Effect evaluation method and system for hair care and hair growth

Abstract

The invention relates to the field of image processing, in particular to an effect evaluation method and system for hair care and hair growth. The method comprises the steps that a hair image is acquired, image preprocessing is carried out through a multi-dimensional gradient aggregation enhancement algorithm, and an enhanced image is obtained; performing feature extraction on the enhanced image through a multi-level adaptive texture analysis algorithm to obtain a comprehensive feature vector; based on the comprehensive feature vector, generating a binary feature map through an adaptive threshold method; based on the binary feature map, a phase transformation matrix is constructed through a dynamic phase transformation tracking algorithm, and the growth rate is calculated; based on the growth rate, the hair growth amount is calculated, and a comprehensive evaluation report is generated. The problem that a traditional evaluation method cannot provide systematic analysis on key indexes such as hair growth, density and glossiness is solved; the real-time tracking and analysis capability on the dynamic change of hair growth is lacked; the operation is complicated, the result is difficult to read, and the wide application is limited.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and particularly to a method and system for evaluating the effects of hair care and hair growth promotion. Background Art

[0002] With the increasing attention of people to beauty and health, the demand for hair care and hair growth promotion products continues to rise. Hair is not only an important part of personal image but also an external manifestation of health status. Good hair quality and sufficient hair are widely regarded as symbols of beauty and health. Therefore, more and more consumers begin to pay attention to the use effects of hair care and hair growth promotion products. In this context, the importance of scientifically evaluating the effects of hair care and hair growth promotion becomes even more prominent.

[0003] However, traditional evaluation methods often rely on consumers' subjective feelings and simple image comparison. This way not only lacks objectivity but is also easily affected by personal emotions and subjective judgments. At the same time, traditional evaluation methods fail to provide systematic and quantitative effect evaluation criteria, making it often confusing for users to choose hair care products and difficult to make wise decisions.

[0004] In summary, the traditional evaluation methods have the following technical problems: lacking scientific and objective evaluation criteria and being unable to provide systematic analysis of key indicators such as hair growth, density, and gloss; lacking the ability to track and analyze the dynamic changes of hair growth in real time and being unable to timely understand the hair care effects; being lacking in user experience, with complex operations and difficult-to-interpret results, which limits their application in the broad consumer market. Summary of the Invention

[0005] The present invention provides a method and system for evaluating the effects of hair care and hair growth promotion to solve the problems of traditional evaluation methods lacking scientific and objective evaluation criteria and being unable to provide systematic analysis of key indicators such as hair growth, density, and gloss; lacking the ability to track and analyze the dynamic changes of hair growth in real time and being unable to timely understand the hair care effects; being lacking in user experience, with complex operations and difficult-to-interpret results, which limits their application in the broad consumer market.

[0006] A method and system for evaluating the effects of hair care and hair growth promotion according to the present invention specifically include the following technical solutions:

[0007] A method for evaluating the effects of hair care and hair growth promotion includes the following steps:

[0008] S1. Obtain hair images and perform image preprocessing through a multi-dimensional gradient aggregation enhancement algorithm to obtain enhanced images;

[0009] S2. Extract features from the enhanced image through a multi-level adaptive texture analysis algorithm to obtain a comprehensive feature vector; generate a binary feature map based on the comprehensive feature vector through an adaptive threshold method.

[0010] S3. Based on the binary feature map, construct a phase transformation matrix through a dynamic phase transformation tracking algorithm; calculate the growth rate based on the phase transformation matrix; calculate the hair growth amount based on the growth rate, and generate a comprehensive evaluation report.

[0011] Preferably, S1 specifically includes:

[0012] During the implementation of the multi-dimensional gradient aggregation enhancement algorithm, calculate the gradients of the hair image in the horizontal and vertical directions respectively through the Sobel operator.

[0013] Preferably, S1 specifically includes:

[0014] Based on the gradients of the hair image in the horizontal and vertical directions, calculate the comprehensive gradient information by combining spatial gradient and temporal change information.

