting bracket 20. This protects the opening / closing drive end and further prevents foreign objects from entering.

[0095] like Figures 4 to 6 As shown, the first opening and closing unit includes two first opening and closing drive rods 21. One end of each first opening and closing drive rod 21 is a first opening and closing connection end 212, and the other end is a first opening and closing drive end 211. Drive teeth are provided on the first opening and closing drive ends 211. The drive teeth on the two first opening and closing drive ends 211 mesh with each other. The two first opening and closing connection ends 212 are rotatably connected to the first hinge points 101 of the two distributing tooth plates 10, respectively. The two first opening and closing drive ends 211 are rotatably connected to the two second hinge points 201 on the fixed frame 20, respectively.

[0096] like Figures 4 to 6As shown, the second opening and closing unit includes two second opening and closing drive rods 22. One end of each second opening and closing drive rod 22 is a second opening and closing connection end 222, and the other end is a second opening and closing drive end 221. Drive teeth are provided on the second opening and closing drive end 221. The drive teeth on the two second opening and closing drive ends 221 mesh with each other. The two second opening and closing connection ends 222 are rotatably connected to the third hinge points 102 of the two distribution tooth plates 10, respectively. The two second opening and closing drive ends 221 are rotatably connected to the two fourth hinge points 202 on the fixed frame 20, respectively. In this embodiment, the drive teeth on the first opening and closing drive end 211 and the second opening and closing drive end 221 are the same as the teeth in a gear, and the first opening and closing drive end 211 and the second opening and closing drive end 221 can be regarded as a gear structure. Therefore, through the meshing connection of the gear structures of any two opening and closing drive ends, it can be ensured that the opening and closing movements between the two first opening and closing drive rods 21 or the two second opening and closing drive rods 22 are symmetrical and the opening and closing angles are synchronous.

[0097] like Figure 6 As shown, the distance between the first hinge point 101 and the third hinge point 102 on the same dispensing tooth plate 10 (L2 in the figure) is the same as the distance between the first opening / closing drive end 211 and the second opening / closing drive end 221 (L1 in the figure). The distance between the first opening / closing connecting end 212 and the first opening / closing drive end 211 of the first opening / closing drive rod 21 (R1 in the figure) is the same as the distance between the second opening / closing connecting end 222 and the second opening / closing drive end 221 of the second opening / closing drive rod 22 (R2 in the figure). The two straight lines formed by connecting the second hinge point 201 and the fourth hinge point 202 on the fixing frame 20 are arranged parallel to each other. This arrangement ensures that the initial state between the two dispensing tooth plates 10 is parallel to each other.

[0098] In this embodiment, by configuring the connection relationships between the opening / closing connection end and the closing drive end of the first and second opening / closing units and the fixed frame 20 and the distributing toothed plate 10, respectively, the first opening / closing drive rod 21, the second opening / closing drive rod 22, the fixed frame 20, and the distributing toothed plate 10 located on the same side can form a parallelogram linkage mechanism after connection, that is, by... Figure 6 The parallelogram formed by L1, L2, R1, and R2 is used to control the two parting plates 10 to move in a parallel posture during the opening process, thereby ensuring that the distance between the two parting plates 10 is the same, so as to ensure that all the hair between the two parting plates 10 is pressed down and the scalp is fully exposed.

[0099] In one possible embodiment of this application, such as Figure 4 and Figure 5 As shown, the first and second opening / closing units can be configured as follows:

[0100] Specifically, two first opening / closing drive rods 21 are symmetrically arranged, with the first opening / closing connecting end 212 and the first opening / closing driving end 211 both located on the side of the first opening / closing drive rod 21 closest to the distributing tooth plate 10. Two second opening / closing drive rods 22 are symmetrically arranged, with the second opening / closing connecting end 222 and the second opening / closing driving end 221 both located on the side of the second opening / closing drive rod 22 furthest from the distributing tooth plate 10. The two first opening / closing driving ends 211 are located within the internal space enclosed by the two second opening / closing drive rods 22.

[0101] This setting ensures that, in the fully closed state, the rotational hinge centers on the second opening / closing connection end 222, the second opening / closing drive end 221, the first opening / closing connection end 212, and the first opening / closing drive end 211 on the same side are on the same straight line. As a result, the two distributing tooth plates 10 can achieve mutual contact with a lower thickness.

[0102] In addition, such as Figures 1 to 3 As shown, the parting plate 10 has multiple parting teeth 11 at one end near the hair. These are used to press the hair in a better and more close manner.

