A skin and hair analysis method and system based on mobile screen projection interconnection detector

Abstract

The present invention relates to the technical field of skin and hair analysis, and in particular to a skin and hair analysis method and system based on a mobile screen projection interconnected detector. The method comprises the following steps: obtaining a skin and hair multispectral image set based on the camera of the detector detection end; performing multi-image spectral quantitative analysis on the skin and hair multispectral image set to construct a skin and hair pigment distribution map; performing contour detail feature analysis and detail image reconstruction on the skin and hair multispectral image set to construct a detail reconstructed skin and hair image; performing fine-grained visual recognition of hair follicles on the detail reconstructed skin and hair image to obtain the spatial position coordinates of the hair follicles; performing regional hair feature change trend analysis and feature area clustering division on the skin pigment distribution map and the hair follicle density distribution trend model to obtain multiple change trend feature areas. The present invention realizes fast and efficient skin and hair analysis, and can visualize the analysis results on the mobile terminal and the detector display device.

Description

Technical Field

[0001] The present invention relates to the technical field of skin and hair analysis, and in particular to a skin and hair analysis method and system based on a mobile terminal projection screen interconnection detector. Background Art

[0002] The condition of personal skin and hair is one of the important indicators to measure the health status of the human body. With the increasing demand for beauty and health, it is becoming more and more important to accurately evaluate and monitor the condition of skin and hair. Traditional skin and hair analysis methods usually rely on professional testing instruments, which not only require professional operation, but also have problems such as long testing time and inability to monitor in real time. Traditional testing instruments cannot connect to user terminal devices and cannot present skin and hair analysis results to users in real time and quickly. At the same time, mobile phones, as the most popular smart terminal devices at present, are reshaping the medical and health field with their powerful computing power and rich functions, bringing new opportunities for personal health testing. Based on this, it is urgent to explore a skin and hair analysis method based on mobile smart terminal screen projection and interconnection detectors, using smart mobile terminals such as mobile phones and tablets as carriers of data analysis, and through screen projection and interconnection detection equipment, to achieve fast, efficient and non-invasive detection of skin and hair conditions. Summary of the invention

[0003] In order to solve the above-mentioned technical problems, the present invention proposes a skin and hair analysis method and system based on a mobile screen projection interconnection detector to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above-mentioned object, the present invention provides a skin and hair analysis method based on a mobile terminal screen projection interconnected detector, which is implemented based on a mobile terminal and a detector based on real-time communication, wherein the detector includes a detector detection terminal and a detector display device, and the mobile terminal is used to provide computing power for data analysis for the detector, including the following steps:

[0005] Step S1: obtaining a skin multispectral image set based on the camera at the detection end of the detector; performing multi-image spectral quantitative analysis on the skin multispectral image set to construct a skin pigment distribution map;

[0006] Step S2: performing contour detail feature analysis on the skin multispectral image set, and reconstructing the detail image to construct a detail reconstructed skin and hair image;

[0007] Step S3: performing fine visual recognition of hair follicles on the detailed reconstructed skin hair image to obtain the spatial position coordinates of the hair follicles; performing hair follicle density distribution analysis based on the spatial position coordinates of the hair follicles to construct a hair follicle density distribution trend model;

[0008] Step S4: performing regional hair feature change trend analysis on the skin pigment distribution map and the hair follicle density distribution trend model, and performing feature region clustering to obtain multiple change trend feature regions;

[0009] Step S5: performing multi-scenario growth time series evolution simulation on multiple change trend feature areas, and predicting the growth trend change, to construct a hair area growth trend evolution curve;

[0010] Step S6: Evaluate the hair growth status of the hair area growth trend evolution curve to obtain a growth status evaluation result; and visualize the display device of the detector based on the growth status evaluation result to present the hair analysis result.

[0011] The present invention obtains more information about the skin and hair by acquiring a set of multispectral images of the skin, provides a data basis for subsequent analysis, performs multi-image spectral quantitative analysis, constructs a skin pigment distribution map to understand the pigment distribution of the hair, and provides a basis for subsequent analysis and identification. Through contour detail feature analysis and detail image reconstruction, the detailed features of the skin and hair are highlighted, the understanding and display of the hair structure are improved, and a detail reconstructed skin and hair image is constructed to observe and analyze the microstructure of the hair. Through fine visual identification of hair follicles and analysis of hair follicle density distribution, the spatial position coordinates and hair follicle density information of the hair follicles are accurately obtained, and a hair follicle density distribution trend model is constructed to understand the distribution of hair follicles on the skin surface and Density change trend, conduct regional hair feature change trend analysis and feature area clustering, identify and classify hair feature change trends in different regions, obtain multiple change trend feature areas to gain an in-depth understanding of hair features and their changing patterns in different regions, simulate hair growth process and predict its changing trend through multi-scenario growth time series evolution simulation and growth trend change prediction, construct hair area growth trend evolution curve to understand hair growth patterns and trends, evaluate hair growth status, obtain growth status evaluation results, comprehensively evaluate hair health status and growth status, and present hair analysis results visually on the screen to intuitively display analysis results, improve communication efficiency and clarity of result presentation.

[0012] Preferably, step S1 comprises the following steps:

[0013] Step S11: acquiring a skin multispectral image set based on the camera at the detector end;

[0014] Step S12: performing multi-image spectral quantitative analysis on the skin multi-spectral image set to extract image spectral feature vectors;

[0015] Step S13: performing regional color difference analysis on the image spectrum feature vector to obtain color difference data of different image regions;

[0016] Step S14: performing color space difference decomposition on the skin multispectral image set according to the color difference data of different image regions to generate hair pigment region feature data;

[0017] Step S15: performing pigment distribution fitting on the hair pigment region characteristic data to construct a skin pigment distribution map.

[0018] The present invention obtains rich spectral information by acquiring a multi-spectral image set of skin, provides a data basis for subsequent analysis, performs multi-image spectral quantitative analysis, extracts image spectral feature vectors, quantifies spectral information, provides data support for subsequent analysis, performs regional color difference analysis on image spectral feature vectors, obtains color difference data of different image regions, helps understand the color difference situation of different regions, performs color space difference decomposition based on the color difference data of different image regions, generates hair pigment regional feature data, distinguishes the characteristics of different color spaces, provides more specific pigment distribution information for the hair pigment regional feature data, performs pigment distribution fitting on the hair pigment regional feature data, constructs a skin pigment distribution map, understands the distribution of hair pigment in different regions, and the constructed skin pigment distribution map provides a visual reference basis for subsequent analysis and diagnosis.

[0019] Preferably, the specific steps of step S2 are:

[0020] Step S21: performing hair root recognition on the skin multispectral image set to mark the hair root area;

[0021] Step S22: performing brightness enhancement processing on the hair root area to obtain a brightness enhanced hair image;

[0022] Step S23: performing hair contour analysis on the brightness enhanced hair image to extract hair contour lines;

[0023] Step S24: performing contour enlargement processing on the hair contour line to obtain a hair contour enlarged image;

[0024] Step S25: performing contour detail feature analysis on the hair contour detail enlarged image to generate hair contour detail features;

[0025] Step S26: reconstructing the detail image of the brightness enhanced hair image according to the detail features of the hair contour, and constructing a detail reconstructed skin and hair image.

