Hair follicle activity grading and positioning system and method based on multispectral imaging

Abstract

The embodiment of the invention provides a hair follicle activity grading and positioning system and method based on multispectral imaging, and relates to the technical field of hair follicle activity grading and positioning. The method comprises the following steps: acquiring reflected light information, and constructing image information based on the reflected light information; preprocessing the image information to obtain a first image; performing feature extraction on the first image to obtain a first feature and a second feature; determining the activity level of a target hair follicle based on the first feature and the second feature; and determining the position of the target hair follicle according to the first feature, the second feature and the activity grade. According to the invention, the problem of low positioning precision of hair follicle activity grading is solved, and the effect of improving the positioning precision of hair follicle activity grading is achieved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of hair follicle activity grading and positioning, and more specifically, to a hair follicle activity grading and positioning system and method based on multispectral imaging. Background Art

[0002] Hair follicles are important structures in the skin that are responsible for the growth and regeneration of hair. The health of hair follicles is directly related to the growth cycle and quality of hair.

[0003] Most existing hair follicle detection methods only focus on the morphological characteristics of hair follicles and lack a comprehensive analysis of the spectral information and morphological characteristics of hair follicles, making it difficult to accurately grade and locate hair follicle activity.

[0004] There is currently no better solution to the above problems. Summary of the Invention

[0005] The embodiments of the present invention provide a hair follicle activity grading and positioning system and method based on multispectral imaging, so as to at least solve the problem of low accuracy of hair follicle activity grading and positioning in the related art.

[0006] According to one embodiment of the present invention, a method for grading and locating hair follicle activity based on multispectral imaging is provided, comprising:

[0007] Acquiring reflected light information and constructing image information based on the reflected light information, wherein the reflected light information is obtained by illuminating the hair follicles with light sources of several different wavelengths and then detecting them with a multispectral detector;

[0008] Preprocessing the image information to obtain a first image;

[0009] Performing feature extraction on the first image to obtain a first feature and a second feature, wherein the first feature includes an image pixel feature and the second feature includes an image morphological feature;

[0010] determining an activity level of a target hair follicle based on the first feature and the second feature;

[0011] The position of the target hair follicle is determined according to the first feature, the second feature and the activity level.

[0012] In an exemplary embodiment, determining the location of the target hair follicle according to the first feature, the second feature, and the activity level includes:

[0013] determining the state information of the target hair follicle according to the first feature and the second feature;

[0014] determining the activity level according to the status information;

[0015] The position of the target hair follicle is determined according to the distribution of the activity levels.

[0016] In an exemplary embodiment, after determining the status information of the target hair follicle according to the first feature and the second feature, the method further includes:

[0017] performing normalization processing on the first feature and the second feature;

[0018] A correlation calculation is performed on the normalized first feature and the second feature. If the correlation calculation result does not meet the first condition, it is determined that the first feature and / or the second feature is abnormal.

[0019] In an exemplary embodiment, after determining the location of the target hair follicle according to the first feature, the second feature, and the activity level, the method further includes:

[0020] Matching the position results of the target hair follicles with a preset skin macro map;

[0021] If the matching result does not meet the second condition, it is determined that the location result is abnormal.

[0022] According to another embodiment of the present invention, a hair follicle activity grading and positioning system based on multispectral imaging is provided, comprising:

[0023] An image construction module, configured to obtain reflected light information and construct image information based on the reflected light information, wherein the reflected light information is obtained by illuminating the hair follicles with light sources of several different wavelengths and then detecting the follicles with a multispectral detector;

[0024] a preprocessing module, configured to preprocess the image information to obtain a first image;

[0025] a feature extraction module, configured to extract features from the first image to obtain a first feature and a second feature, wherein the first feature includes an image pixel feature and the second feature includes an image morphological feature;

[0026] an activity level determination module, configured to determine the activity level of the target hair follicle based on the first feature and the second feature;

[0027] A position determination module is used to determine the position of the target hair follicle according to the first feature, the second feature and the activity level.

[0028] In an exemplary embodiment, determining the location of the target hair follicle according to the first feature, the second feature, and the activity level includes:

[0029] determining the state information of the target hair follicle according to the first feature and the second feature;

[0030] determining the activity level according to the status information;

[0031] The position of the target hair follicle is determined according to the distribution of the activity levels.