[0103] And, as Figure 1 and Figure 7 As shown, it also includes two finger loops 13, which are respectively disposed on the outer surfaces of the two dispensing toothed plates 10. The two finger loops 13 are used to insert fingers, so that the opening and closing of the fingers drives the opening and closing of the two dispensing toothed plates 10. Specifically, the connection between the finger loops 13 and the dispensing toothed plates 10 can be in various ways, such as the finger loops 13 and the dispensing toothed plates 10 being integrally formed; or the finger loops 13 and the dispensing toothed plates 10 being detachably connected to facilitate the replacement of different types of finger loops or other handheld operating mechanisms to suit different users; or the finger loops 13 and the dispensing toothed plates 10 being rotatably connected, such as by a hinge, which allows for better adjustment of the angle for easier operation during use.

[0104] Furthermore, such as Figure 1 , Figure 2 and Figure 8 As shown, it also includes a parting angle 12, which is disposed on the parting tooth plate 10 or the fixing frame 20, with the tip of the parting angle 12 facing outward. The structure of the parting angle 12 is similar to the parting structure of the tail of an existing comb, and is used to part the hair. The number of parting angles 12 can be one or two.

[0105] Embodiments of the present invention also provide a non-transitory computer-readable storage medium that can be disposed in an electronic device to store at least one instruction or at least one program related to implementing a method in the method embodiments, wherein the at least one instruction or the at least one program is loaded and executed by the processor to implement the method provided in the above embodiments.

[0106] Embodiments of the present invention also provide an electronic device, including a processor and the aforementioned non-transitory computer-readable storage medium.

[0107] Embodiments of the present invention also provide a computer program product including program code, which, when the program product is run on an electronic device, causes the electronic device to perform the steps of the methods described above in various exemplary embodiments of the present invention.

[0108] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0109] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0110] In an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided.

[0111] Those skilled in the art will understand that various aspects of the present invention can be implemented as systems, methods, or program products. Therefore, various aspects of the present invention can be specifically implemented in the following forms: entirely in hardware, entirely in software (including firmware, microcode, etc.), or in a combination of hardware and software, collectively referred to herein as “circuit,” “module,” or “system.”

[0112] An electronic device according to this embodiment of the invention. The electronic device is merely an example and should not be construed as limiting the functionality or scope of the embodiments of the invention.

[0113] Electronic devices are manifested in the form of general-purpose computing devices. The components of an electronic device may include, but are not limited to: at least one processor, at least one memory, and a bus connecting different system components (including memory and processor).

[0114] The memory stores program code that can be executed by a processor, causing the processor to perform the steps described in the "Exemplary Methods" section above, according to various exemplary embodiments of the present invention.

[0115] The storage may include readable media in the form of volatile storage, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0116] The storage may also include programs / utilities having a set (at least one) of program modules, including but not limited to: an operating system, one or more applications, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0117] A bus can represent one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus that uses any of the various bus architectures.

[0118] The electronic device can also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication can be performed via input / output (I / O) interfaces. Furthermore, the electronic device can communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter. The network adapter communicates with other modules of the electronic device via a bus. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0119] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0120] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible embodiments, various aspects of the present invention may also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of the present invention described in the "Exemplary Methods" section above.

[0121] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0122] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0123] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0124] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0125] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0126] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0127] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for determining the profile of a distribution comb based on three-dimensional data acquisition, characterized in that, The method comprises the following steps: Obtaining contour curves of specific head shape regions of different user heads through a three-dimensional point cloud scanning technology, wherein the contour curves are composed of discrete coordinate point sequences, and the coordinate points between the contour curves maintain topological consistency; Performing clustering processing on all the contour curves to generate class centroid curves corresponding to the clustering clusters; the class centroid curve is a clustering center corresponding to a clustering cluster; Dividing the class centroid curves into a plurality of partitioned centroid curves based on a preset segmentation interval; Determining at least one fitting candidate curve corresponding to each partitioned centroid curve according to the similarity between each partitioned centroid curve and a section curve corresponding to each contour curve in the clustering cluster where the partitioned centroid curve is located; the fitting candidate curve is a section curve corresponding to the partitioned centroid curve in the clustering cluster where the partitioned centroid curve is located, and the similarity between the fitting candidate curve and the partitioned centroid curve is greater than a preset threshold value; Establishing a multi-objective optimization function comprising a curvature continuity, a second derivability and an anatomical fitness index, and performing global optimal combination on all the fitting candidate curves corresponding to the class centroid curves by using a dynamic programming algorithm to generate an initial contour point sequence; Performing smoothness optimization on a contour curve formed by the initial contour point sequence to generate a contour curve corresponding to a side of a scalp where a distribution comb is attached.

