Skin Detection Method, Device, Equipment and Product Based on Long-Wave Infrared Images

Abstract

The present application discloses a skin detection method, device, equipment and product based on long-wave infrared images, relating to the technical field of skin detection. The method includes: obtaining a long-wave infrared image of a skin area to be detected; converting the long-wave infrared image to the HIS space and extracting the I-channel image; determining a characteristic image of the skin area to be detected based on the long-wave infrared image and the I-channel image, thereby determining the temperature diffusion distance of adjacent isotherms; using the Hausdorff distance to measure the difference in the temperature diffusion distance of adjacent isotherms to determine the skin lesion range; calculating the gray value centroid points of the isotherm contour point interval in the skin lesion range area to construct a skin temperature centroid diffusion model; calculating the skin lesion diffusion distance based on the skin temperature centroid diffusion model to complete the detection of the skin lesion area. The present application can quickly judge the diseased tissue and the development trend of the disease of the skin, and effectively improve the accuracy of skin detection.

Description

Technical Field

[0001] The present application relates to the technical field of skin detection, and in particular, to a skin detection method, device, equipment, and product based on long-wave infrared images. Background Art

[0002] Long-wave infrared imaging technology uses the long-wave infrared radiation in the wavelength range of 8 to 14 micrometers emitted by an object to detect, image, and analyze the object. In the field of skin detection, since the changes in the long-wave infrared radiation of the skin are directly related to the physiological, positional, and pathological characteristics of the skin, long-wave infrared imaging technology can be used to obtain information such as the surface temperature distribution, tissue structure differences, and blood perfusion changes of the skin, which cannot be detected by conventional intensity imaging technologies, making it gradually become an emerging technical means and method in the field of skin medical detection. Factors such as the distribution of different positions of the skin tissue, physiological changes, and sclerosing lesions will all produce changes in long-wave infrared radiation related to temperature, resulting in changes or deformations in the long-wave infrared images of that position. Therefore, there is a strong correlation and sensitivity between the long-wave infrared images of the skin and skin damage or deformations. Therefore, by performing long-wave infrared imaging on the differences in the long-wave infrared radiation of the skin and then reflecting the subtle changes in the skin temperature, the visualization display and detection of the skin tissue distribution, physiological state differences, and pathological development trends can be effectively achieved. In addition, long-wave infrared imaging technology has the advantages of non-contact, high sensitivity, and real-time imaging, making it a safe, reliable, simple, effective, and cost-effective tool in applications such as early screening of skin lesions, dynamic monitoring, inflammation and infection detection, and blood circulation assessment, and is of great significance for the early auxiliary diagnosis, health assessment, and precise treatment of skin lesion conditions.

[0003] However, in practical applications, such as the detection of initial lesions of systemic sclerosis of the skin, since the temperature difference between the skin lesion tissue and the adjacent healthy tissue is small, the temperature characteristics of the long-wave infrared image of the skin lesion area are not obvious, resulting in the situation that the long-wave infrared image cannot accurately judge the true lesion area and the lesion development trend of the skin, affecting the accuracy of skin lesion detection. Therefore, the method of using single long-wave infrared intensity imaging cannot effectively achieve the early diagnosis of skin lesions.

[0004] In the existing related technologies, there is a detection method for detecting the skin based on the blood perfusion coefficient, "Pennes bioheat equation with heterogeneous blood perfusion: A newer perspective." According to the skin heat conduction equation, this method proposes that the anisotropic blood perfusion coefficient of the skin reflects the skin characteristics, and determines whether the skin at a certain place is diseased by measuring the perfusion rate coefficient of blood in the unit skin area. And a Doppler ultrasound device is used to evaluate the blood perfusion heterogeneity of the skin tissue and measure the position of the change in the bioheat exchange temperature of the biological tissue, so as to realize the detection of irregular tumors and lesions in the skin tissue. However, when there is a blood circulation disorder in the skin tissue or no blood flow due to inflammation, the "material properties" of the skin will change, resulting in errors in the Doppler ultrasound signal, affecting the determination of the skin blood perfusion coefficient, and causing this method to be unable to accurately evaluate the development trend of lesions in the low blood perfusion or bloodless perfusion skin area, resulting in the inability of this method to effectively detect the skin lesions in this skin area, and the improvement of skin lesion detection is not comprehensive enough. At the same time, the detection equipment of this method is relatively expensive, its mechanical structure is relatively complex, the operating cost requirements and detection costs are relatively high, and it has certain limitations in actual skin detection applications.

