Hair and hair follicle health state detection system based on image analysis

Abstract

The invention relates to the technical field of biomedicine and image processing, in particular to a hair and hair follicle health state detection system based on image analysis, which comprises an image acquisition module, an image preprocessing module, a feature extraction module, a health parameter calculation module and a health state evaluation module, wherein the image acquisition module is used for acquiring an original image of a scalp target area; the image preprocessing module is used for executing reflection suppression and contrast enhancement operation; the feature extraction module is used for outputting hair follicle morphological feature data and capillary density data; the health parameter calculation module is used for calculating and outputting a hair follicle activity index and a hair density parameter; and the health state evaluation module is used for generating a comprehensive health level and outputting a detection report. According to the invention, through automatic image analysis in combination with the hair follicle activity index and the hair density parameter, accurate hair health assessment is provided, and the detection accuracy and convenience are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of biomedical and image processing, and particularly relates to a hair and hair follicle health state detection system based on image analysis. BACKGROUND

[0002] With the improvement of living standards and changes in environmental factors, hair problems have become a common concern for health issues; hair health not only directly affects personal appearance, but also is closely related to the health status of the body; traditional hair health detection methods often rely on manual inspection or analysis of local samples, which have strong subjectivity and inaccurate results.

[0003] In addition, the existing technology mainly focuses on the analysis of external features of hair, such as hair density and length, and less involves the comprehensive evaluation of hair follicle activity and its microenvironment; hair follicle activity is an important indicator of hair growth, which is affected by blood supply, hair follicle morphology and other factors; therefore, a single external detection method cannot comprehensively evaluate the health status of hair. Therefore, there is an urgent need for a hair and hair follicle health state detection system based on image analysis to solve the above problems. SUMMARY

[0004] Based on the above purpose, the present application provides a hair and hair follicle health state detection system based on image analysis.

[0005] A hair and hair follicle health state detection system based on image analysis, comprising an image acquisition module, an image preprocessing module, a feature extraction module, a health parameter calculation module and a health state evaluation module; wherein:

[0006] The image acquisition module: integrates a multi-spectral imaging device for acquiring original images of the target area of the scalp;

[0007] The image preprocessing module: is used to receive the original image and perform anti-reflection and contrast enhancement operations to output an enhanced image;

[0008] The feature extraction module: is used to receive the enhanced image, segment the hair follicle area and identify the distribution of hair papilla microvessels, and output hair follicle morphology feature data and microvessel density data;

[0009] The health parameter calculation module: calculates and outputs the hair follicle activity index and hair density parameters based on the hair follicle morphology feature data and microvessel density data;

[0010] The health state evaluation module: is used to generate a comprehensive health grade and output a detection report according to the hair follicle activity index and hair density parameters.

[0011] Optionally, the image acquisition module comprises a light source control unit, an optical imaging unit and an image transmission unit; wherein:

[0012] Light source control unit: Used to control the light source in the multispectral imaging device to illuminate the target area of ​​the scalp in different wavelengths;

[0013] Optical imaging unit: used to receive reflected light signals, form a raw image of the scalp area, and adjust imaging modes of different wavelengths according to the light source control unit to obtain images of different spectral levels;

[0014] Image transmission unit: used to transmit the raw images acquired by the optical imaging unit to the image preprocessing module.

[0015] Optionally, the image preprocessing module includes a reflection suppression unit, a contrast enhancement unit, and an image output unit; wherein:

[0016] Reflection suppression unit: Used to identify reflected light areas in the original image, and reduce the bright areas caused by light source reflection in the image through an adaptive filtering algorithm, thereby eliminating image distortion caused by reflection;

[0017] Contrast enhancement unit: Used to perform contrast enhancement processing on the received raw image to enhance the details and texture information of the scalp area;

[0018] Image output unit: Used to transmit the image data after reflection suppression and contrast enhancement to the feature extraction module.

[0019] Optionally, the reflection suppression unit includes:

[0020] Reflected light region identification subunit: used to detect bright regions in the original image, and use the brightness threshold segmentation method to mark regions with brightness values ​​greater than a set threshold as reflected light regions;

[0021] Reflection suppression filtering subunit: Based on the results of reflected light area identification, it applies an adaptive filtering algorithm to adjust pixel values ​​by calculating the local mean of the image, so as to reduce the brightness value of the reflected light area;

[0022] Image fusion subunit: Used to fuse the filtered image with the unprocessed area to form an enhanced image.