2. The method of claim 1, wherein, The three-dimensional point cloud scanning adopts a non-contact laser triangulation technology, and multi-view point cloud registration is achieved through an iterative closest point algorithm.

3. The method of claim 1, wherein, Obtaining contour curves of specific head shape regions of different user heads through a three-dimensional point cloud scanning technology comprises the following steps: Resampling discrete coordinate point sequences of the initially collected contour curves to ensure that all the contour curves finally obtained have the same number and distribution of coordinate points; Performing normalization processing on the coordinate points to eliminate scale differences.

4. The method of claim 3, wherein, The clustering processing adopts a K-Means clustering algorithm.

5. The method of claim 1, wherein, Dividing the class centroid curves into a plurality of partitioned centroid curves based on a preset segmentation interval comprises the following steps: Dividing the class centroid curves into N continuous section partitioned centroid curves according to anatomical feature points of the specific head shape regions of the head; the boundary points of each section maintain a curvature continuity constraint.

6. The method of claim 5, wherein, Determining at least one fitting candidate curve corresponding to each partitioned centroid curve according to the similarity between each partitioned centroid curve and a section curve corresponding to each contour curve in the clustering cluster where the partitioned centroid curve is located comprises the following steps: Performing vector transformation processing on point coordinate hash values respectively corresponding to the partitioned centroid curve and the section curve corresponding to the contour curve to generate high-dimensional curve vectors respectively corresponding to the partitioned centroid curve and the section curve corresponding to the contour curve; Obtaining the similarity between the high-dimensional curve vector corresponding to the partitioned centroid curve and the high-dimensional curve vector corresponding to any section curve using a cosine similarity; If the similarity is greater than a preset similarity threshold value, or the similarity ranking belongs to the top n, then the section curve corresponding to the similarity is determined as the fitting candidate curve corresponding to the partitioned centroid curve.

7. The method of claim 1, wherein, Performing smoothness optimization on a contour curve formed by the initial contour point sequence to generate a contour curve corresponding to a side of a scalp where a distribution comb is attached comprises the following steps: Performing second derivative continuity optimization on the contour curve formed by the initial contour point sequence by using a non-uniform rational B-spline curve to generate a contour curve corresponding to a side of a scalp where a distribution comb is attached.

8. The method of claim 1, wherein, The distribution comb comprises: Parallel opening and closing mechanism and two distribution tooth plates; the contour curve corresponding to the side of the scalp to which the distribution comb is attached is the contour curve corresponding to the side of the scalp to which the distribution tooth plate is attached; Two distribution tooth plates are respectively connected to two opening and closing control ends of the parallel opening and closing mechanism; The parallel opening and closing mechanism comprises a fixed frame, a first opening and closing unit and a second opening and closing unit, and the first opening and closing unit and the second opening and closing unit are both rotationally arranged in the fixed frame; The first opening and closing unit comprises two first opening and closing driving rods, one end of the first opening and closing driving rod is a first opening and closing connecting end, and the other end is a first opening and closing driving end, a driving tooth is arranged on the first opening and closing driving end, the driving teeth on the two first opening and closing driving ends are in meshing engagement, the two first opening and closing connecting ends are respectively rotationally connected to first hinged points of the two distribution tooth plates, and the two first opening and closing driving ends are respectively rotationally connected to two second hinged points on the fixed frame; The second opening and closing unit comprises two second opening and closing driving rods, one end of the second opening and closing driving rod is a second opening and closing connecting end, and the other end is a second opening and closing driving end, a driving tooth is arranged on the second opening and closing driving end, the driving teeth on the two second opening and closing driving ends are in meshing engagement, the two second opening and closing connecting ends are respectively rotationally connected to third hinged points of the two distribution tooth plates, and the two second opening and closing driving ends are respectively rotationally connected to two fourth hinged points on the fixed frame. The distance between the first hinged point and the third hinged point on the same distribution tooth plate is the same as the distance between the first opening and closing driving end and the second opening and closing driving end, the distance between the first opening and closing connecting end of the first opening and closing driving rod and the first opening and closing driving end is the same as the distance between the second opening and closing connecting end of the second opening and closing driving rod and the second opening and closing driving end, and the two straight lines formed by the second hinged point and the fourth hinged point on the fixed frame are arranged in parallel to each other. 9.A non-transitory computer-readable storage medium storing a computer program, the computer program comprising instructions causing a processor to perform the method according to any one of claims 1 to 8. The computer program is executed by the processor to realize the distribution comb contour determination method based on three-dimensional data acquisition.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the distribution comb contour determination method based on three-dimensional data acquisition.

Images