[0015] Preferably, S1 specifically includes:

[0016] Introduce an adjustment factor for the enhancement intensity, weight the comprehensive gradient information, and generate an enhanced image.

[0017] Preferably, S2 specifically includes:

[0018] During the implementation of the multi-level adaptive texture analysis algorithm, decompose the enhanced image through the pyramid decomposition technique to construct a multi-level image and obtain the image after pyramid decomposition.

[0019] Preferably, S2 specifically includes:

[0020] Based on the image after pyramid decomposition, calculate the adaptive texture feature vector; perform multi-level fusion on the adaptive texture feature vectors at different levels to obtain a comprehensive feature vector; obtain a dynamically calculated threshold based on the mean and standard deviation of the comprehensive feature vector distribution, and optimize the feature extraction through the adaptive threshold method to generate a binary feature map.

[0021] Preferably, S3 specifically includes:

[0022] During the implementation of the dynamic phase transformation tracking algorithm, construct a phase transformation matrix based on the binary feature map and the conjugate of the binary feature map.

[0023] Preferably, S3 specifically includes:

[0024] Dynamically update the phase transformation matrix, and estimate the growth rate through phase changes.

[0025] Preferably, the S3 specifically includes:

[0026] Combine the growth rate with the phase information to calculate the hair growth amount. The specific formula is:

[0027]

[0028] where G estimate represents the hair growth amount; R(x, y) represents the growth rate of hair at the position (x, y); P t (x, y) represents the phase transformation matrix at time t; φ is the phase offset of the growth direction; λ is the attenuation factor.

[0029] An effect evaluation system for hair care and growth promotion includes the following parts:

[0030] An image acquisition module, an image preprocessing module, a feature extraction module, a growth evaluation module, and a report generation module;

[0031] The image acquisition module takes multi-angle photos of the hair to obtain hair images; the image acquisition module transmits the hair images to the image preprocessing module;

[0032] The image preprocessing module calculates the gradients of the hair image in the horizontal and vertical directions; based on the gradients of the hair image in the horizontal and vertical directions, calculates the comprehensive gradient information; weights the comprehensive gradient information to generate an enhanced image; the image preprocessing module transmits the enhanced image to the feature extraction module;

[0033] The feature extraction module decomposes the enhanced image through the pyramid decomposition technology to construct a multi-level image, extracts multi-scale information to obtain the image after pyramid decomposition; based on the image after pyramid decomposition, calculates the adaptive texture feature vector; fuses the adaptive texture feature vectors at different levels to obtain the comprehensive feature vector; based on the comprehensive feature vector, optimizes and extracts features through the adaptive threshold method to generate a binary feature map; the feature extraction module transmits the binary feature map to the growth evaluation module;

[0034] The growth evaluation module constructs a phase transformation matrix based on the binary feature map; dynamically updates the phase transformation matrix, and estimates the growth rate through phase changes; calculates the hair growth amount based on the growth rate; the growth evaluation module transmits the hair growth amount result to the report generation module;

[0035] The report generation module generates a comprehensive evaluation report, including the results of growth rate, density change, and texture analysis, providing a scientific basis for the evaluation of hair care and growth promotion effects.

[0036] The beneficial effects of the technical solution of the present invention are as follows:

[0037] 1. The effect evaluation system combines multiple algorithms such as multi-dimensional gradient aggregation enhancement, pyramid decomposition, and dynamic phase transformation tracking to eliminate noise in the hair image, enhance the saliency of the hair image edges and textures; it can track the hair growth changes in real time, reflect the dynamic changes of the hair at different time periods, and accurately evaluate the hair growth rate, density changes, and texture features.

[0038] 2. The effect evaluation system extracts various features of the hair, including thickness, density, and distribution, etc., through an adaptive texture analysis algorithm, and then generates a comprehensive feature vector, so as to comprehensively reflect the hair health status.