[0026] The present invention identifies the hair roots of a skin multispectral image set, accurately locates and marks the starting point of hair growth, provides an accurate basis for subsequent analysis, performs brightness enhancement processing on the hair root area, highlights the brightness characteristics of the hair roots, and improves the visualization effect of the hair root area, performs hair contour analysis on the brightness enhanced hair image, extracts the hair contour line, accurately captures the shape and contour information of the hair, performs contour enlargement processing on the hair contour line to obtain a hair contour enlarged image, enhances the display effect of the hair contour, and makes the hair morphology clearer, performs contour detail feature analysis on the hair contour detail enlarged image, highlights the detail features of the hair contour, improves the understanding and display of the hair structure, reconstructs the detail image of the brightness enhanced hair image according to the hair contour detail features, constructs a detail reconstructed skin hair image, and deeply observes the microstructure and features of the hair.

[0027] Preferably, step S3 specifically comprises the following steps:

[0028] Step S31: performing fine visual recognition of hair follicles on the detailed reconstructed skin and hair image, marking each hair follicle feature point;

[0029] Step S32: Calculate the spatial position of each hair follicle feature point to obtain the spatial position coordinates of the hair follicle;

[0030] Step S33: calculating the distance between hair follicles according to the spatial position coordinates of the hair follicles, thereby obtaining a plurality of distances between hair follicles;

[0031] Step S34: performing hair follicle density distribution analysis on each hair follicle feature point based on a plurality of distances between hair follicles to generate hair follicle density distribution data;

[0032] Step S35: Perform density trend mapping on the hair follicle density distribution data to construct a hair follicle density distribution trend model.

[0033] The present invention performs fine visual recognition of hair follicles on detailed reconstructed skin and hair images, marks each hair follicle feature point, accurately captures the position and morphological characteristics of each hair follicle, calculates the spatial position of each hair follicle feature point, obtains the spatial position coordinates of the hair follicle, establishes a spatial distribution model of the hair follicle, calculates the distance between hair follicles according to the spatial position coordinates of the hair follicles, obtains distance data between multiple hair follicles, understands the distribution density and spatial relationship between hair follicles, provides data support for density distribution analysis, performs hair follicle density distribution analysis based on the distance between multiple hair follicles, reveals the density distribution of hair follicles on the skin, understands the law and change trend of hair growth by analyzing the hair follicle density, performs density trend mapping on the hair follicle density distribution data, constructs a hair follicle density distribution trend model, predicts the change trend of hair follicle density, and provides a scientific basis for skin hair growth and density regulation.

[0034] Preferably, the specific steps of step S4 are:

[0035] Step S41: performing image segmentation processing on the detail reconstructed skin and hair image to obtain multiple image regions;

[0036] Step S42: performing regional hair feature change trend analysis on multiple image regions based on the skin pigment distribution map and the hair follicle density distribution trend model to generate feature change trends of different image regions;

[0037] Step S43: performing change trend similarity analysis on the feature change trends of different image regions to generate regional change trend similarities;

[0038] Step S44: clustering and dividing the detail reconstructed skin and hair image into characteristic regions according to the similarity of the regional change trends, thereby obtaining a plurality of change trend characteristic regions.

[0039] The present invention performs image segmentation processing on a detailed reconstructed skin and hair image to divide the image into multiple regions, each region representing a different hair density or feature, and extracts the hair region from the overall image to provide a basis for subsequent analysis; based on a skin pigment distribution map and a hair follicle density distribution trend model, characteristic change trend analysis is performed on multiple image regions to reveal the changing laws of hair characteristics in different regions, understand the growth conditions and characteristic changes of hair in different regions, and provide a basis for personalized care and treatment; similarity analysis is performed on characteristic change trends in different image regions to evaluate the similarities and differences between regions, identify regional groups with similar characteristic change trends, and provide a basis for subsequent cluster analysis; characteristic region clustering and division is performed on the detailed reconstructed skin and hair image according to the similarity of regional change trends to obtain multiple change trend characteristic regions, and regions with similar features are clustered together to provide support for personalized analysis and processing of different characteristic regions.

[0040] Preferably, the specific steps of step S5 are:

[0041] Step S51: performing a multi-scenario growth time series evolution simulation on a plurality of change trend characteristic regions to generate multi-scenario time series evolution simulation data;

[0042] Step S52: performing growth time series response rate analysis on the multi-scenario time series evolution simulation data to obtain hair growth time series response rate data;

[0043] Step S53: predicting the growth trend change of the hair growth time series response rate data to generate hair growth trend prediction data;

[0044] Step S54: performing stage evolution trajectory analysis on the hair growth trend prediction data to construct a hair area growth trend evolution curve.

[0045] The present invention simulates the process and changes of hair growth in different scenarios by performing multi-scenario growth time-series evolution simulation on multiple change trend characteristic areas, analyzes the growth of hair under different conditions, and provides a data basis for subsequent growth rate analysis. It performs growth time-series response rate analysis on multi-scenario time-series evolution simulation data, evaluates the growth rate and response of hair under different conditions, understands the dynamic changes and response characteristics of hair growth, and provides a basis for growth trend prediction. It predicts the growth trend change according to the hair growth time-series response rate data, generates hair growth trend prediction data, predicts the growth trend change trend of hair in the future, and provides a reference for the formulation of personalized care and treatment plans. It performs stage evolution trajectory analysis on the hair growth trend prediction data, constructs a hair area growth trend evolution curve, and reveals the stage changes and trends of hair growth.

[0046] Preferably, the specific steps of step S51 are:

[0047] The growth trend of multiple change trend characteristic areas is deduced to obtain the growth trend rules of different areas;

[0048] Define multi-scenario growth environment parameters;

[0049] Based on the growth environment parameters of multiple scenarios, the time domain growth numerical simulation calculation is performed on the growth trend law of different regions to obtain the regional growth trend parameters of multiple scenarios;

[0050] Based on the regional growth trend parameters of multiple scenarios, multi-time point growth evolution simulation is performed to generate multi-scenario time series evolution simulation data.

[0051] The present invention deduces growth trends of multiple change trend characteristic areas, reveals the growth laws and trends of different areas, understands the differences in hair growth in different areas, defines multi-scenario growth environment parameters to simulate hair growth under different conditions, takes into account the impact of the environment on the growth trend, simulates growth conditions that are closer to the actual situation, and improves the accuracy of the simulation results. Based on the multi-scenario growth environment parameters, time-domain growth numerical simulation calculations are performed on the regional growth trend laws to obtain regional growth trend parameters for multiple scenes, quantify the characteristics and trends of hair growth in different scenes, and provide data support for subsequent simulation and analysis. Multi-time point growth evolution simulation is performed based on the regional growth trend parameters of multiple scenes to generate multi-scenario time series evolution simulation data, simulate the growth change process of hair in different scenes, and provide a basis for growth trend prediction and personalized care plans.