[0005] In summary, how to use a relatively simple and effective skin detection method and device to detect skin lesions while ensuring the accuracy of detection is still an urgent problem to be solved. Summary of the Invention

[0006] The purpose of this application is to provide a skin detection method, device, equipment and product based on long-wave infrared images, which can quickly judge the diseased tissues and the development trend of lesions of the skin, and effectively improve the accuracy of skin detection.

[0007] To achieve the above purpose, this application provides the following solutions:

[0008] In the first aspect, this application provides a skin detection method based on long-wave infrared images, including:

[0009] Obtain the long-wave infrared image of the skin area to be detected;

[0010] Convert the long-wave infrared image from the RGB space to the HIS space and extract the I-channel image;

[0011] Determine the characteristic image of the skin area to be detected based on the long-wave infrared image and the I-channel image;

[0012] Determine the temperature diffusion distance of adjacent isotherms based on the characteristic image of the skin area to be detected;

[0013] The Hausdorff distance is used to measure the difference in the temperature diffusion distance between adjacent isotherms, and the skin lesion range is determined;

[0014] Calculate the centroid point of the gray value of the isotherm contour point interval in the skin lesion range area, and construct a skin temperature centroid diffusion model in combination with the Bayesian probability density function;

[0015] Based on the skin temperature centroid diffusion model, calculate the skin lesion diffusion distance to complete the detection of the skin lesion area.

[0016] Optionally, the conversion of the long-wave infrared image from the RGB space to the HIS space and the extraction of the I-channel image specifically include:

[0017] Convert the long-wave infrared image of the skin area to be detected into the gray value space and perform preprocessing to obtain the preprocessed gray image; the preprocessing includes filtering, denoising, contrast enhancement, and calibration processing;

[0018] Perform normalization processing on the preprocessed gray image to obtain the normalized image;

[0019] Extract the gray value data of the normalized image, and sequentially convert the normalized image to the RGB space and the HIS space according to the gray value data, and extract the I-channel data of the I-channel image in the HIS space.

[0020] Optionally, the determination of the skin area to be detected feature image based on the long-wave infrared image and the I-channel image specifically includes:

[0021] Perform image fusion on the long-wave infrared image and the I-channel image to obtain a fused image;

[0022] Calculate and statistically analyze the statistical histogram data of the fused image;

[0023] Based on the statistical histogram data of the fused image, through the formula peak_index e = max{e∣H(e)>H(e - 1) and H(e)>H(e + 1), 1≤e<Q} to determine the maximum value position peak_index in the statistical histogram data e ; through the formula start_index g = max{g∣H(g)<H(g - 1) and H(g)<H(g + 1), 1≤g<peak_index e} to determine the first minimum value position start_index in the interval to the left of the maximum value in the statistical histogram data g ; through the formula descent_index o= min{o | H(o) < H(o - 1) and H(o) < H(o + 1), peak_index e < o < Q} to determine the position descent_index of the first minimum value in the interval on the right side of the maximum value in the statistical histogram data o ; where, e is the index of the position of the maximum value in the statistical histogram data; g is the position index of the first minimum value in the interval on the left side of the maximum value in the statistical histogram data; o is the position index of the first minimum value in the interval on the right side of the maximum value in the statistical histogram data; H(·) is the corresponding statistical histogram data at each place in the statistical histogram of the fused image; Q is the maximum gray value in the statistical histogram data of the fused image;

[0024] According to start_index g and descent_index o to determine the gray value interval of the fused image, assign the values outside the gray value interval range to 0, and perform binarization processing to obtain the binarized image;

[0025] Multiply the binarized image with the gray data of the I-channel image point by point to obtain the skin area to be detected feature image.