[0039] 3. The final generated comprehensive evaluation report contains information such as growth rate, density changes, and texture analysis, enabling consumers to easily understand the actual effects of hair care and hair growth products, providing a scientific basis for the development and improvement of hair care products, and helping enterprises optimize the formulations of hair care and hair growth products according to user feedback and effect evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a structural diagram of an effect evaluation system for hair care and hair growth according to the present invention;

[0041] Figure 2 It is a flowchart of an effect evaluation method for hair care and hair growth according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of the present invention.

[0044] The following specifically describes the specific solutions of an effect evaluation method and system for hair care and hair growth provided by the present invention in conjunction with the accompanying drawings.

[0045] Referring to the attached Figure 1 , which shows a structural diagram of an effect evaluation system for hair care and hair growth provided by an embodiment of the present invention. The system includes the following parts:

[0046] An image acquisition module, an image preprocessing module, a feature extraction module, a growth evaluation module, and a report generation module;

[0047] The image acquisition module uses a camera to take multi-angle photos of the hair to ensure that the state of the hair can be clearly shown at each angle (such as the front, side, and back), and obtains the hair image; the image acquisition module transmits the hair image to the image preprocessing module;

[0048] The image preprocessing module calculates the gradients of the hair image in the horizontal and vertical directions; based on the gradients of the hair image in the horizontal and vertical directions, calculates the comprehensive gradient information; weights the comprehensive gradient information to generate an enhanced image; the image preprocessing module transmits the enhanced image to the feature extraction module;

[0049] The feature extraction module decomposes the enhanced image through the pyramid decomposition technology to construct a multi-level image, extracts multi-scale information, and obtains the image after pyramid decomposition to obtain hair features at different resolutions; based on the image after pyramid decomposition, calculates the adaptive texture feature vector to capture various texture features of the hair; performs multi-level fusion on the adaptive texture feature vectors at different levels to obtain the comprehensive feature vector; based on the comprehensive feature vector, optimizes the extraction of features through the adaptive threshold method to generate a binary feature map; the feature extraction module transmits the binary feature map to the growth evaluation module;

[0050] The growth evaluation module constructs a phase transformation matrix based on the binary feature map to real-time track the hair growth changes; dynamically updates the phase transformation matrix, calculates the growth rate, and reflects the speed and direction of hair growth; based on the growth rate, calculates the hair growth amount to evaluate the overall hair growth situation; the growth evaluation module transmits the hair growth amount result to the report generation module;

[0051] The report generation module generates a comprehensive evaluation report, including the results of growth rate, density change, and texture analysis, providing a scientific basis for the evaluation of hair care and hair growth effects.

[0052] Refer to Appendix Figure 2 , which shows a flowchart of a method for evaluating the effect of hair care and hair growth provided by an embodiment of the present invention. The method includes the following steps:

[0053] S1. Obtain a hair image and perform image preprocessing through a multi-dimensional gradient aggregation enhancement algorithm to obtain an enhanced image;

[0054] Select multiple perspectives of the hair (such as front, side, back), use the camera to take multi-angle photos of the hair, ensure that the state of the hair can be clearly displayed at each angle, and obtain hair images; set the input hair image as I(x, y), and then perform three stages on the hair image in sequence: image preprocessing, feature extraction, and growth evaluation.

[0055] In the image preprocessing stage, based on the hair image, through the multi-dimensional gradient aggregation enhancement algorithm, an enhanced image is obtained to improve the clarity of the hair image and eliminate noise;

[0056] The specific implementation process of the multi-dimensional gradient aggregation enhancement algorithm is as follows: First, through the Sobel operator, calculate the gradients of the hair image in the horizontal and vertical directions respectively. The specific formulas are as follows:

[0057]

[0058] where, G x (x, y) and G y (x, y) represent the gradients of the hair image in the x direction (horizontal direction) and y direction (vertical direction) respectively, which are used to reflect the change intensity of the hair image in the horizontal and vertical directions; i represents the offset in the x direction of the hair image, and j represents the offset in the y direction of the hair image; Sobel 1 is the Sobel convolution kernel in the horizontal direction; Sobel 2 is the Sobel convolution kernel in the vertical direction; G is the surrounding local area of each pixel in the image I(x, y);