[0052] Preferably, the specific steps of step S6 are:

[0053] Step S61: identifying the periodic fluctuation amplitude of the hair region growth trend evolution curve, and extracting the periodic fluctuation amplitude of the trend curve;

[0054] Step S62: calculating the trend peak time point of the hair area growth trend evolution curve to generate multiple trend peak time points;

[0055] Step S63: evaluating the hair growth status of multiple situation peak time points and the periodic fluctuation amplitudes of the situation curve, thereby obtaining a growth status evaluation result;

[0056] Step S64: Visually project the growth status assessment results and the hair area growth trend evolution curve onto the detector display device to present the hair analysis results in detail.

[0057] The present invention identifies the periodic fluctuation amplitude of the hair area growth trend evolution curve, extracts the periodic fluctuation of the trend curve, identifies the periodic changes in the hair growth process, and provides an important reference for subsequent growth status evaluation. The trend peak time point of the hair area growth trend evolution curve is calculated to determine the peak time point in the curve, that is, the peak period of the growth trend, and identifies the peak period in the hair growth process, providing key information for growth status evaluation and prediction. In combination with multiple trend peak time points and the periodic fluctuation amplitude of the trend curve, the hair growth status is evaluated to fully understand the state and trend of hair growth, providing a basis for formulating personalized care plans and predicting growth conditions. The growth status evaluation results and the hair area growth trend evolution curve are projected onto the display device of the detector to achieve visual display, intuitively display the hair analysis results, provide user-friendly data display and interpretation methods, and facilitate user understanding and application.

[0058] In this specification, a skin and hair analysis system based on a mobile terminal projection screen interconnected detector is provided, the skin and hair analysis system based on the mobile terminal projection screen interconnected detector includes a mobile terminal and a detector, and the mobile terminal and the detector perform real-time data transmission through a wired or wireless network, the mobile terminal is used to execute the algorithm program of the skin and hair analysis method based on the mobile terminal projection screen interconnected detector as described above, the detector includes a detector detection end and a detector display device, the detector detection end is used to obtain multi-spectral image data of skin and hair, and the detector display device is used to synchronize the screen of the mobile terminal and display network push information; the skin and hair analysis system based on the mobile terminal projection screen interconnected detector specifically includes:

[0059] The pigment distribution module is used to obtain a skin multispectral image set based on the camera at the detector end; perform multi-image spectral quantitative analysis on the skin multispectral image set to construct a skin pigment distribution map;

[0060] An image reconstruction module is used to perform contour detail feature analysis on a skin multispectral image set, and to reconstruct detail images to construct detail reconstructed skin and hair images;

[0061] The density distribution module is used to perform fine visual recognition of hair follicles on the detailed reconstructed skin hair image, so as to obtain the spatial position coordinates of the hair follicles; perform hair follicle density distribution analysis based on the spatial position coordinates of the hair follicles, and construct a hair follicle density distribution trend model;

[0062] The feature change trend module is used to analyze the regional hair feature change trend based on the skin pigment distribution map and the hair follicle density distribution trend model, and to perform feature regional clustering and division, thereby obtaining multiple change trend feature regions;

[0063] The growth trend evolution module is used to simulate the time-series evolution of growth in multiple scenarios for multiple change trend feature areas, predict the growth trend changes, and construct the hair area growth trend evolution curve;

[0064] The condition assessment module is used to assess the hair growth condition based on the growth trend evolution curve of the hair area, so as to obtain the growth condition assessment result; based on the growth condition assessment result, a visual projection is performed to present the hair analysis result.

[0065] The present invention performs multi-image spectral quantitative analysis through a multi-spectral image set, can accurately capture the pigment distribution of skin and hair, construct a skin pigment distribution map, provide basic data for subsequent analysis, perform contour detail feature analysis on the multi-spectral image set and reconstruct detailed images, show the detailed features of skin and hair, provide clearer and more accurate skin and hair images, and provide a more reliable data basis for subsequent analysis. Through the refined visual recognition and density distribution analysis of hair follicles, the spatial position coordinates and density distribution trend model of hair follicles are obtained, which can deeply understand the distribution of hair follicles and provide more detailed data support for subsequent analysis. By analyzing the skin pigment distribution map and hair follicle density analysis, The hair growth trend can be analyzed and predicted based on the growth trend of the hair area. The hair growth condition can be evaluated based on the hair area growth trend evolution curve to obtain the growth condition evaluation results. Personalized care suggestions can be provided based on the evaluation results. The hair analysis results can be presented through visual projection to help users understand their own hair health status and further improve the care plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1This is a schematic diagram of the steps of a skin and hair analysis method based on a mobile terminal screen projection interconnection detector of the present invention;

[0067] Figure 2 Detailed implementation flow chart of step S1;

[0068] Figure 3 Detailed implementation flow chart of step S2;

[0069] Figure 4 is a schematic diagram of a detailed implementation process of step S3;

[0070] Figure 5 This is a structural diagram of the mobile screen projection interconnection tester. DETAILED DESCRIPTION

[0071] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0072] The present application example provides a skin and hair analysis method and system based on a mobile screen projection interconnected detector. The execution subject of the skin and hair analysis method and system based on a mobile screen projection interconnected detector includes but is not limited to the following: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0073] See also Figures 1 to 4 The present invention provides a skin and hair analysis method based on a mobile terminal screen projection interconnected detector, which is implemented by a mobile terminal and a detector based on real-time communication, wherein the detector includes a detector detection terminal and a detector display device, and the mobile terminal is used to provide computing power for data analysis for the detector, specifically including the following steps:

[0074] Step S1: obtaining a skin multispectral image set based on the camera at the detection end of the detector; performing multi-image spectral quantitative analysis on the skin multispectral image set to construct a skin pigment distribution map;

[0075] Step S2: performing contour detail feature analysis on the skin multispectral image set, and reconstructing the detail image to construct a detail reconstructed skin and hair image;

[0076] Step S3: performing fine visual recognition of hair follicles on the detailed reconstructed skin hair image to obtain the spatial position coordinates of the hair follicles; performing hair follicle density distribution analysis based on the spatial position coordinates of the hair follicles to construct a hair follicle density distribution trend model;

[0077] Step S4: performing regional hair feature change trend analysis on the skin pigment distribution map and the hair follicle density distribution trend model, and performing feature region clustering to obtain multiple change trend feature regions;

[0078] Step S5: performing multi-scenario growth time series evolution simulation on multiple change trend feature areas, and predicting the growth trend change, to construct a hair area growth trend evolution curve;

[0079] Step S6: Evaluate the hair growth status of the hair area growth trend evolution curve to obtain a growth status evaluation result; and visualize the display device of the detector based on the growth status evaluation result to present the hair analysis result.