[0032] In an exemplary embodiment, the system further comprises:

[0033] a normalization module, configured to perform normalization processing on the first feature and the second feature after determining the state information of the target hair follicle according to the first feature and the second feature;

[0034] The correlation calculation module is used to perform correlation calculation on the first feature and the second feature after normalization, and determine that the first feature and / or the second feature is abnormal when the correlation calculation result does not meet the first condition.

[0035] In an exemplary embodiment, the system further comprises:

[0036] a matching module, configured to match the position result of the target hair follicle with a preset skin macro map after determining the position of the target hair follicle according to the first feature, the second feature and the activity level;

[0037] The judgment module is used to determine that the location result is abnormal if the matching result does not meet the second condition.

[0038] According to yet another embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when run.

[0039] According to another embodiment of the present invention, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any one of the above method embodiments.

[0040] The present invention achieves quantitative evaluation of hair follicle activity by extracting the spectral and morphological characteristics of hair follicles, and accurately locates the hair follicles through feature fusion and classification methods. Therefore, the problem of low accuracy in grading and positioning hair follicle activity can be solved, thereby achieving the effect of improving the accuracy of grading and positioning hair follicle activity. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1is a flow chart of a method for grading and locating hair follicle activity based on multispectral imaging according to an embodiment of the present invention;

[0042] Figure 2 is a diagram of experimental results according to an embodiment of the present invention;

[0043] Figure 3 This is a structural block diagram of a hair follicle activity grading and positioning system based on multispectral imaging according to an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments.

[0045] Hereinafter, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature identified with "first," "second," etc., may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0046] In addition, in this application, directional terms such as "up", "down", "left", and "right" may be defined including but not limited to the orientation relative to the schematic placement of the components in the drawings. It should be understood that these directional terms may be relative concepts. They are used for relative descriptions and clarifications, and they may change accordingly according to changes in the orientation of the components in the drawings.

[0047] In this application, unless otherwise specified or limited, the term "connection" should be understood broadly. For example, "connection" can mean fixed connection, detachable connection, or integration; it can mean direct connection or indirect connection through an intermediate medium. In addition, the term "coupling" can refer to the manner in which electrical connection is achieved for signal transmission.

[0048] As used herein, "about," "substantially," or "approximately" includes the stated value and an average value that is within an acceptable range of deviation from the particular value as determined by one of ordinary skill in the art taking into account the measurements in question and the errors associated with the measurement of the particular quantity (i.e., the limitations of the measurement system).

[0049] In this embodiment, a method for grading and locating hair follicle activity based on multispectral imaging is provided. Figure 1 FIG. 1 is a flow chart of a method for grading and locating hair follicle activity based on multispectral imaging according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0050] Step S11, obtaining reflected light information and constructing image information based on the reflected light information, wherein the reflected light information is obtained by illuminating the hair follicles with light sources of several different wavelengths and then detecting them with a multispectral detector;

[0051] In this embodiment, the chemical components in hair follicles (such as melanin, hemoglobin, collagen, etc.) have significant absorption or reflection characteristics within specific wavelength ranges. For example, melanin has a strong absorption peak in the 600-700nm range, and hemoglobin has significant absorption in the 540-580nm range. The melanin and hemoglobin contents of hair follicles vary depending on their state. For example, hair follicles in the growth phase are active, with vigorous cell division and high melanin content; hair follicles in the catagen phase begin to degenerate, with reduced cell division and gradually decreasing melanin content; and hair follicles in the resting phase have the lowest melanin content. Therefore, the state of the hair follicles can be determined by detecting their reflection of reflected light.

[0052] In order to ensure the detection accuracy, multiple light sources with specific wavelengths are used to illuminate the target object during hair follicle reflected light detection, and detectors are used to receive reflected or transmitted light (such as Figure 2 and compose images such as an energy distribution diagram, a light intensity distribution diagram, a reflectivity distribution diagram, and a spectral characteristic distribution diagram according to the energy distribution, light intensity distribution, reflectivity distribution, and spectral characteristic distribution of the reflected light or the transmitted light in the preset area.