[0059] Then, based on the gradients of the hair image in the horizontal and vertical directions, calculate the comprehensive gradient information to reflect the edge information in the hair image; the specific formula is:

[0060]

[0061] where, G(x, y) represents the comprehensive gradient information, which represents the change intensity of each pixel position in the hair image, that is, the degree of change at that position or the obviousness of the edge. The larger the total gradient amplitude, the clearer the details of the hair image; γ is a weight factor used to control the time change, and its value ranges from 0 to 1; is the derivative of the hair image with respect to time, approximated by the difference between consecutive time-frame hair images, which reflects the impact of dynamic changes on feature enhancement. By combining spatial gradient and time change information, the enhancement effect is more comprehensive and accurate;

[0062] Furthermore, weight the comprehensive gradient information to generate the enhanced image. The specific formula is:

[0063]

[0064] Among them, I en (x, y) represents the enhanced image, which is used to improve the hair image so that the hair features (such as texture, edges, etc.) in the hair image are more obvious; α is the adjustment factor for the enhancement intensity, which is set between 0.5 and 1.5, and the specific value can be adjusted according to actual needs, and is used to control the degree of image enhancement; max(G) is the maximum value of the comprehensive gradient information, which is used to ensure that the hair image is not distorted when enhanced, improve the saliency of the hair image edges and textures, and make the subsequent feature extraction more accurate.

[0065] S2. Through the multi-level adaptive texture analysis algorithm, feature extraction is performed on the enhanced image to obtain a comprehensive feature vector; based on the comprehensive feature vector, a binary feature map is generated through the adaptive threshold method;

[0066] After image preprocessing, it enters the feature extraction stage, and through the multi-level adaptive texture analysis algorithm, feature extraction is performed on the enhanced image;

[0067] The specific implementation process of the multi-level adaptive texture analysis algorithm is as follows: First, the enhanced image is decomposed through the pyramid decomposition technology to construct a multi-level image, and the image after pyramid decomposition is obtained, and each layer of the image is divided into uniform small regions to obtain hair features at different resolutions; the pyramid decomposition technology can effectively capture information at different scales of the enhanced image, so that subsequent feature extraction can synthesize data at multiple levels; the specific formula for pyramid decomposition is:

[0068]

[0069] Among them, I p (x, y) represents the p-th layer image after pyramid decomposition, which is used to extract hair features at different resolutions; K is the normalization factor, which is set to the total number of image pixels in the region; is the neighborhood of the pixel (x, y) in the enhanced image, and the neighborhood size can be determined according to specific image features. For example, a 3×3 or 5×5 window is selected; I en (i, j) is a reference to the specific pixel value of the enhanced image, and (i, j) are the pixel coordinates of interest during feature extraction. By constructing a multi-level structure, hair information at multiple scales is extracted, and the correlation between different features is enhanced;

[0070] Based on the image after pyramid decomposition, an adaptive texture feature vector is calculated to capture various texture features of the hair, and the specific formula is as follows:

[0071]

[0072] Among them, T p (x, y) represents the adaptive texture feature vector of the p-th layer, which contains texture intensity information in multiple directions; k represents the number of pixels offset in the x and y directions of the image after pyramid decomposition. The summation result of each term calculates the intensity of the image in different directions after pyramid decomposition. By summing the intensities in multiple directions, the texture features of the hair are captured. For example, the first term calculates the intensity in the horizontal direction, the second term is the intensity in the vertical direction, and other terms consider the intensity in the diagonal direction. The adaptive texture feature vector reflects the thickness, distribution, and structural information of the hair;

[0073] The adaptive texture feature vectors at different levels are fused at multiple levels to obtain a comprehensive feature vector. The specific formula is:

[0074] T com (x, y) = β · T p (x, y) + (1 - β) · T p-1 (x, y)

[0075] Among them, T com (x, y) represents the comprehensive feature vector after multi-level fusion; β is the fusion coefficient, with a value between [0, 1], used to control the influence weight of each layer of adaptive texture feature vector; T p-1 (x, y) represents the adaptive texture feature vector of the (p - 1)-th layer. By fusing the multi-level adaptive texture feature vectors, the overall features of the hair are described more comprehensively, enhancing the accuracy of subsequent analysis.