[0080] The present invention obtains more information about the skin and hair by acquiring a set of multispectral images of the skin, provides a data basis for subsequent analysis, performs multi-image spectral quantitative analysis, constructs a skin pigment distribution map to understand the pigment distribution of the hair, and provides a basis for subsequent analysis and identification. Through contour detail feature analysis and detail image reconstruction, the detailed features of the skin and hair are highlighted, the understanding and display of the hair structure are improved, and a detail reconstructed skin and hair image is constructed to observe and analyze the microstructure of the hair. Through fine visual identification of hair follicles and analysis of hair follicle density distribution, the spatial position coordinates and hair follicle density information of the hair follicles are accurately obtained, and a hair follicle density distribution trend model is constructed to understand the distribution of hair follicles on the skin surface and Density change trend, conduct regional hair feature change trend analysis and feature area clustering, identify and classify hair feature change trends in different regions, obtain multiple change trend feature areas to gain an in-depth understanding of hair features and their changing patterns in different regions, simulate hair growth process and predict its changing trend through multi-scenario growth time series evolution simulation and growth trend change prediction, construct hair area growth trend evolution curve to understand hair growth patterns and trends, evaluate hair growth status, obtain growth status evaluation results, comprehensively evaluate hair health status and growth status, and present hair analysis results visually on the screen to intuitively display analysis results, improve communication efficiency and clarity of result presentation.

[0081] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a skin and hair analysis method based on a mobile terminal screen projection interconnection detector of the present invention. In this example, the steps of the skin and hair analysis method based on a mobile terminal screen projection interconnection detector include:

[0082] Step S1: obtaining a skin multispectral image set based on the camera at the detection end of the detector; performing multi-image spectral quantitative analysis on the skin multispectral image set to construct a skin pigment distribution map;

[0083] In this embodiment, a multi-spectral imaging camera on the detection end of the detector is used to control the light source and the filter to obtain a multi-channel spectral image covering the visible light to near-infrared band, ensure good imaging conditions, such as uniform lighting and clear imaging focus, so as to obtain high-quality multi-spectral image data, collect images at multiple angles and positions to obtain comprehensive skin and hair information, and pre-process the acquired multi-spectral image set, including image registration, denoising, optical correction, etc., to ensure data quality. For the image of each spectral channel, statistical features within the region of interest (ROI), such as average reflectance value, variance, etc., are extracted, and the ROI features of different spectral channels are combined into a high-dimensional feature vector to describe the spectral features of the region. A clustering algorithm (such as K-means) is used to classify all ROI features to divide different pigment distribution areas, and the classification results are mapped back to the original image space to construct a visual map reflecting the distribution of skin and hair pigments.

[0084] Step S2: performing contour detail feature analysis on the skin multispectral image set, and reconstructing the detail image to construct a detail reconstructed skin and hair image;

[0085] In this embodiment, the extracted contour features are analyzed, including calculating geometric features such as contour line length, curvature, and the number of inflection points, and texture features of the contour are extracted using a texture analysis method (such as a gray level co-occurrence matrix, a Gabor filter, etc.). The geometric features and texture features are combined into a high-dimensional feature vector for describing the detail information of the contour. A machine learning or deep learning model, such as a super-resolution convolutional network, is used to learn the mapping relationship between the contour details and the original image from the multispectral image. The learned model is applied to the original multispectral image to generate a reconstructed image containing richer detail information. The reconstructed image is post-processed, such as sharpening and denoising, to further improve the image quality. The detailed reconstructed image is fused with the original multispectral image to obtain a final skin and hair image containing richer details. The fusion result is manually or automatically evaluated for quality to ensure that the image detail information is effectively retained and enhanced.

[0086] Step S3: performing fine visual recognition of hair follicles on the detailed reconstructed skin hair image to obtain the spatial position coordinates of the hair follicles; performing hair follicle density distribution analysis based on the spatial position coordinates of the hair follicles to construct a hair follicle density distribution trend model;

[0087] In this embodiment, an image segmentation algorithm (such as semantic segmentation or instance segmentation) is used to process the skin hair image after detail reconstruction, and the hair follicle area is segmented from the background. The segmented hair follicle area is further subjected to feature extraction and classification. For example, a deep learning model is used to identify different types of hair follicles. Through these visual recognition technologies, the spatial coordinate position of each hair follicle in the image is accurately located. According to the obtained hair follicle coordinate position information, the distribution density of hair follicles in different areas is calculated. The density value is mapped to a two-dimensional plane using methods such as kernel density estimation and Voronoi diagram, and a hair follicle density distribution map is constructed. The density distribution map is analyzed to identify high-density areas and low-density areas, providing a basis for subsequent growth trend analysis. The hair follicle density distribution maps obtained at different time points are compared and analyzed to identify the change trend of the density value. A mathematical model describing the evolution law of hair follicle density distribution is constructed using a time series analysis or machine learning method. The model predicts the change of hair follicle density in the future period of time, providing a quantitative basis for growth trend analysis.

[0088] Step S4: performing regional hair feature change trend analysis on the skin pigment distribution map and the hair follicle density distribution trend model, and performing feature region clustering to obtain multiple change trend feature regions;

[0089] In this embodiment, time series analysis is performed on the hair characteristics (pigment distribution, density, etc.) of different regions to identify the change trends of the hair characteristics in different regions, such as increase, decrease, fluctuation, etc., and the change trends are quantitatively described. According to the characteristics of the change trends, the entire skin hair region is preliminarily divided, and the division is based on the change rate, amplitude, etc. of the hair characteristics. Based on the preliminary region division results, as input features, a clustering algorithm (such as K-means, hierarchical clustering, etc.) is used for unsupervised learning. Through cluster analysis, regions with similar hair characteristic change trends are classified into the same category to form a more refined feature region division. According to the silhouette coefficient or other indicators of the clustering results, the optimal number of clusters is determined to obtain the final feature region division scheme. Through the analysis and clustering of the above steps, we obtain a plurality of different change trend feature regions, and the change trends of the hair characteristics in each region are relatively consistent. For each feature region, we further describe the change of its hair characteristics, such as the increase or decrease of the average pigment concentration, the change of the average density, etc. These change trend feature regions provide a more refined and accurate data basis for the subsequent growth trend analysis.