[0026] Optionally, the determining the adjacent isotherm temperature diffusion distance based on the skin area to be detected feature image specifically includes:

[0027] Based on the skin area to be detected feature image, use the formula to determine the adjacent isotherm temperature diffusion distance d inter (A, B); where, sup represents the supremum; inf represents the infimum; a ∈ A = {contour_levels k,1 , contour_levels k,2 ,..., contour_levels k,n}; b ∈ B = {contour_levels k+1,1 , contour_levels k+1 , 2,..., contour_levels k+1,m}; contour_levels k,n is the nth contour point on the kth isotherm, and contour_levels k+1,m is the mth contour point on the (k + 1)th isotherm.

[0028] Optionally, the using the Hausdorff distance to measure the difference in the adjacent isotherm temperature diffusion distance to determine the skin lesion range specifically includes:

[0029] The Hausdorff distance is used to measure the temperature diffusion distance of adjacent isotherms between healthy tissues and diseased tissues, analyze the difference in the temperature diffusion distance of adjacent isotherms between healthy tissues and diseased tissues, and set a distance judgment threshold T dis ; When the temperature diffusion distance d inter (A,B) of adjacent isotherms is greater than or equal to the distance judgment threshold T dis , it is a healthy tissue. When the temperature diffusion distance d inter (A,B) of adjacent isotherms is less than the distance judgment threshold T dis , it is a skin diseased tissue, thereby determining the skin lesion range.

[0030] Optionally, calculate the centroid point of the gray value of the isotherm contour point interval in the skin lesion range area, and construct a skin temperature centroid diffusion model in combination with the Bayesian probability density function, specifically including:

[0031] Through the formula and , calculate the centroid point (x centroid(k,i) ,y centroid(k,i) ) of the gray value within the range of different isotherm contour point intervals in the skin lesion range area; where M is the contour point interval range; (x t ,y t ) is the position coordinate of the k-th isotherm contour centered on the t-th pixel point within the contour point interval range M; I segment(k,i) is the gray value index of the i-th pixel point within the k-th isotherm contour interval where the skin diseased tissue is located in the skin lesion range area of the gray data of the skin area to be detected.

[0032] Based on the centroid point of the gray value (x centroid(k,i) ,y centroid(k,i) ), use the Bayesian probability density function to determine the maximum possible diffusion direction of the temperature centroid point as the temperature diffusion direction vector and use the temperature diffusion direction vector expression as the skin temperature centroid diffusion model; where (x contour_levels(k,i) ,y contour_levels(k,i) ) is the position coordinate of the contour point on the isotherm where the skin diseased tissue is located in the skin lesion range area.

[0033] Optionally, calculate the skin lesion diffusion distance based on the skin temperature centroid diffusion model to complete the detection of the skin lesion area, specifically including:

[0034] Construct a straight line equation for the skin lesion diffusion direction based on the skin temperature centroid diffusion model where d x represents the component of the temperature diffusion direction vector in the x direction; d y represents the temperature diffusion direction vector Component in the y direction; (x, y) are the position coordinates of a point on the straight-line equation of the skin lesion diffusion direction.

[0035] Based on the straight-line equation of the skin lesion diffusion direction and the distance metric formula Calculate the skin lesion diffusion distance D i,j ; where (x cross(k+1,j) , y cross(k+1,j) ) are the intersection position coordinates of the straight-line equation of the skin lesion diffusion direction and the adjacent isotherm of the skin lesion tissue within the skin lesion range area.