[0023] Optionally, the feature extraction module includes a hair follicle region segmentation unit, a hair papilla microvessel identification unit, a hair follicle morphology feature extraction unit, and a microvessel density calculation unit; wherein:

[0024] Hair follicle region segmentation unit: used to extract hair follicle regions in enhanced images and locate hair follicle boundaries using image segmentation algorithms;

[0025] Hair papilla microvessel recognition unit: used to identify the distribution of microvessels within the hair follicle area, and extract microvessel features through texture and edge analysis;

[0026] Hair follicle morphology feature extraction unit: used to extract the geometric features of hair follicles, including size, shape and depth, and generate hair follicle morphology feature data;

[0027] Microvessel density calculation unit: used to calculate the density of microvessels in the hair papilla, and output density data based on the number or area ratio of microvessel regions.

[0028] Optionally, the hair follicle region segmentation unit includes:

[0029] Preprocessing subunit: used to denoise the enhanced image and remove noise from the image;

[0030] Edge detection subunit: used to detect hair follicle edges, extract areas in the image where the brightness change is greater than a preset threshold, and generate a preliminary outline of the hair follicle boundary;

[0031] Thresholding segmentation subunit: Based on the brightness or color distribution of the image, a dynamic adaptive thresholding segmentation algorithm is used to determine the hair follicle boundary. The determination expression is:

[0032]

[0033] Among them, I binary (x,y) represents the binary image values ​​after thresholding; I filtered (x, y) represents the denoised pixel values; T dynamic This is an adaptive dynamic threshold.

[0034] Optionally, the dermal papilla microvessel recognition unit includes:

[0035] Texture analysis subunit: used to analyze the texture features in the hair follicle region image. It extracts the texture information of microvessels through the local binary mode algorithm and matches the texture features with the morphological features of blood vessels to identify the microvessel region.

[0036] Edge detection subunit: used to identify the edges of microvessels in the image. It extracts detailed information of microvessels and marks them as potential microvessel regions by detecting gradient changes in the image.

[0037] Microvessel morphology feature extraction subunit: used to extract the morphological features of microvessels, including vessel length, width, curvature and branching points;

[0038] Microvascular region screening subunit: Used to screen regions that conform to microvascular characteristics based on extracted texture and edge features. By analyzing the connectivity, area and morphology of the regions, noisy regions that do not conform to microvascular characteristics are removed, and the distribution of microvessels in the hair papilla is finally determined.

[0039] Optionally, the health parameter calculation module includes a hair follicle activity index calculation unit and a hair density parameter calculation unit; wherein:

[0040] Hair follicle activity index calculation unit: used to calculate the hair follicle activity index, which combines hair follicle morphology data and microvascular density data to calculate the activity index A by weighted average.

[0041] Hair density parameter calculation unit: Used to calculate hair density parameters. By counting the number of hairs within the hair follicle region and combining this with the area of ​​the hair follicle region, it outputs the hair density parameter D. hair .

[0042] Optionally, the health status assessment module includes a health level calculation unit, a health status decision unit, and a test report generation unit; wherein:

[0043] Health level calculation unit: used to calculate the overall health level by weighting the hair follicle activity index and hair density parameters according to the preset health level standards;

[0044] Health Status Decision Unit: Used to calculate the comprehensive health level output by the health level unit and provide corresponding recommended measures or prompts;

[0045] Test report generation unit: Used to automatically generate test reports based on health level and health status decision results, including hair follicle activity index, hair density parameters, comprehensive health level and related suggestions.

[0046] Optionally, the health level calculation unit includes:

[0047] Data standardization subunit: used to standardize the hair follicle activity index and hair density parameters so that their values ​​are within a uniform range;

[0048] Weighted calculation subunit: Used to perform weighted calculations on the standardized hair follicle activity index and hair density parameters according to preset weighting coefficients, and generate a comprehensive health score S. health ;

[0049] Health Level Assessment Subunit: Used to calculate the comprehensive health score S based on preset health level standards. health Translated into specific health levels;

[0050] When S health When the value is ≥0.8, the overall health level is excellent;

[0051] When 0.6≤S health When the value is less than 0.8, the overall health level is considered good.

[0052] When S health When the score is less than 0.6, the overall health level is poor.