[0090] Step S5: performing multi-scenario growth time series evolution simulation on multiple change trend feature areas, and predicting the growth trend change, to construct a hair area growth trend evolution curve;

[0091] In this embodiment, a corresponding growth time series evolution model is constructed for each region, and different external environmental conditions or intervention measures are set as input parameters according to actual conditions, such as nutritional status, hormone levels, disease factors, etc., and the growth time series evolution process of each characteristic region under different scenarios is predicted by numerical simulation, including changes in indicators such as hair density and pigment content. The evolution results under different scenarios are compared and analyzed to understand the degree of influence of various factors on hair growth. The growth trend of each characteristic region is predicted and analyzed, focusing on the change trend of hair growth indicators (density, pigment content, etc.) in each region, and predicting the change of growth trend in the future. A growth trend change prediction model is established by using time series analysis, gray model, neural network and other methods, and a sensitivity analysis is performed on the prediction results to understand the degree of influence of key influencing factors on the growth trend. The growth trend change prediction results of each characteristic region are integrated and plotted into a growth trend evolution curve. The curve reflects the growth trend changes of different characteristic regions in the time series, intuitively showing the differences between the regions, and combined with the actual situation, the inflection point and fluctuation trend of the curve are deeply analyzed to reveal the potential physiological mechanism. The growth trend evolution curve provides a visual data basis for subsequent comprehensive analysis and decision support.

[0092] Step S6: Evaluate the hair growth status of the hair area growth trend evolution curve to obtain a growth status evaluation result; perform a visual projection based on the growth status evaluation result to present the hair analysis result.

[0093] In this embodiment, a comprehensive evaluation is performed on the hair growth status of each characteristic area. For each curve, key indicators such as its change trend, fluctuation frequency, and peak characteristics are analyzed, and interpreted in combination with actual physiological knowledge to determine whether the hair growth in each area is in a good, normal, or abnormal state, and the abnormal state is further divided into mild, moderate, and severe abnormalities. Evaluation standards and quantitative indicators for hair growth status are formulated to ensure that the evaluation results are objective, fair, and comparable. The evaluation results of each characteristic area are integrated to obtain a global hair growth status evaluation result, and the hair growth status evaluation result is presented in an intuitive visual form. The growth status of each area is intuitively marked on the human skin map using heat maps, color coding, data charts, etc. Different colors or logos are used according to different levels of the evaluation results to clearly display the hair growth status of each area. An interactive interface is set to allow users to zoom in and rotate to observe different angles to obtain more analysis details, and the visualization results are output in the form of screen projection.

[0094] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0095] Step S11: acquiring a skin multispectral image set based on the camera at the detector end;

[0096] Step S12: performing multi-image spectral quantitative analysis on the skin multi-spectral image set to extract image spectral feature vectors;

[0097] Step S13: Perform regional color difference analysis on the image spectral feature vector to obtain color difference data of different image regions:

[0098] Step S14: performing color space difference decomposition on the skin multispectral image set according to the color difference data of different image regions to generate hair pigment region feature data;

[0099] Step S15: performing pigment distribution fitting on the hair pigment region characteristic data to construct a skin pigment distribution map.

[0100] In this embodiment, the multispectral imaging camera on the detection end of the detector is used to image the skin and hair of the sample to be tested. During the imaging process, it is necessary to ensure that the lighting conditions are stable and avoid interference from ambient light sources, obtain a multispectral image set containing spectral information of different bands, and provide a data basis for subsequent spectral analysis. The multispectral image set is processed, and the multi-band spectral information corresponding to each image pixel is extracted. For each pixel, a feature vector containing different spectral band values ​​is constructed for subsequent spectral analysis. After this step, detailed image spectral feature data is obtained, which lays the foundation for regional color difference analysis. The extracted spectral feature vector is used to calculate the color difference values ​​between different pixel points, and the entire image is divided into several regions of interest. The color difference values ​​of each region are calculated separately. The average color difference within the domain is used to obtain the color difference data between different image areas, which provides a reference for the subsequent pigment distribution analysis. The obtained regional color difference data is used to perform difference decomposition of the multispectral image in color space, determine the key color channels reflecting the hair pigment distribution, and extract regional features for these channels to generate characteristic data describing the hair pigment distribution in different image areas, which provides a basis for the subsequent pigment distribution analysis. Mathematical models, such as Gaussian mixture models, are used to perform fitting analysis on the hair pigment regional characteristic data. Through the fitting process, the distribution characteristics of hair pigment in different areas are determined, including peak position, distribution width, etc. The fitting results are visualized to construct a map describing the pigment distribution of the entire hair sample, which provides an intuitive reference for the subsequent pigment analysis.

[0101] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0102] Step S21: performing hair root recognition on the skin multispectral image set to mark the hair root area;

[0103] Step S22: performing brightness enhancement processing on the hair root area to obtain a brightness enhanced hair image;

[0104] Step S23: performing hair contour analysis on the brightness enhanced hair image to extract hair contour lines;

[0105] Step S24: performing contour enlargement processing on the hair contour line to obtain a hair contour enlarged image;

[0106] Step S25: performing contour detail feature analysis on the hair contour detail enlarged image to generate hair contour detail features;

[0107] Step S26: reconstructing the detail image of the brightness enhanced hair image according to the detail features of the hair contour, and constructing a detail reconstructed skin and hair image.

[0108] In this embodiment, image processing techniques such as edge detection and region growing are used to analyze and process the multispectral image, determine the position and range of the hair root in the image, mark and segment the hair root region, provide targeted region positioning for subsequent brightness enhancement and contour analysis, perform local brightness adjustment and enhancement processing on the identified hair root region, use image processing algorithms such as histogram equalization and adaptive filtering to improve the overall brightness of the hair region, highlight the hair details through brightness enhancement, and provide a better image basis for subsequent contour analysis, use edge detection, shape analysis and other techniques to process the brightness enhanced hair image, identify and extract the contour line of the hair in the image, obtain contour information describing the shape and details of the hair, and extract the contour information of the hair root region. Based on the hair contour line, pixel-level contour expansion processing is performed, and morphological operations such as dilation and erosion are used to appropriately expand the width and range of the contour line. The expanded contour line better covers the overall shape and detail information of the hair. For the hair contour enlarged image, the shape, texture and other features of the contour line are extracted. Digital image processing techniques, such as texture analysis and shape descriptors, are used to quantitatively describe the detailed features of the hair contour. These detailed features reflect the microscopic structure of the hair and provide a basis for subsequent image reconstruction. The extracted hair contour detail features are used to reconstruct the brightness enhanced hair image, and the detail feature information is integrated into the original image to generate a reconstructed image with richer details. On the basis of retaining the brightness information of the original image, the microscopic details of the hair are restored and enhanced.

[0109] In this embodiment, reference Figure 4 The above is a schematic flow chart of the detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0110] Step S31: performing fine visual recognition of hair follicles on the detailed reconstructed skin and hair image, marking each hair follicle feature point;

[0111] Step S32: Calculate the spatial position of each hair follicle feature point to obtain the spatial position coordinates of the hair follicle;

[0112] Step S33: calculating the distance between hair follicles according to the spatial position coordinates of the hair follicles, thereby obtaining a plurality of distances between hair follicles;

[0113] Step S34: performing hair follicle density distribution analysis on each hair follicle feature point based on a plurality of distances between hair follicles to generate hair follicle density distribution data;

[0114] Step S35: Perform density trend mapping on the hair follicle density distribution data to construct a hair follicle density distribution trend model.