[0036] In a second aspect, the present application provides a skin detection device based on a long-wave infrared image, including: a constant-temperature stage, a hardware controller, a long-wave infrared camera, a first stepping motor, a second stepping motor, and a computer;

[0037] The computer is electrically connected to the constant-temperature stage, the hardware controller, and the long-wave infrared camera through control lines respectively; the computer is used to control the temperature of the constant-temperature stage; the hardware controller is electrically connected to the first stepping motor and the second stepping motor through control lines respectively; the first stepping motor and the second stepping motor are orthogonally distributed around the constant-temperature stage and are connected to the constant-temperature stage through threaded rods; the computer controls the operation of the first stepping motor and the second stepping motor through the hardware controller, thereby controlling the movement of the constant-temperature stage to ensure that the skin area to be detected is within the field of view of the long-wave infrared camera; the long-wave infrared camera is supported directly above the constant-temperature stage by a bracket; the long-wave infrared camera is used to perform long-wave infrared imaging on the skin area to be detected of the test sample placed on the constant-temperature stage to obtain a long-wave infrared image; the computer performs skin detection based on the long-wave infrared image.

[0038] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement the skin detection method based on the long-wave infrared image.

[0039] In a fourth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the skin detection method based on the long-wave infrared image.

[0040] According to the specific embodiments provided by the present application, the present application has the following technical effects:

[0041] The present application provides a skin detection method, device, equipment and product based on long-wave infrared images, mainly involving a non-contact lesion image detection method using long-wave infrared images of the skin for isotherm similarity analysis. To solve the problem in the existing related technologies that it is impossible to accurately judge and evaluate the skin lesion area and the lesion development trend, the present application measures the temperature diffusion distance difference of adjacent isotherms in the long-wave infrared skin image by using the Hausdorff distance, calculates the centroid point of the gray value in the interval of the isotherm contour points in the lesion range area, combines the Bayesian probability density function to analyze the maximum possible diffusion direction of the temperature centroid point, and constructs a skin temperature centroid diffusion model. The present application determines the skin lesion range and the lesion development trend by measuring the skin lesion diffusion distance, establishes a skin detection method based on long-wave infrared imaging, detects the deterioration of the skin lesion area, and provides a new detection method and technical means for skin lesion prevention, medical intervention and treatment. Therefore, the skin detection method, device, equipment and product based on long-wave infrared images in the present application can quickly judge the diseased tissue and the lesion development trend of the skin, and effectively improve the accuracy of skin detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0043] Figure 1 It is a schematic diagram of the initial infrared temperature image of systemic sclerosis of the skin provided by the present application.

[0044] Figure 2 It is a flowchart of the skin detection method based on long-wave infrared images provided by the present application.

[0045] Figure 3 It is a schematic diagram of the principle of the skin detection method based on long-wave infrared images provided by the present application.

[0046] Figure 4 It is a schematic diagram of the long-wave infrared image provided by the present application.

[0047] Figure 5 It is a schematic diagram of the I-channel image provided by the present application.

[0048] Figure 6 It is a schematic diagram of the statistical histogram data of the fused image provided by the present application.

[0049] Figure 7 It is a schematic diagram of the characteristic image of the skin area to be detected provided by the present application.

[0050] Figure 8Schematic diagram of the temperature diffusion distance between adjacent isotherms provided for this application.

[0051] Figure 9 Schematic diagram of the skin lesion range provided for this application.

[0052] Figure 10 is Figure 9 Magnified view of the lesion diffusion distance at position 1 in

[0053] Figure 11 Schematic diagram for judging the development trend of skin lesions provided for this application.

[0054] Figure 12 Structural diagram of the skin detection device based on long-wave infrared images provided for this application. Detailed implementation manners

[0055] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without making creative efforts belong to the scope of protection of this application.

[0056] To make the above objects, features, and advantages of this application more obvious and understandable, the following further details this application in conjunction with the drawings and specific implementation manners.

[0057] In practical applications, such as in the detection of early-stage lesions of systemic sclerosis of the skin, the schematic diagram of the infrared temperature image in the early stage of systemic sclerosis of the skin is as Figure 1 shown. Since the temperature of the skin lesion tissue is relatively small compared to the temperature of adjacent healthy tissues, the temperature characteristics of the long-wave infrared image in the skin lesion area are not obvious, and it is impossible to effectively achieve the early diagnosis of skin lesions.