[0053] The beneficial effects of this invention are:

[0054] This invention achieves a comprehensive and accurate assessment of hair health by combining hair follicle activity index and hair density parameters. Through automated image analysis, it comprehensively considers multi-dimensional information such as hair follicle morphology and microvascular density, overcoming the subjectivity and limitations of traditional detection methods and improving the accuracy and reliability of health assessment.

[0055] This invention accurately calculates a comprehensive health level and automatically generates a detailed test report, making it easier for users to understand their health status and take corresponding improvement measures. Compared with existing technologies, it has a higher level of automation, improving the efficiency and convenience of the testing process. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0057] Fig. 1 This is a schematic diagram of a health status detection system according to an embodiment of the present invention;

[0058] Fig. 2 This is a schematic diagram of the feature extraction module in an embodiment of the present invention. Detailed Implementation

[0059] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. It should also be noted that, to make the embodiments more comprehensive, the following embodiments are the best and preferred embodiments, and those skilled in the art can use other alternative methods to implement some well-known technologies; moreover, the accompanying drawings are only for more specific description of the embodiments and are not intended to specifically limit the present invention.

[0060] It should be noted that the use of terms such as "an embodiment," "an embodiment," "an exemplary embodiment," and "some embodiments" in the specification indicates that the described embodiment may include a specific feature, structure, or characteristic, but not every embodiment necessarily includes that specific feature, structure, or characteristic. Furthermore, when a specific feature, structure, or characteristic is described in connection with an embodiment, implementing such a feature, structure, or characteristic in conjunction with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the art.

[0061] Generally, terms can be understood at least partly from their use in context. For example, depending at least partly on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in a singular sense, or a combination of features, structures, or characteristics in a plural sense. Additionally, the term "based on" can be understood not necessarily to convey an exclusive set of factors, but rather, alternatively, depending at least partly on the context, to allow for the presence of other factors that are not necessarily explicitly described.

[0062] like Figs. 1-2 As shown, a hair and hair follicle health status detection system based on image analysis includes an image acquisition module, an image preprocessing module, a feature extraction module, a health parameter calculation module, and a health status assessment module; wherein:

[0063] Image acquisition module: integrates multispectral imaging equipment to acquire raw images of the target area of ​​the scalp;

[0064] Image preprocessing module: used to receive the original image, perform reflection suppression and contrast enhancement operations, and output an enhanced image;

[0065] Feature extraction module: used to receive enhanced images, segment hair follicle regions and identify the distribution of microvessels in the hair papilla, and output hair follicle morphological feature data and microvessel density data;

[0066] Health parameter calculation module: Based on hair follicle morphology data and microvascular density data, calculate and output hair follicle activity index and hair density parameters;

[0067] Health status assessment module: Used to generate a comprehensive health level and output a test report based on hair follicle activity index and hair density parameters.

[0068] The image acquisition module includes a light source control unit, an optical imaging unit, and an image transmission unit; wherein:

[0069] Light source control unit: Used to control the light source in the multispectral imaging device to illuminate the target area of ​​the scalp in different wavelengths, ensuring that the light source wavelength covers the range from ultraviolet to near infrared, and to acquire different spectral information;

[0070] Optical imaging unit: used to receive reflected light signals, form a raw image of the scalp area, and adjust imaging modes of different wavelengths according to the light source control unit to obtain images of different spectral levels;

[0071] Image transmission unit: Used to transmit the raw images acquired by the optical imaging unit to the image preprocessing module, ensuring the real-time performance and high quality of the image data; by integrating the light source control unit, optical imaging unit and image transmission unit, the image acquisition module can accurately control the light source illumination in a multi-band range and ensure that the image signals received by the optical imaging unit are accurate and clear; this design effectively improves the quality of scalp area image acquisition, provides high-resolution, full-band information, and provides richer and more accurate image data for subsequent image preprocessing and health analysis.

[0072] The image preprocessing module includes a reflection suppression unit, a contrast enhancement unit, and an image output unit; wherein:

[0073] Reflection suppression unit: Used to identify reflected light areas in the original image, reduce the bright areas caused by light source reflection in the image through adaptive filtering algorithm, eliminate image distortion caused by reflection, and improve image details and quality;

[0074] Contrast enhancement unit: used to perform contrast enhancement processing on the received raw image, enhance the details and texture information of the scalp area, thereby enhancing the visibility of the hair follicle area and microvessels;

[0075] Image output unit: used to transmit the image data after reflection suppression and contrast enhancement to the feature extraction module to ensure that the image quality meets the needs of subsequent analysis; through the collaborative work of the above units, the image preprocessing module can effectively remove reflection interference in the original image and improve the image clarity and readability through contrast enhancement, providing more accurate input image data for subsequent hair and hair follicle health status analysis.