[0053] It is easy to understand that the reflected light information includes the aforementioned energy distribution, light intensity distribution, reflectivity distribution, spectral characteristic distribution, etc.; because hair follicles in different states absorb light differently, the energy distribution and other information are also different. For example, the energy in area A is a1, the reflected light intensity is a2, the reflectivity is a3, and the spectral characteristic is a4; the energy in area B is b1, the reflected light intensity is b2, the reflectivity is b3, and the spectral characteristic is b4. At this time, by fusing the energy distribution map, it can be determined that the hair follicles in area A are in state a and the hair follicles in area B are in state b, and thus it can be determined that areas A and B are the head, underarms, face, etc. of the target object, and so on.

[0054] It should be noted that when collecting reflected light, a high-resolution multispectral camera can be used. This device covers the visible light to near-infrared band (such as 400-1000nm), capturing the absorption and reflection characteristics of the hair follicle area to light of different wavelengths. The sensitive bands of oxygenated / deoxygenated hemoglobin that can reflect the blood supply and metabolic activity of the hair follicles (such as 530-590nm and 760-850nm) are all within the camera capture band, so using this device can achieve better results. Of course, a CMOS camera can also be used, which is not limited here.

[0055] Step S12, preprocessing the image information to obtain a first image;

[0056] In this embodiment, the image is pre-processed to reduce interference from debris, thereby improving subsequent detection accuracy.

[0057] The preprocessing includes at least one of aligning images of different wavelengths to eliminate offsets caused by equipment or motion, using wavelet transform or non-local mean filtering to reduce imaging noise, and eliminating the effects of illumination differences through histogram matching or white balance processing; the first image includes images such as a preprocessed energy distribution map, a light intensity distribution map, a reflectivity distribution map, and a spectral characteristic distribution map; and image alignment can be implemented based on the following code:

[0058]

[0059] Step S13: performing feature extraction on the first image to obtain a first feature and a second feature, wherein the first feature includes an image pixel feature, and the second feature includes an image morphology feature;

[0060] In this embodiment, the image pixel features are combined with the image morphological features to judge the status of the hair follicles in the image from multiple dimensions, thereby improving the judgment accuracy of the hair follicle status.

[0061] Among them, the image pixel features mainly reflect the spectral information of the image, including the mean pixel value and spectral intensity of each area in the image. The following takes spectral intensity as an example to illustrate:

[0062] First, according to the spectral characteristics of hair follicles, the wavelength range related to hair follicle activity is selected, and then for each wavelength, the spectral intensity I of each pixel in the image is calculated. λ (x, y), and normalize the spectral intensity to the range of 0, 1 for subsequent processing; then calculate the average spectral intensity μ of all pixels in the image according to formula 1 λ , and then the skewness and kurtosis of the spectral intensity can be further calculated based on the average spectral intensity and the spectral intensity as needed to reflect the shape of the spectral distribution.

[0063]

[0064] Where, is the normalized spectral intensity.

[0065] Image morphological features mainly reflect the shape, texture, and structure of hair follicles, such as the length, diameter, and curvature of the hair follicles. These features can help assess the health and activity of hair follicles. Specifically, edge detection algorithms (such as Canny edge detection) can be used to extract the edges of the hair follicles, extract the contours of the hair follicles from the edge image, and then calculate the length, diameter, curvature, etc. of the hair follicles. The curvature can be calculated using the following formula 2:

[0066]

[0067] Where S is the area of the hair follicle and P is the perimeter of the hair follicle.

[0068] Based on this, the shape factors of the hair follicles, such as circularity and ellipticity, can be further calculated as needed:

[0069]

[0070] Where MA is the length of the major axis of the hair follicle, Mi is the length of the minor axis of the hair follicle, and Ci is the shape factor.

[0071] The extracted first and second features are then fused to form a comprehensive feature vector for subsequent hair follicle activity classification and positioning.

[0072] Step S14, determining the activity level of the target hair follicle based on the first feature and the second feature;

[0073] In this embodiment, a neural network is used to fuse the first feature and the second feature to obtain the state feature vector of the hair follicle. Then the feature vector The data is input into a pre-trained neural network model to classify the feature vectors of the target hair follicles and determine their activity levels based on the classification results. The activity levels include growth phase, regression phase, resting phase, etc.