[0058] Based on the above situation, a skin detection method based on long-wave infrared images provided by this application mainly lies in proposing to construct a skin temperature centroid diffusion model to calculate the skin lesion diffusion distance for skin lesion judgment. The skin detection method based on long-wave infrared images of this application further analyzes factors such as skin temperature information and the temperature diffusion distance of adjacent isotherms on the basis of long-wave infrared images, measures the temperature characteristics of skin lesion areas and healthy areas, and thus realizes the effective diagnosis and detection of skin lesions. By calculating and analyzing the temperature diffusion distance of adjacent isotherms in the long-wave infrared image and combining the skin temperature diffusion distribution, a skin temperature centroid diffusion model is constructed to diagnose and detect skin lesions, realize the early diagnosis of systemic sclerosis lesions of the skin and predict the development trend of the lesion area, and improve the accuracy of the detection of lesions such as systemic sclerosis of the skin. This method is specifically realized through three major steps: First, after obtaining the long-wave infrared image of the skin area to be detected, extract the characteristic image of the skin area to be detected; Second, calculate the temperature diffusion distance of adjacent isotherms in the characteristic image of the skin area to be detected and judge whether a lesion has occurred; Third, calculate the skin lesion diffusion distance based on the skin lesion tissue area to determine the lesion development trend, and complete the skin detection based on the long-wave infrared image of the skin. The specific judgment process of the lesion tissue and its development trend realized by the skin detection method based on long-wave infrared images of this application is as follows:

[0059] As Figure 2 and Figure 3 shown, a skin detection method based on long-wave infrared images disclosed in this application includes:

[0060] For the first major step, first extract the gray-scale data of the long-wave infrared image of the skin area to be detected, convert the long-wave infrared image from the RGB space to the HIS space, and extract the I-channel image; then perform a filtering preprocessing operation on the long-wave infrared image and calculate its statistical histogram data; finally, segment the skin area to be detected according to the statistical histogram data of the long-wave infrared image combined with the gray-scale data of the I-channel image to obtain the characteristic image of the skin area to be detected, as shown in the following steps 1 to 3 specifically.

[0061] Step 1: Obtain the long-wave infrared image of the skin area to be detected.

[0062] Specifically, use an infrared camera to photograph the skin area to be detected to obtain the long-wave infrared image of the skin area to be detected, referred to as the skin long-wave infrared image, as Figure 4As shown, the pixel value of each pixel in the long-wave infrared image represents the thermal radiation intensity at that position. After obtaining the long-wave infrared image of the skin area to be detected, the long-wave infrared image of the skin area to be detected is converted to the gray value space and preprocessed, including filtering, denoising, enhancing contrast, and correction processing, etc., to obtain the preprocessed gray image, so as to improve the accuracy of subsequent conversion. In addition, the present application also performs normalization processing on the preprocessed gray image to obtain the normalized image, and the specific formula is:

[0063]

[0064] where, I is the pixel value of the preprocessed image; I max and I min are the maximum and minimum pixel values of the preprocessed image respectively; I' is the normalized pixel value.

[0065] Step 2: Convert the long-wave infrared image from the RGB space to the HIS space and extract the I-channel image.

[0066] Extract the gray value data of the normalized image, and convert the normalized image to the RGB space and the HIS space in sequence according to the gray value data, and extract the I-channel data of the I-channel image in the HIS space. Specifically, convert the normalized long-wave infrared image of the skin from the RGB space (long-wave infrared RGB image) to the HIS space to obtain the hue H-channel component H 分 、brightness I-channel component I 分 and saturation S-channel component S 分 , and the conversion formulas of each channel component are as follows:

[0067] Calculate the I-channel component:

[0068]

[0069] where, R, G, and B are the red, green, and blue components of the long-wave infrared RGB image of the skin respectively.

[0070] Calculate the S-channel component:

[0071]

[0072] Calculate the H-channel component:

[0073]

[0074] When B ≤ G, H 分 = θ, when B > G, H 分 = 360 - θ. The I-channel image in the long-wave infrared image of the skin can be extracted through formula (2), as Figure 5 shown.