[0076] The reflection suppression unit includes:

[0077] Reflected light region identification subunit: Used to detect bright regions in the original image. Using a brightness threshold segmentation method, regions with brightness values ​​greater than a set threshold are marked as reflected light regions. The formula is as follows: I reflection = {I(x, y)|I(x, y)>T}, where I(x, y) is the brightness value of the image at coordinates (x, y), in pixels; T is the set brightness threshold, in pixels; I reflection This is the set of regions of reflected light, representing the locations of all pixels in the image whose brightness values ​​are greater than the threshold T;

[0078] Reflection suppression filtering subunit: Based on the reflected light area identification results, it applies an adaptive filtering algorithm to adjust pixel values ​​by calculating the local mean of the image, thereby reducing the brightness of the reflected light areas and restoring detail information in the image. The formula is as follows: Among them, I adjusted(x, y) represents the adjusted pixel value in pixel brightness; (x′, y′) represents the coordinates of the neighboring pixels, indicating the pixels adjacent to the target pixel (x, y); N(x, y) represents the set of neighboring pixels centered at (x, y), in pixels; I(x′, y′) represents the brightness value at the neighboring pixel position (x′, y′), in pixels brightness; N is the number of neighboring pixels, indicating the size of the pixel range considered.

[0079] Image fusion subunit: This unit is used to fuse the filtered image with the unprocessed area to form an enhanced image, ensuring that the removal of reflected light areas does not affect the overall image quality. The above subunit accurately identifies reflected light areas in the original image and applies an adaptive filtering algorithm to effectively remove the bright areas caused by light source reflection, ensuring that the details of the image are restored and enhancing the naturalness and readability of the image.

[0080] The feature extraction module includes a hair follicle region segmentation unit, a hair papilla microvessel identification unit, a hair follicle morphology feature extraction unit, and a microvessel density calculation unit; among which:

[0081] Hair follicle region segmentation unit: used to extract hair follicle regions in enhanced images, locate hair follicle boundaries through image segmentation algorithms, and provide accurate regions for subsequent analysis;

[0082] Hair papilla microvessel recognition unit: used to identify the distribution of microvessels within the hair follicle area, and extract microvessel features through texture and edge analysis;

[0083] Hair follicle morphology feature extraction unit: used to extract the geometric features of hair follicles, including size, shape and depth, and generate hair follicle morphology feature data;

[0084] The microvessel density calculation unit calculates the density of microvessels in the hair papilla, outputting density data based on the number or area ratio of microvessel regions. The feature extraction module effectively extracts the hair follicle morphology and microvessel density data required for health assessment through precise hair follicle region segmentation and microvessel identification, improving the accuracy and reliability of subsequent health status assessments.

[0085] The hair follicle region segmentation unit includes:

[0086] The preprocessing subunit is used to denoise the enhanced image, removing noise and improving image quality. Specifically, it uses a median filtering algorithm, as shown in the following formula:

[0087] I filtered(x, y)=median(I(x′,y′)|(x′,y′)∈N(x,y)),

[0088] Among them, I filtered (x, y) represents the denoised pixel value, I(x′, y′) represents the neighboring pixel value, and N(x, y) represents the set of neighboring pixels centered at (x, y).

[0089] Edge detection subunit: used to detect hair follicle edges, extract areas in the image where the brightness change is greater than a preset threshold, and generate a preliminary outline of the hair follicle boundary;

[0090] Thresholding segmentation subunit: Based on the brightness or color distribution of the image, a dynamic adaptive thresholding segmentation algorithm is used to determine the hair follicle boundary. The determination expression is:

[0091]

[0092] Among them, I binary (x,y) represents the binary image values ​​after thresholding; I filtered (x, y) represents the denoised pixel values; T dynamic The adaptive dynamic threshold is calculated based on the mean brightness μ and standard deviation σ of the local region, using the formula: T dynamic =μ+k·σ, where k is an adjustment coefficient used to control the sensitivity of the threshold; the hair follicle region segmentation unit can accurately extract the boundary of the hair follicle, avoiding interference from noise and irrelevant areas; this process effectively improves the accuracy of segmentation, providing accurate regional input for subsequent extraction of hair follicle morphology and microvessel density.