[0074] Among them, the eigenvector The weighted values of the first and second features need to be dynamically adjusted according to the state of the hair follicles, as shown in the following formula 4-5:

[0075]

[0076] β = 1 - α (Formula 5)

[0077] Where P1 is the first characteristic discrimination (e.g., the reflectivity difference between the growth phase and the resting phase at 760 nm), and P2 is the second characteristic discrimination (e.g., the variance ratio of the morphological characteristics (such as area) of the two types of hair follicles).

[0078] Step S15: determining the location of the target hair follicle according to the first feature, the second feature, and the activity level.

[0079] In this embodiment, the image is first segmented to isolate the hair follicle region from the multispectral image to facilitate subsequent analysis and location. Specifically, an appropriate threshold is selected based on spectral characteristics (such as light intensity at a specific wavelength) to separate the hair follicle region from the background. For example, an edge detection algorithm (such as Canny edge detection) is used to extract the edges of the hair follicles, and then the hair follicle region is determined through contour extraction. Alternatively, a region growing or segmentation algorithm (such as the Watershed algorithm) is used to segment the hair follicle region. Other methods are also possible and are not limited here. The state of the target hair follicle is then determined based on the first and second characteristics and the activity level, and the location of the hair follicle is determined based on the distribution of the hair follicle state.

[0080] Wherein, determining the location of the target hair follicle according to the first feature, the second feature, and the activity level includes:

[0081] Step S151, determining the state information of the target hair follicle according to the first feature and the second feature;

[0082] Step S152, determining the activity level according to the state information;

[0083] Step S153: determining the location of the target hair follicle according to the distribution of the activity levels.

[0084] In this embodiment, the activity level of the target hair follicle is determined based on its state, and then the hair follicle positioning is optimized based on the spatial distribution of the activity level, excluding low-activity noise areas, thereby determining the activity level distribution of the target hair follicle; and then the most likely position of the target hair follicle is determined.

[0085] For example, the number of A1 levels in area A is a1, the number of A2 levels is a2, the number of A3 levels is a3, the number of A1 levels in area B is b1, the number of A2 levels is b2, the number of A3 levels is b3... This distribution feature is consistent with the distribution of hair follicle activity levels at position 1 in the historical data. Therefore, it can be judged that the location of the target hair follicle cluster may be at position 1, and so on.

[0086] The activity level can be determined by trained support vector models (SVM), random forests (RandomForest) or convolutional neural networks (CNN), etc. Input into the trained model, and the model outputs the corresponding activity level.

[0087] The process of determining the location of the hair follicles includes first mapping the activity level onto the image to generate an activity level distribution map, then matching the activity level distribution map with the level distribution of each location in the historical data, and using the location with the highest matching degree as the location of the hair follicle; in addition, the center of mass of the area with the highest activity level can be calculated based on the distribution of activity levels, and the center of mass can be used as the location of the target hair follicle, which is not limited here.

[0088] For example, input image: multispectral hair follicle region (including 3 adhered hair follicles).

[0089] S151: Extracting state information, it is found that the spectral reflectance of hair follicle A is extremely low at 760nm (S1′=0.1S1′=0.1) and the area is large (G1′=0.9G1′=0.9).

[0090] S152: Logistic regression output P(growth period) = 0.92, and it is determined to be the growth period.

[0091] S153:

[0092] S1531: Filter the resting phase area and retain follicles A and B;

[0093] S1532: The watershed algorithm uses follicle A as the seed point to segment the precise boundary;

[0094] S1533: Output the center of mass coordinates (x=120, y=85) (x=120, y=85), which are the position coordinates of the target hair follicle.

[0095] The following is part of the code for calculating the hair follicle position:

[0096] #Select the contour with the highest activity level

[0097] target_contour=contours[np.argmax(activity_levels)]

[0098] #Calculate the center of mass

[0099] M=cv2.moments(target_contour)

[0100] x_c = int(M['m10'] / M['m00'])

[0101] y_c=int(M['m01'] / M['m00'])

[0102] print(f'Target Follicle Position:({x_c},{y_c})')

[0103] # draw the centroid

[0104] cv2.circle(activity_map,(x_c,y_c),5,(0,0,255),-1)

[0105] cv2.imshow('Activity Map with Centroid',activity_map)

[0106] cv2.waitKey(0)

[0107] cv2.destroyAllWindows()

[0108] Particularly, after determining the state information of the target hair follicle according to the first feature and the second feature, the method further includes:

[0109] Step S154: normalizing the first feature and the second feature;

[0110] Step S155 , performing correlation calculation on the normalized first feature and the second feature. If the correlation calculation result does not meet the first condition, it is determined that the first feature and / or the second feature is abnormal.