[0075] Step 3: Determine the characteristic image of the skin area to be detected based on the long-wave infrared image and the I-channel image.

[0076] Fuse the long-wave infrared image and the I-channel image to obtain a fused image; calculate and statistically analyze the statistical histogram data of the fused image. Specifically, first use the skin long-wave infrared image as the target data to fuse with the I-channel image, and perform filtering on the fused image to obtain a filtered image F. Then calculate the statistical histogram data H of the filtered image F as the statistical histogram data of the fused image. During this process, apply a Gaussian convolution kernel to the statistical histogram to obtain the statistical histogram data H after filtering the fused image.

[0077]

[0078] where H(L) is the value of the statistical histogram of the fused image at the L-th position; H(L - j) is the value of the statistical histogram of the fused image at the (L - j)-th position; G[H(j)] represents the value of the Gaussian kernel at the j-th position; represents the sum of the Gaussian kernel within the range [-t', t'], which is used to normalize the Gaussian kernel, represents the Gaussian kernel radius, and T is the numerical value of the Gaussian kernel window interval.

[0079] Find the position of the maximum value and the position of the minimum value near the maximum gray value point in the histogram according to the statistical histogram data H after filtering the fused image, as Figure 6 shown, so as to segment the pixel positions of the characteristic image of the skin area to be detected and obtain the characteristic image of the skin area to be detected.

[0080] The formula for the index of the maximum value position in the statistical histogram data is:

[0081] peak_index e = max{e | H(e) > H(e - 1) and H(e) > H(e + 1), 1 ≤ e < Q} (6)

[0082] The formula for the index of the first minimum value position in the left interval of the maximum value in the statistical histogram data is:

[0083] start_index g = max{g | H(g) < H(g - 1) and H(g) < H(g + 1), 1 ≤ g < peak_index e}}(7)

[0084] The formula for the index of the first minimum value position in the right interval of the maximum value in the statistical histogram data is:

[0085] descent_index o = min{o | H(o) < H(o - 1) and H(o) < H(o + 1), peak_index e < o < Q}(8)

[0086] where peak_index e is the position of the maximum value in the statistical histogram data of the fused image; start_index g is the position of the first minimum value in the interval to the left of the maximum value in the statistical histogram data of the fused image; descent_index o is the position of the first minimum value in the interval to the right of the maximum value in the statistical histogram data of the fused image; H(·) is the corresponding statistical histogram data at each position in the statistical histogram data of the fused image; e is the index of the position of the maximum value in the statistical histogram data; g is the index of the position of the first minimum value in the interval to the left of the maximum value in the statistical histogram data; o is the index of the position of the first minimum value in the interval to the right of the maximum value in the statistical histogram data; Q is the maximum gray value in the statistical histogram data of the fused image.

[0087] Based on start_index g and descent_index o the gray value range in the histogram is used as the gray value interval of the gray data of the final skin area to be detected feature image, and the gray values outside the interval are assigned 0 to obtain image G filter , then G filter is binarized to obtain image G bin , and image G bin is multiplied point - by - point with the gray data of the I - channel image to obtain the skin area to be detected feature image I segment , as Figure 7 shown.

[0088] I segment = G bin .*I 分 (9)

[0089] For the second major step, first, based on the skin area to be detected feature image I segment the number of isotherms is divided and the contour curves of the isotherms are drawn to obtain different contour points C k,n on different isotherms, where C k,n represents the n - th contour point on the k - th isotherm; subsequently, the distance between C k+1,n and C k,nThe maximum deviation distance between two contour points on adjacent isotherms is used as the value of the temperature diffusion distance between adjacent isotherms. This method requires finding the minimum distance between two sets of adjacent isotherm contour points and taking the maximum value among them. When skin lesions occur, the "material properties" of the skin tissue will change, resulting in a value of the temperature diffusion distance between adjacent isotherms that is inconsistent with normal skin. Therefore, by measuring the temperature diffusion distance between adjacent isotherms and setting a distance judgment threshold T dis The second major step in segmenting diseased tissues is to construct a skin lesion detection model to determine whether lesions have occurred by calculating the image data of the characteristic region, using the Hausdorff distance to judge diseased tissues, calculating the diffusion distance between adjacent isotherms, and judging the diseased region based on the diffusion distance, as shown in the following steps 4 to 5.