[0093] The dermal papilla microvessel recognition unit includes:

[0094] Texture analysis subunit: Used to analyze texture features in hair follicle region images. It extracts microvascular texture information using the Local Binary Pattern (LBP) algorithm and matches texture features with blood vessel morphology features to identify microvascular regions. The LBP algorithm formula is: Where LBP(x,y) is the local binary pattern value at position (x,y), representing the texture feature; I(p) is the gray value of the neighboring pixel p in the image; and I(c) is the position... The grayscale value of the center pixel at point P; P is the total number of neighboring pixels, representing the pixels surrounding the center pixel; s(I(p)-I(c)) is the threshold function, defined as... 2 p Used to convert the result of each neighboring pixel into a binary number and represent it in a weighted manner;

[0095] Edge detection subunit: Used to identify the edges of microvessels in the image. It extracts detailed information about microvessels and marks them as potential microvessel regions by detecting gradient changes in the image; the gradient calculation formula is as follows: Where G(x,y) is the gradient value at image position (x,y); and These are the gradients of the image in the x and y directions, respectively;

[0096] Microvessel morphology feature extraction subunit: used to extract the morphological features of microvessels, including the length, width, curvature and branch points of the vessels, and to describe the structure of microvessels by calculating the geometric parameters of the vessels;

[0097] The microvessel region screening subunit is used to filter regions that conform to microvessel characteristics based on extracted texture and edge features. By analyzing the connectivity, area, and morphology of the regions, noisy regions that do not conform to microvessel characteristics are removed, and the distribution of microvessels within the hair papilla is finally determined. The above subunit can accurately identify the distribution of microvessels within the hair follicle region through multiple steps such as texture analysis, edge detection, and morphological feature extraction. This process combines the extraction of texture, edge, and geometric morphological features to ensure the accurate identification of microvessel features and provide reliable data support for microvessel density calculation.

[0098] The health parameter calculation module includes a hair follicle activity index calculation unit and a hair density parameter calculation unit; among which:

[0099] Hair follicle activity index calculation unit: Used to calculate the hair follicle activity index. It combines hair follicle morphological characteristic data (such as hair follicle area, aspect ratio, etc.) and microvascular density data to calculate the activity index A through a weighted average method, as shown in the following formula: Where A is the hair follicle activity index; w1 and w2 are the weighting coefficients for hair follicle morphology and microvessel density, respectively; A follicle A represents the area of ​​the hair follicle region. max M represents the maximum area of ​​the hair follicle region. vascular Microvessel density; M max This represents the maximum value of microvascular density;

[0100] Hair density parameter calculation unit: Used to calculate hair density parameters. By counting the number of hairs within the hair follicle region and combining this with the area of ​​the hair follicle region, it outputs the hair density parameter D. hair Its expression is:

[0101] Where, N hair The number of hairs within the hair follicle area; A follicleThe area of ​​the hair follicle region is used as a reference. By combining the morphological characteristics of the hair follicle and the microvascular density data, the hair follicle activity index and hair density parameters can be accurately calculated. These two health parameters provide key basis for subsequent health status assessment and help to accurately judge the health status of hair and hair follicles.

[0102] The health status assessment module includes a health level calculation unit, a health status decision-making unit, and a test report generation unit; among which:

[0103] Health level calculation unit: used to calculate the overall health level by weighting the hair follicle activity index and hair density parameters according to the preset health level standards;

[0104] Health Status Decision Unit: Used to calculate the comprehensive health level output by the health level unit, and provide corresponding recommended measures or prompts to help users understand the test results and their meaning;

[0105] The report generation unit automatically generates a report based on the health level and health status decision results. This report includes the hair follicle activity index, hair density parameters, overall health level, and related suggestions, presented as a text report for user viewing and archiving. The health status assessment module, by combining the hair follicle activity index and hair density parameters, generates an accurate overall health level, providing a comprehensive analysis of hair follicle health. Furthermore, the automatically generated reports provide users with a clear and concise summary of their health status and suggestions, enhancing the system's usability and user experience.