[0115] In this embodiment, computer vision technology, such as a deep learning target detection algorithm, is used to analyze the generated detailed reconstructed image, identify the position and features of each hair follicle in the image, and mark the feature points of each hair follicle on the image to accurately locate each independent hair follicle in the image. The two-dimensional or three-dimensional spatial coordinates of each hair follicle in the image coordinate system are calculated based on the marked hair follicle feature points. Image processing technology, such as feature point matching and projection transformation, is used to map the hair follicle feature points to the actual spatial coordinate system to obtain the accurate position information of each hair follicle on the skin surface. The obtained hair follicle spatial coordinates are used to calculate the Euclidean distance between any two hair follicles. Distance, traverse all the pairs of hair follicle feature points in the image, obtain the distance data between each hair follicle, output a set of distance data describing the distribution law of hair follicles in the image, calculate the density of hair follicles within a certain range around each hair follicle feature point, use kernel density estimation and other methods to estimate the hair follicle distribution density in the local area based on the distance data, and obtain the density distribution data of each hair follicle position, which reflects the distribution characteristics of hair follicles in the image. Map the local density distribution data to the density distribution trend of the entire image, and use interpolation, smoothing and other technologies to construct a continuous hair follicle density distribution trend model to describe the overall trend of hair follicle distribution in the entire skin area.

[0116] In this embodiment, step S4 includes the following steps:

[0117] Step S41: performing image segmentation processing on the detail reconstructed skin and hair image to obtain multiple image regions;

[0118] Step S42: performing regional hair feature change trend analysis on multiple image regions based on the skin pigment distribution map and the hair follicle density distribution trend model to generate feature change trends of different image regions;

[0119] Step S43: performing change trend similarity analysis on the feature change trends of different image regions to generate regional change trend similarities;

[0120] Step S44: clustering and dividing the detail reconstructed skin and hair image into characteristic regions according to the similarity of the regional change trends, thereby obtaining a plurality of change trend characteristic regions.

[0121] In this embodiment, an image segmentation technique is used, such as a method based on region growing, image edge detection, etc., to divide the generated detailed reconstructed image into multiple independent regions. Each region should have relatively independent visual features to reflect the skin and hair conditions of different parts, so as to obtain a group of representative image regions. The skin pigment distribution map is combined with the constructed hair follicle density distribution trend model to analyze the changes in hair characteristics in each image region. For each region, the change trends of indicators such as hair pigment content and hair follicle density are evaluated to describe the overall changes in hair characteristics in the region, so as to obtain a group of trends representing the change rules of hair characteristics in different image regions. The feature change trend data of each region is used to calculate the similarity of the change trends between any two regions. Statistical methods, such as correlation coefficient and cosine similarity, are used to quantitatively describe the similarity of the feature change trends between different regions. Regions with similar feature change trends in the image are found. According to the similarity matrix between regions, clustering algorithms (such as spectral clustering and hierarchical clustering) are used to cluster the image regions. The goal of clustering is to classify regions with similar feature change trends into the same category to form multiple change trend feature regions, and output a set of representative feature regions, which reflects the change trend of hair features in different parts of the entire skin image.

[0122] In this embodiment, the specific steps of step S5 are:

[0123] Step S51: performing a multi-scenario growth time series evolution simulation on a plurality of change trend characteristic regions to generate multi-scenario time series evolution simulation data;

[0124] Step S52: performing growth time series response rate analysis on the multi-scenario time series evolution simulation data to obtain hair growth time series response rate data;

[0125] Step S53: predicting the growth trend change of the hair growth time series response rate data to generate hair growth trend prediction data;

[0126] Step S54: performing stage evolution trajectory analysis on the hair growth trend prediction data to construct a hair area growth trend evolution curve.

[0127] In this embodiment, a hair growth time series evolution model is constructed for each region. The model should consider the change pattern of hair characteristics (such as color and density) in the region over time and be able to simulate the change of growth trend under different environmental conditions. By adjusting the parameters of the model, hair growth time series evolution data under various environmental conditions (such as nutritional level, hormone level, etc.) are generated. The response rate of hair growth characteristics (such as color and density) to environmental changes is calculated for each characteristic region. The response rate is evaluated by analyzing the change trend of the time series data, such as calculating the slope and derivative of the characteristic change, quantitatively describing the sensitivity of hair growth in different regions to environmental changes, and predicting the change trend of hair growth characteristics in each characteristic region in the future period of time in combination with the existing environmental change prediction information. Time series analysis, machine learning and other methods are used to generate prediction data of future growth trend according to historical change patterns and external environment predictions, analyze the evolution trajectory of hair growth characteristics in each characteristic region over time, and use curve fitting and other methods to describe the change pattern of hair growth conditions at different time stages, so as to obtain curves representing the evolution of hair growth trend in different characteristic regions.

[0128] In this embodiment, the specific steps of step S511 are:

[0129] The growth trend of multiple change trend characteristic areas is deduced to obtain the growth trend rules of different areas;

[0130] Define multi-scenario growth environment parameters;

[0131] Based on the growth environment parameters of multiple scenarios, the time domain growth numerical simulation calculation is performed on the growth trend law of different regions to obtain the regional growth trend parameters of multiple scenarios;

[0132] Based on the regional growth trend parameters of multiple scenarios, multi-time point growth evolution simulation is performed to generate multi-scenario time series evolution simulation data.

[0133] In this embodiment, the variation law of hair growth characteristics (such as color, density, etc.) over time is analyzed for each region, and the variation trend of hair growth characteristics in each region is described by time series analysis, curve fitting and other methods, so as to obtain the variation law of hair growth characteristics in different regions. According to the actual application situation, a set of representative growth environment parameters, such as nutrition level, hormone level, temperature and humidity, etc., is defined, and multiple value ranges are set for each parameter to cover different environmental conditions, so as to construct a series of growth environment scenarios. According to the hair growth trend law of each region and the set multi-scenario growth environment parameters, a time domain growth numerical simulation calculation is performed, and the variation trend of hair growth characteristics in the future period is calculated for each characteristic region and each growth environment scenario. The dynamic change in the growth process is simulated by numerical simulation methods such as differential equations and difference equations, so as to obtain the growth trend parameters of different regions under different environmental conditions. According to the growth trend parameters of each region under different environmental scenarios, the growth evolution simulation at multiple time points is performed, and the simulation data sequence of the evolution of hair growth characteristics over time under different environmental conditions is generated by adjusting the model parameters, so as to obtain a set of representative hair growth time series evolution data, which provides a basis for the subsequent response rate analysis and situation prediction.

[0134] In this embodiment, the specific steps of step S6 are:

[0135] Step S61: identifying the periodic fluctuation amplitude of the hair region growth trend evolution curve, and extracting the periodic fluctuation amplitude of the trend curve;

[0136] Step S62: calculating the trend peak time point of the hair area growth trend evolution curve to generate multiple trend peak time points;

[0137] Step S63: evaluating the hair growth status of multiple situation peak time points and the periodic fluctuation amplitudes of the situation curve, thereby obtaining a growth status evaluation result;

[0138] Step S64: Visually project the growth status assessment results and the hair area growth trend evolution curve onto the detector display device to present the hair analysis results in detail.