[0076] Based on the comprehensive feature vector, the features are optimized and extracted through the adaptive threshold method to generate a binary feature map, thereby eliminating irrelevant information and focusing on the actual hair features, providing effective input data for subsequent growth assessment; the specific calculation formula of the binary feature map is:

[0077]

[0078] Among them, F(x, y) represents the binary feature map; T threshold is a dynamically calculated threshold, which depends on the mean and standard deviation of the comprehensive feature vector distribution to ensure that the extracted comprehensive feature vector meets specific criteria. The specific formula of the dynamically calculated threshold is:

[0079]

[0080] Among them, is a constant, with a value between 1 and 2; μ and σ are the mean and standard deviation of the comprehensive feature vector distribution respectively.

[0081] S3. Based on the binary feature map, construct a phase transformation matrix through the dynamic phase transformation tracking algorithm; based on the phase transformation matrix, calculate the growth rate; based on the growth rate, calculate the hair growth amount, and generate a comprehensive evaluation report.

[0082] After the feature extraction stage, enter the growth evaluation stage; based on the binary feature map, use the dynamic phase transformation tracking algorithm to track the hair growth changes in real time and construct a phase transformation matrix. The specific formula is:

[0083]

[0084] Among them, P t (x, y) represents the phase transformation matrix at time t; F t (x, y) is the binary feature map at time t; * represents the conjugate operation, and the conjugate of the binary feature map is used to ensure the accuracy of the phase information. The phase transformation matrix can reflect the displacement information of the binary feature map in the time series, and track the position change of the hair in the spatial domain through the phase information in the frequency domain to ensure the accuracy of the tracking.

[0085] Dynamically update the phase transformation matrix to track the growth rate; the calculation formula for the growth rate is:

[0086]

[0087] Among them, R(x, y) represents the growth rate of the hair at the position (x, y), which is used to reflect the speed and direction of hair growth; Δt represents the time interval, and its value is the actual time difference between two time frames; N is the total number of time frames required for dynamically updating the phase transformation matrix. Estimate the hair growth rate through the phase change to ensure accurate dynamic growth information.

[0088] Based on the growth rate, calculate the hair growth amount:

[0089]

[0090] Among them, G estimate represents the hair growth amount, which is used to reflect the overall hair growth situation; φ is the phase offset of the growth direction, representing the main direction of hair growth; λ is the attenuation factor, which is used to reflect the possible attenuation situation during the growth process, and its specific value can be set according to experience, usually in the range of [0, 1]. By combining the growth rate with the phase information, accurately evaluate the overall hair growth situation.

[0091] The finally generated comprehensive evaluation report includes the comprehensive evaluation of the growth rate, density change and texture analysis, providing a scientific basis for the evaluation of hair care and hair growth effects.

[0092] In summary, a method and system for evaluating the effect of hair care and hair growth are completed.

[0093] The order of the invention embodiments is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0094] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. The key point of each embodiment is to illustrate the differences from other embodiments.

[0095] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for evaluating the effect of hair care and growth, characterized in that: The following steps are involved: S1, obtaining a hair image, and performing image preprocessing through a multi-dimensional gradient aggregation enhancement algorithm to obtain an enhanced image; S2. Extract features from the enhanced image using a multi-level adaptive texture analysis algorithm to obtain a comprehensive feature vector; based on the comprehensive feature vector, generate a binary feature map using an adaptive threshold method; S3, based on the binary feature map, construct a phase transformation matrix through a dynamic phase transformation tracking algorithm; Based on the phase transformation matrix, the growth rate is calculated; based on the growth rate, the hair growth amount is calculated and a comprehensive evaluation report is generated.