[0106] The health level calculation unit includes:

[0107] Data standardization subunit: Used to standardize the hair follicle activity index and hair density parameters, ensuring their values ​​are within a uniform range (e.g., between 0 and 1) for easier weighted calculation; standardization is performed using the following formula: Among them, I normalized The value is the standardized value; I raw For the hair follicle activity index or hair density parameter; I min and I max These are the minimum and maximum values ​​of the hair follicle activity index or hair density parameter, respectively.

[0108] Weighted calculation subunit: Used to perform weighted calculations on the standardized hair follicle activity index and hair density parameters according to preset weighting coefficients, and generate a comprehensive health score S. health The weighted calculation formula is: S health =w3·I active +w4·I density , among which, S healthFor comprehensive health scoring; w3 and w4 are preset weighting coefficients for the hair follicle activity index and hair density parameters, w3+w4=1; I active and I density These are the standardized hair follicle activity index and hair density parameters;

[0109] Health Level Assessment Subunit: Used to calculate the comprehensive health score S based on preset health level standards. health Translated into specific health levels;

[0110] When S health When the value is ≥0.8, the overall health level is excellent;

[0111] When 0.6≤S health When the value is less than 0.8, the overall health level is considered good.

[0112] When S health When the value is less than 0.6, the overall health level is poor.

[0113] The health level calculation unit, by standardizing the hair follicle activity index and hair density parameters and using a weighted calculation method, can accurately and comprehensively assess the health status of hair and hair follicles. This technical solution ensures the scientific nature and reliability of the health level assessment and improves the accuracy and practicality of hair and hair follicle health status detection.

[0114] This invention encompasses any substitutions, modifications, equivalent methods, and solutions made within the spirit and scope of this invention. To provide the public with a thorough understanding of this invention, specific details are described in detail in the following preferred embodiments; however, those skilled in the art will fully understand the invention even without these details. Furthermore, to avoid unnecessary misunderstanding of the essence of this invention, well-known methods, processes, procedures, components, and circuits are not described in detail.

[0115] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A system for detecting the health status of hair and hair follicles based on image analysis, characterized in that, It includes an image acquisition module, an image preprocessing module, a feature extraction module, a health parameter calculation module, and a health status assessment module; among which: Image acquisition module: integrates multispectral imaging equipment to acquire raw images of the target area of ​​the scalp; Image preprocessing module: used to receive the original image, perform reflection suppression and contrast enhancement operations, and output an enhanced image; Feature extraction module: used to receive enhanced images, segment hair follicle regions and identify the distribution of microvessels in the hair papilla, and output hair follicle morphological feature data and microvessel density data; Health parameter calculation module: Based on hair follicle morphology data and microvascular density data, calculate and output hair follicle activity index and hair density parameters; Health status assessment module: Used to generate a comprehensive health level and output a test report based on hair follicle activity index and hair density parameters.

2. The image analysis-based hair and hair follicle health status detection system according to claim 1, characterized in that, The image acquisition module includes a light source control unit, an optical imaging unit, and an image transmission unit; wherein: Light source control unit: Used to control the light source in the multispectral imaging device to illuminate the target area of ​​the scalp in different wavelengths; Optical imaging unit: used to receive reflected light signals, form a raw image of the scalp area, and adjust imaging modes of different wavelengths according to the light source control unit to obtain images of different spectral levels; Image transmission unit: used to transmit the raw images acquired by the optical imaging unit to the image preprocessing module.

3. The image analysis-based hair and hair follicle health status detection system according to claim 1, characterized in that, The image preprocessing module includes a reflection suppression unit, a contrast enhancement unit, and an image output unit; wherein: Reflection suppression unit: Used to identify reflected light areas in the original image, and reduce the bright areas caused by light source reflection in the image through an adaptive filtering algorithm, thereby eliminating image distortion caused by reflection; Contrast enhancement unit: Used to perform contrast enhancement processing on the received raw image to enhance the details and texture information of the scalp area; Image output unit: Used to transmit the image data after reflection suppression and contrast enhancement to the feature extraction module.

4. The image analysis-based hair and hair follicle health status detection system according to claim 3, characterized in that, The reflection suppression unit includes: Reflected light region identification subunit: used to detect bright regions in the original image, and use the brightness threshold segmentation method to mark regions with brightness values ​​greater than a set threshold as reflected light regions; Reflection suppression filtering subunit: Based on the results of reflected light area identification, it applies an adaptive filtering algorithm to adjust pixel values ​​by calculating the local mean of the image, so as to reduce the brightness value of the reflected light area; Image fusion subunit: Used to fuse the filtered image with the unprocessed area to form an enhanced image.