[0139] In this embodiment, based on the simulation data of the time series evolution of hair growth, a time series analysis is performed on the growth trend curve of each region, and signal processing methods such as Fourier transform and wavelet transform are used to identify the periodic fluctuation characteristics in the growth trend curve, and the amplitude of each periodic fluctuation is quantified as an important indicator for evaluating the growth status. Based on the time series evolution data of hair growth, the peak time point in the growth trend curve is identified. The peak time point represents the time node when the hair growth rate reaches the maximum, which is another important indicator for evaluating the growth status. The peak time point of the growth trend curve of each region is obtained by curve extreme value analysis, sliding window method and other methods, and the indicators obtained are combined to establish The hair growth condition assessment model designs an assessment algorithm based on fuzzy logic, neural networks, etc., maps indicators such as periodic fluctuation amplitude and peak time point to the degree of growth condition, and obtains the assessment results of hair growth conditions in each area, providing a basis for subsequent visualization. The obtained growth condition assessment results and hair growth trend evolution curve are presented in an intuitive graphical manner on the detector display device. Common visualization charts such as bar charts and line charts are used to display the growth condition assessment scores and growth trend curves of different areas. The screen characteristics of the detector display device are used to create an interactive visualization interface to facilitate users to view and analyze hair growth status.

[0140] On the other hand, this embodiment also provides a skin and hair analysis system based on a mobile terminal projection screen interconnection detector, such as Figure 5, is a structural diagram of a mobile terminal screen projection interconnection detector, the mobile terminal includes mobile smart devices such as mobile phones, tablets, laptops and wearable devices, the detector includes a detector detection terminal and a detector display device, and real-time data transmission is performed between the mobile terminal and the detector through a wired or wireless network. Optionally, real-time data transmission can also be performed between the detector detection terminal and the detector display device through a wired or wireless network; it should be noted that the network includes Wi-Fi Direct, broadband wide area network, local area network, cellular network, Ethernet, radio frequency and satellite communication, that is, the mobile terminal and the detector both have the function of wireless data transmission and access to the Internet. In some scenarios, the detector can push service information to users by directly connecting to the Internet, or is used to receive push information from the mobile terminal to improve user experience. The mobile terminal is used to execute any algorithm program of the skin and hair analysis method based on the mobile terminal screen projection interconnection detector in the aforementioned embodiments. In this embodiment, Mira cast using Wi-Fi Direct technology is used for wireless screen projection connection between the mobile terminal and the display device, and Wi-Fi is used to connect to the display device. Direct conducts point-to-point Wi-Fi connection between devices, without connecting to a router, to achieve fast wireless screen projection. Bluetooth or Wi-Fi connection is used for wireless communication between the mobile terminal and the detector. Bluetooth or Wi-Fi connection can achieve real-time data transmission and wireless control between the mobile terminal and the detector within a short distance. In one embodiment, the detector can also be used alone to view the surface state of the skin and hair. When more computing power is needed to conduct in-depth analysis of the skin and hair status data, the detector detection end is used to provide the captured various skin and hair multispectral image data to the mobile terminal for analysis, and the analysis data and results are transmitted to the detector display device in real time via the wireless network for display. Furthermore, the skin and hair analysis system of the mobile terminal screen projection interconnected detector specifically includes:

[0141] The pigment distribution module is used to obtain a skin multispectral image set based on the camera at the detector end; perform multi-image spectral quantitative analysis on the skin multispectral image set to construct a skin pigment distribution map;

[0142] An image reconstruction module is used to perform contour detail feature analysis on a skin multispectral image set, and to reconstruct detail images to construct detail reconstructed skin and hair images;

[0143] The density distribution module is used to perform fine visual recognition of hair follicles on the detailed reconstructed skin hair image, so as to obtain the spatial position coordinates of the hair follicles; perform hair follicle density distribution analysis based on the spatial position coordinates of the hair follicles, and construct a hair follicle density distribution trend model;

[0144] The feature change trend module is used to analyze the regional hair feature change trend based on the skin pigment distribution map and the hair follicle density distribution trend model, and to perform feature regional clustering and division, thereby obtaining multiple change trend feature regions;

[0145] The growth trend evolution module is used to simulate the time-series evolution of growth in multiple scenarios for multiple change trend feature areas, predict the growth trend changes, and construct the hair area growth trend evolution curve;

[0146] The condition assessment module is used to assess the hair growth condition based on the growth trend evolution curve of the hair area, so as to obtain the growth condition assessment result; based on the growth condition assessment result, a visual projection is performed to present the hair analysis result.

[0147] The present invention performs multi-image spectral quantitative analysis through a multi-spectral image set, can accurately capture the pigment distribution of skin and hair, construct a skin pigment distribution map, provide basic data for subsequent analysis, perform contour detail feature analysis on the multi-spectral image set and reconstruct detailed images, show the detailed features of skin and hair, provide clearer and more accurate skin and hair images, and provide a more reliable data basis for subsequent analysis. Through the refined visual recognition and density distribution analysis of hair follicles, the spatial position coordinates and density distribution trend model of hair follicles are obtained, which can deeply understand the distribution of hair follicles and provide more detailed data support for subsequent analysis. By analyzing the skin pigment distribution map and hair follicle density analysis, The hair growth trend can be analyzed and predicted based on the growth trend of the hair area. The hair growth condition can be evaluated based on the hair area growth trend evolution curve to obtain the growth condition evaluation results. Personalized care suggestions can be provided based on the evaluation results. The hair analysis results can be presented through visual projection to help users understand their own hair health status and further improve the care plan.

[0148] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0149] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A skin and hair analysis method based on a mobile screen projection interconnection detector, characterized in that: The mobile terminal and the detector based on real-time communication are implemented, wherein the detector includes a detector detection terminal and a detector display device, and the mobile terminal is used to provide computing power for data analysis for the detector, specifically including the following steps: Step S1: obtaining a skin multispectral image set based on the camera at the detection end of the detector; performing multi-image spectral quantitative analysis on the skin multispectral image set to construct a skin pigment distribution map; Step S2: performing contour detail feature analysis on the skin multispectral image set, and reconstructing the detail image to construct a detail reconstructed skin and hair image; Step S3: performing fine visual recognition of hair follicles on the detailed reconstructed skin hair image to obtain the spatial position coordinates of the hair follicles; performing hair follicle density distribution analysis based on the spatial position coordinates of the hair follicles to construct a hair follicle density distribution trend model; Step S4: performing regional hair feature change trend analysis on the skin pigment distribution map and the hair follicle density distribution trend model, and performing feature region clustering to obtain multiple change trend feature regions; Step S5: performing multi-scenario growth time series evolution simulation on multiple change trend feature areas, and predicting the growth trend change, to construct a hair area growth trend evolution curve; Step S6: Evaluate the hair growth status of the hair area growth trend evolution curve to obtain a growth status evaluation result; and visualize the display device of the detector based on the growth status evaluation result to present the hair analysis result.