2. A method for evaluating the effect of hair care and growth according to claim 1, characterized in that: The S1 specifically includes: In the implementation of the multi-dimensional gradient aggregation enhancement algorithm, the gradients of the hair image in the horizontal and vertical directions are calculated respectively through the Sobel operator.

3. A method for evaluating the effect of hair care and growth according to claim 2, characterized in that: The S1 specifically includes: Based on the gradients of the hair image in the horizontal and vertical directions, the comprehensive gradient information is calculated by combining the spatial gradient and the temporal variation information.

4. A method for evaluating the effect of hair care and growth according to claim 3, characterized in that: The S1 specifically includes: An adjustment factor of the enhancement strength is introduced to weight the comprehensive gradient information to generate an enhanced image.

5. A method for evaluating the effect of hair care and growth according to claim 1, characterized in that: The S2 specifically includes: In the process of realizing the multi-level adaptive texture analysis algorithm, the enhanced image is decomposed by pyramid decomposition technology to construct a multi-level image and obtain an image after pyramid decomposition.

6. A method for evaluating the effect of hair care and growth according to claim 5, characterized in that: The S2 specifically includes: Based on the image after pyramid decomposition, the adaptive texture feature vector is calculated; the adaptive texture feature vectors at different levels are multi-level fused to obtain a comprehensive feature vector; based on the mean and standard deviation of the comprehensive feature vector distribution, a dynamically calculated threshold is obtained, and the features are optimized and extracted through the adaptive threshold method to generate a binary feature map.

7. A method for evaluating the effect of hair care and growth according to claim 1, characterized in that: The S3 specifically includes: In the process of implementing the dynamic phase transformation tracking algorithm, a phase transformation matrix is ​​constructed based on the binary feature map and the conjugate of the binary feature map.

8. A method for evaluating the effect of hair care and growth according to claim 7, characterized in that: The S3 specifically includes: The phase transformation matrix is ​​dynamically updated, and the growth rate is estimated through the phase change.

9. A method for evaluating the effect of hair care and growth according to claim 8, characterized in that: The S3 specifically includes: The growth rate is combined with the phase information to calculate the hair growth amount. The specific formula is: Among them, G estimate represents the amount of hair growth; R(x, y) represents the growth rate of hair at position (x, y); P t (x, y) represents the phase transformation matrix at time t; φ is the phase offset in the growth direction; λ is the attenuation factor.

10. A system for evaluating the effect of hair care and growth, applied to the method for evaluating the effect of hair care and growth as claimed in claim 1, characterized in that: Includes the following parts: Image acquisition module, image preprocessing module, feature extraction module, growth assessment module, report generation module; The image acquisition module takes pictures of the hair at multiple angles to obtain hair images; the image acquisition module transmits the hair images to the image preprocessing module; The image preprocessing module calculates the gradients of the hair image in the horizontal and vertical directions; calculates the comprehensive gradient information based on the gradients of the hair image in the horizontal and vertical directions; weights the comprehensive gradient information to generate an enhanced image; the image preprocessing module transmits the enhanced image to the feature extraction module; The feature extraction module decomposes the enhanced image through the pyramid decomposition technology, constructs a multi-level image, extracts multi-scale information, and obtains an image after pyramid decomposition; based on the image after pyramid decomposition, the adaptive texture feature vector is calculated; the adaptive texture feature vectors of different levels are multi-level fused to obtain a comprehensive feature vector; based on the comprehensive feature vector, the feature is optimized and extracted through the adaptive threshold method to generate a binary feature map; the feature extraction module transmits the binary feature map to the growth assessment module; The growth assessment module constructs a phase transformation matrix based on the binary feature map; dynamically updates the phase transformation matrix and estimates the growth rate through phase changes; calculates the hair growth amount based on the growth rate; and the growth assessment module transmits the hair growth amount result to the report generation module; The report generation module generates a comprehensive evaluation report, including the results of growth rate, density change and texture analysis, providing a scientific basis for the evaluation of hair care and growth effects.

Images