5. The image analysis-based hair and hair follicle health status detection system according to claim 1, characterized in that, The feature extraction module includes a hair follicle region segmentation unit, a hair papilla microvessel identification unit, a hair follicle morphology feature extraction unit, and a microvessel density calculation unit; wherein: Hair follicle region segmentation unit: used to extract hair follicle regions in enhanced images and locate hair follicle boundaries using image segmentation algorithms; Hair papilla microvessel recognition unit: used to identify the distribution of microvessels within the hair follicle area, and extract microvessel features through texture and edge analysis; Hair follicle morphology feature extraction unit: used to extract the geometric features of hair follicles, including size, shape and depth, and generate hair follicle morphology feature data; Microvessel density calculation unit: used to calculate the density of microvessels in the hair papilla, and output density data based on the number or area ratio of microvessel regions.

6. The image analysis-based hair and hair follicle health status detection system according to claim 4, characterized in that, The hair follicle region segmentation unit includes: Preprocessing subunit: used to denoise the enhanced image and remove noise from the image; Edge detection subunit: used to detect hair follicle edges, extract areas in the image where the brightness change is greater than a preset threshold, and generate a preliminary outline of the hair follicle boundary; Thresholding segmentation subunit: Based on the brightness or color distribution of the image, a dynamic adaptive thresholding segmentation algorithm is used to determine the hair follicle boundary. The determination expression is: Among them, I binary (x,y) represents the binary image values ​​after thresholding; I filtered (x, y) represents the denoised pixel value; T dynamic This is an adaptive dynamic threshold.

7. The image analysis-based hair and hair follicle health status detection system according to claim 5, characterized in that, The dermal papilla microvessel recognition unit includes: Texture analysis subunit: used to analyze the texture features in the hair follicle region image. It extracts the texture information of microvessels through the local binary mode algorithm and matches the texture features with the morphological features of blood vessels to identify the microvessel region. Edge detection subunit: used to identify the edges of microvessels in the image. It extracts detailed information of microvessels and marks them as potential microvessel regions by detecting gradient changes in the image. Microvessel morphology feature extraction subunit: used to extract the morphological features of microvessels, including vessel length, width, curvature and branching points; Microvascular region screening subunit: Used to screen regions that conform to microvascular characteristics based on extracted texture and edge features. By analyzing the connectivity, area and morphology of the regions, noisy regions that do not conform to microvascular characteristics are removed, and the distribution of microvessels in the hair papilla is finally determined.

8. The image analysis-based hair and hair follicle health status detection system according to claim 1, characterized in that, The health parameter calculation module includes a hair follicle activity index calculation unit and a hair density parameter calculation unit; wherein: Hair follicle activity index calculation unit: used to calculate the hair follicle activity index, which combines hair follicle morphology data and microvascular density data to calculate the activity index A by weighted average. Hair density parameter calculation unit: Used to calculate hair density parameters. By counting the number of hairs within the hair follicle region and combining this with the area of ​​the hair follicle region, it outputs the hair density parameter D. hair .

9. The image analysis-based hair and hair follicle health status detection system according to claim 1, characterized in that, The health status assessment module includes a health level calculation unit, a health status decision unit, and a test report generation unit; wherein: Health level calculation unit: used to calculate the overall health level by weighting the hair follicle activity index and hair density parameters according to the preset health level standards; Health Status Decision Unit: Used to calculate the comprehensive health level output by the health level unit and provide corresponding recommended measures or prompts; Test report generation unit: Used to automatically generate test reports based on health level and health status decision results, including hair follicle activity index, hair density parameters, comprehensive health level and related suggestions.

10. The image analysis-based hair and hair follicle health status detection system according to claim 9, characterized in that, The health level calculation unit includes: Data standardization subunit: used to standardize the hair follicle activity index and hair density parameters so that their values ​​are within a uniform range; Weighted calculation subunit: Used to perform weighted calculations on the standardized hair follicle activity index and hair density parameters according to preset weighting coefficients, and generate a comprehensive health score S. health ; Health Level Assessment Subunit: Used to calculate the comprehensive health score S based on preset health level standards. health Translated into specific health levels; When S health When the value is ≥0.8, the overall health level is excellent; When 0.6≤S health When the value is less than 0.8, the overall health level is considered good. When S health When the score is less than 0.6, the overall health level is poor.

Images