2. The skin and hair analysis method based on the mobile terminal screen projection interconnection detector according to claim 1 is characterized in that: The specific steps of step S1 are: Step S11: acquiring a skin multispectral image set based on the camera at the detector end; Step S12: performing multi-image spectral quantitative analysis on the skin multi-spectral image set to extract image spectral feature vectors; Step S13: performing regional color difference analysis on the image spectral feature vector to obtain color difference data of different image regions; Step S14: performing color space difference decomposition on the skin multispectral image set according to the color difference data of different image regions to generate skin pigment region feature data; Step S15: performing pigment distribution fitting on the skin pigment area characteristic data to construct a skin pigment distribution map.

3. The skin and hair analysis method based on the mobile screen projection interconnection detector according to claim 1 is characterized in that: The specific steps of step S2 are: Step S21: performing hair root recognition on the skin multispectral image set to mark the hair root area; Step S22: performing brightness enhancement processing on the hair root area to obtain a brightness enhanced hair image; Step S23: performing hair contour analysis on the brightness enhanced hair image to extract hair contour lines; Step S24: performing contour enlargement processing on the hair contour line to obtain a hair contour enlarged image; Step S25: performing contour detail feature analysis on the hair contour detail enlarged image to generate hair contour detail features; Step S26: reconstructing the detail image of the brightness enhanced hair image according to the detail features of the hair contour, and constructing a detail reconstructed skin and hair image.

4. The skin and hair analysis method based on the mobile screen projection interconnection detector according to claim 1 is characterized in that: The specific steps of step S3 are: Step S31: performing fine visual recognition of hair follicles on the detailed reconstructed skin and hair image, marking each hair follicle feature point; Step S32: Calculate the spatial position of each hair follicle feature point to obtain the spatial position coordinates of the hair follicle; Step S33: calculating the distance between hair follicles according to the spatial position coordinates of the hair follicles, thereby obtaining a plurality of distances between hair follicles; Step S34: performing hair follicle density distribution analysis on each hair follicle feature point based on a plurality of distances between hair follicles to generate hair follicle density distribution data; Step S35: Perform density trend mapping on the hair follicle density distribution data to construct a hair follicle density distribution trend model.

5. The skin and hair analysis method based on the mobile terminal screen projection interconnection detector according to claim 1 is characterized in that: The specific steps of step S4 are: Step S41: performing image segmentation processing on the detail reconstructed skin and hair image to obtain multiple image regions; Step S42: performing regional hair feature change trend analysis on multiple image regions based on the skin pigment distribution map and the hair follicle density distribution trend model to generate feature change trends of different image regions; Step S43: performing change trend similarity analysis on the feature change trends of different image regions to generate regional change trend similarities; Step S44: clustering and dividing the detail reconstructed skin and hair image into characteristic regions according to the similarity of the regional change trends, thereby obtaining a plurality of change trend characteristic regions.

6. The skin and hair analysis method based on the mobile terminal screen projection interconnection detector according to claim 1 is characterized in that: The specific steps of step S5 are: Step S51: performing a multi-scenario growth time series evolution simulation on a plurality of change trend characteristic regions to generate multi-scenario time series evolution simulation data; Step S52: performing growth time series response rate analysis on the multi-scenario time series evolution simulation data to obtain hair growth time series response rate data; Step S53: predicting the growth trend change of the hair growth time series response rate data to generate hair growth trend prediction data; Step S54: performing stage evolution trajectory analysis on the hair growth trend prediction data to construct a hair area growth trend evolution curve.

7. The skin and hair analysis method based on the mobile screen projection interconnection detector according to claim 6 is characterized in that: The specific steps of step S51 are: The growth trend of multiple change trend characteristic areas is deduced to obtain the growth trend rules of different areas; Define multi-scenario growth environment parameters; Based on the growth environment parameters of multiple scenarios, the time domain growth numerical simulation calculation is performed on the growth trend law of different regions to obtain the regional growth trend parameters of multiple scenarios; Based on the regional growth trend parameters of multiple scenarios, multi-time point growth evolution simulation is performed to generate multi-scenario time series evolution simulation data.

8. The skin and hair analysis method based on the mobile screen projection interconnection detector according to claim 1 is characterized in that: The specific steps of step S6 are: Step S61: identifying the periodic fluctuation amplitude of the hair region growth trend evolution curve, and extracting the periodic fluctuation amplitude of the trend curve; Step S62: calculating the trend peak time point of the hair area growth trend evolution curve to generate multiple trend peak time points; Step S63: evaluating the hair growth status of multiple situation peak time points and the periodic fluctuation amplitudes of the situation curve, thereby obtaining a growth status evaluation result; Step S64: Visually project the growth status assessment results and the hair area growth trend evolution curve onto the detector display device to present the hair analysis results in detail.

9. A skin and hair analysis system based on a mobile screen projection interconnection detector, characterized in that: The skin and hair analysis system based on the mobile terminal screen projection interconnected detector includes a mobile terminal and a detector, and real-time data is transmitted between the mobile terminal and the detector via a wired or wireless network. The mobile terminal is used to execute an algorithm program containing a skin and hair analysis method based on the mobile terminal screen projection interconnected detector as described in any one of claims 1 to 8. The detector includes a detector detection terminal and a detector display device. The detector detection terminal is used to obtain multispectral image data of skin and hair, and the detector display device is used to synchronize the screen of the mobile terminal and display network push information. The skin and hair analysis system based on the mobile terminal screen projection interconnection detector specifically includes: The pigment distribution module is used to obtain a skin multispectral image set based on the camera at the detector end; perform multi-image spectral quantitative analysis on the skin multispectral image set to construct a skin pigment distribution map; An image reconstruction module is used to perform contour detail feature analysis on a skin multispectral image set, and to reconstruct detail images to construct detail reconstructed skin and hair images; The density distribution module is used to perform fine visual recognition of hair follicles on the detailed reconstructed skin hair image, so as to obtain the spatial position coordinates of the hair follicles; perform hair follicle density distribution analysis based on the spatial position coordinates of the hair follicles, and construct a hair follicle density distribution trend model; The feature change trend module is used to analyze the regional hair feature change trend based on the skin pigment distribution map and the hair follicle density distribution trend model, and to perform feature regional clustering and division, thereby obtaining multiple change trend feature regions; The growth trend evolution module is used to simulate the time-series evolution of growth in multiple scenarios for multiple change trend feature areas, predict the growth trend changes, and construct the hair area growth trend evolution curve; The condition assessment module is used to assess the hair growth condition based on the growth trend evolution curve of the hair area, so as to obtain the growth condition assessment result; based on the growth condition assessment result, a visual projection is performed to present the hair analysis result.

Images