[0111] In this embodiment, to further ensure the accuracy of data calculation, it is necessary to determine the correlation between the first feature and the second feature. Generally, the pixel features and morphological features of the same hair follicle area are correlated. For example, hair follicles in the growth phase have a higher melanin content, and at the same time, their hair follicles have a smaller area and a higher curvature. Therefore, by determining the correlation between the first feature and the second feature, it can be determined whether the relevant data is normal.

[0112] Among them, the calculation of the correlation value can be achieved based on the Pearson correlation coefficient. The first condition can be that the correlation value between the hair follicle area and the near-infrared band reflectance is negatively correlated. At this time, the correlation value should be less than -0.3, otherwise it is judged to be abnormal, and so on; in addition, the first feature and the second feature can be combined into corresponding first feature matrices and second feature matrices according to the location of the features. The matrix elements are the eigenvalues of the feature locations, and then the features are converted into pixel grayscale values. Thus, the feature matrix can be regarded as a feature pixel map, and then its confidence is calculated through the softmax function of the neural network. When the confidence of the two feature pixel maps are within the preset range, it means that the two features are normal, otherwise it is judged to be abnormal and requires further debugging.

[0113] Through the above steps, the quantitative evaluation of hair follicle activity is achieved by extracting the spectral characteristics and morphological characteristics of hair follicles, and the precise positioning of hair follicles is achieved through feature fusion and classification methods, which solves the problem of low accuracy in hair follicle grading and positioning, and improves the accuracy of hair follicle activity grading and positioning.

[0114] In an optional embodiment, after determining the location of the target hair follicle according to the first feature, the second feature and the activity level, the method further includes:

[0115] Step S16, matching the target hair follicle position result with a preset skin macro map;

[0116] Step S17: If the matching result does not meet the second condition, it is determined that the location result is abnormal.

[0117] In this embodiment, after obtaining the position information of the target hair follicle, in order to further ensure the accuracy of the position information, it is necessary to match the obtained result with a preset skin macro map to determine whether the obtained position information is accurate.

[0118] Specifically, the coordinates of the located hair follicles are mapped to the skin macroscopic map, where the skin macroscopic map includes the pre-processed anatomical structure. The mapping process requires converting the target hair follicle coordinates to the macroscopic map coordinate system, and then checking whether the hair follicles fall into the expected anatomical partition. If the macroscopic map contains reference follicle annotations, the position coincidence and density consistency D are calculated. i , the distance between adjacent hair follicles should be greater than the minimum threshold, etc. When these parameters meet the preset requirements, it is judged that the second condition is met, otherwise it is judged that the second condition is not met. Among them, the density consistency can be calculated by the following formula 6:

[0119]

[0120] Where Ni is the number of hair follicles in region i, and Si is the area of region i.

[0121] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0122] This embodiment also provides a hair follicle activity grading and localization system based on multispectral imaging. This system is used to implement the aforementioned embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0123] Figure 3 FIG. 1 is a structural block diagram of a hair follicle activity grading and positioning system based on multispectral imaging according to an embodiment of the present invention. Figure 3 As shown, the system includes:

[0124] An image construction module 31 is configured to obtain reflected light information and construct image information based on the reflected light information, wherein the reflected light information is obtained by illuminating the hair follicles with light sources of several different wavelengths and then detecting them with a multispectral detector;

[0125] A preprocessing module 32, configured to preprocess the image information to obtain a first image;

[0126] a feature extraction module 33 configured to extract features from the first image to obtain a first feature and a second feature, wherein the first feature includes an image pixel feature and the second feature includes an image morphological feature;

[0127] an activity level determination module 34, configured to determine the activity level of the target hair follicle based on the first feature and the second feature;

[0128] The position determination module 35 is configured to determine the position of the target hair follicle according to the first feature, the second feature and the activity level.

[0129] In an optional embodiment, determining the location of the target hair follicle according to the first feature, the second feature, and the activity level includes:

[0130] determining the state information of the target hair follicle according to the first feature and the second feature;

[0131] The activity level is determined based on the status information.

[0132] In an optional embodiment, the system further includes:

[0133] a normalization module, configured to perform normalization processing on the first feature and the second feature after determining the state information of the target hair follicle according to the first feature and the second feature;

[0134] The correlation calculation module is used to perform correlation calculation on the first feature and the second feature after normalization, and determine that the first feature and / or the second feature is abnormal when the correlation calculation result does not meet the first condition.

[0135] In an optional embodiment, the system further includes:

[0136] a matching module, configured to match the position result of the target hair follicle with a preset skin macro map after determining the position of the target hair follicle according to the first feature, the second feature and the activity level;

[0137] The judgment module is used to determine that the location result is abnormal if the matching result does not meet the second condition.

[0138] It should be noted that the above modules can be implemented through software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0139] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when running.

[0140] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0141] An embodiment of the present invention further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0142] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0143] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0144] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0145] Units described as separate components may or may not be physically separate, and components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0146] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0147] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0148] The above content is only a specific embodiment of this application, but the scope of protection of this application is not limited to this. Any changes or replacements within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for grading and locating hair follicle activity based on multispectral imaging, characterized in that: include: Acquiring reflected light information and constructing image information based on the reflected light information, wherein the reflected light information is obtained by illuminating the hair follicles with light sources of several different wavelengths and then detecting them with a multispectral detector; Preprocessing the image information to obtain a first image; Performing feature extraction on the first image to obtain a first feature and a second feature, wherein the first feature includes an image pixel feature and the second feature includes an image morphological feature; determining an activity level of a target hair follicle based on the first feature and the second feature; The position of the target hair follicle is determined according to the first feature, the second feature and the activity level.

2. The method according to claim 1, characterized in that The determining the position of the target hair follicle according to the first feature, the second feature and the activity level includes: determining the state information of the target hair follicle according to the first feature and the second feature; determining the activity level according to the status information; The position of the target hair follicle is determined according to the distribution of the activity levels.

3. The method according to claim 2, characterized in that After determining the state information of the target hair follicle according to the first feature and the second feature, the method further includes: performing normalization processing on the first feature and the second feature; A correlation calculation is performed on the normalized first feature and the second feature. If the correlation calculation result does not meet the first condition, it is determined that the first feature and / or the second feature is abnormal.

4. The method according to claim 1, wherein After determining the location of the target hair follicle according to the first feature, the second feature, and the activity level, the method further includes: Matching the position results of the target hair follicles with a preset skin macro map; If the matching result does not meet the second condition, it is determined that the location result is abnormal.

5. A hair follicle activity grading and positioning system based on multispectral imaging, characterized in that: include: An image construction module, configured to obtain reflected light information and construct image information based on the reflected light information, wherein the reflected light information is obtained by illuminating the hair follicles with light sources of several different wavelengths and then detecting the follicles with a multispectral detector; a preprocessing module, configured to preprocess the image information to obtain a first image; a feature extraction module, configured to extract features from the first image to obtain a first feature and a second feature, wherein the first feature includes an image pixel feature and the second feature includes an image morphological feature; an activity level determination module, configured to determine the activity level of the target hair follicle based on the first feature and the second feature; A position determination module is used to determine the position of the target hair follicle according to the first feature, the second feature and the activity level.

6. The system according to claim 5, characterized in that The determining the position of the target hair follicle according to the first feature, the second feature and the activity level includes: determining the state information of the target hair follicle according to the first feature and the second feature; determining the activity level according to the status information; The position of the target hair follicle is determined according to the distribution of the activity levels.

7. The system according to claim 6, characterized in that The system further comprises: a normalization module, configured to perform normalization processing on the first feature and the second feature after determining the state information of the target hair follicle according to the first feature and the second feature; The correlation calculation module is used to perform correlation calculation on the first feature and the second feature after normalization, and determine that the first feature and / or the second feature is abnormal when the correlation calculation result does not meet the first condition.

8. The system according to claim 5, wherein: The system further comprises: a matching module, configured to match the position result of the target hair follicle with a preset skin macro map after determining the position of the target hair follicle according to the first feature, the second feature and the activity level; The judgment module is used to determine that the location result is abnormal if the matching result does not meet the second condition.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 4 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 4.

Images