[0090] Step 4: Determine the temperature diffusion distance between adjacent isotherms based on the characteristic image of the skin area to be detected.

[0091] First, set the number of contour lines pixel_step of the characteristic image of the skin area to be detected, which is set to 5 here, and calculate the gray interval inter between adjacent isotherms according to this value:

[0092] inter = floor(max(I segment ) - min(I segment > 0)) / pixel_step (10)

[0093] where floor is the floor function.

[0094] Calculate the number of isotherms contour_levels based on the gray interval inter inter :

[0095] contour_levels inter = min(I segment > 0):inter:max(I segment ) (11)

[0096] Finally, calculate the temperature diffusion distance d inter (A, B), as Figure 8 shown:

[0097]

[0098] where sup represents the supremum of the distance between sets a and b; inf represents the infimum of the distance between sets a and b; where set a ∈ A = {contour_levels k,1 , contour_levels k,2 ,..., contour_levelsk,n}, the set b ∈ B = {contour_levels k+1,1 , contour_levels k+1,2 ,..., contour_levels k+1,m}; contour_levels k,n is the nth contour point on the kth isotherm, and contour_levels k+1,m is the mth contour point on the (k + 1)th isotherm, that is, A and B represent the contour point data on adjacent isotherms, a belongs to the contour point data on the isotherm of A, and b belongs to the contour point data on the isotherm of B.

[0099] Step 5: Use the Hausdorff distance to measure the difference in temperature diffusion distances between adjacent isotherms and determine the skin lesion range.

[0100] Specifically, use the Hausdorff distance to measure the temperature diffusion distances of adjacent isotherms between healthy tissue and diseased tissue, analyze the difference in temperature diffusion distances of adjacent isotherms between healthy tissue and diseased tissue, and set a distance judgment threshold T dis : Measure the diffusion distance of adjacent isotherms of the diseased skin through the Hausdorff distance, and measure the diffusion distance of the healthy skin through the same method, where the diseased skin is the skin determined to be diseased through pathological examination, so as to obtain the segmentation threshold between the diseased skin and the healthy skin, that is, the distance judgment threshold T dis . When the temperature diffusion distance d inter (A, B) of adjacent isotherms is greater than or equal to the distance judgment threshold T dis , it is healthy tissue. When the temperature diffusion distance d inter (A, B) of adjacent isotherms is less than the distance judgment threshold T dis , it is skin lesion tissue, thereby determining the skin lesion range, as Figure 9 shown.

[0101] For the third major step, first calculate the gray value centroid points within the range of different isotherm contour point intervals of the skin lesion range area, and calculate the direction vector angle θ' between the isotherm contour point and the gray value centroid point. Then, combine with the Bayesian probability density function formula to calculate the maximum possible diffusion direction vector of the temperature centroid within the contour point interval range Finally, construct the diffusion direction straight line equation of the temperature centroid point according to this direction vector, calculate the intersection point with the adjacent isotherm contour through the diffusion direction straight line equation, and calculate the distance between the new contour point and the intersection point as the lesion diffusion distance, and compare this lesion diffusion distance with the distance judgment threshold T dis for comparison, segment the location of the lesion in this area, and determine the lesion development trend. The specific process is shown in Steps 6 to 7.

[0102] Step 6: Calculate the gray value centroid points of the isotherm contour point intervals in the skin lesion range area, and construct a skin temperature centroid diffusion model in combination with the Bayesian probability density function.

[0103] First, calculate the gray value centroid points (x centroid(k,i) , y centroid(k,i) ) within different isotherm contour point intervals in the skin lesion range area:

[0104]

[0105]

[0106] where M is the contour point interval range; (x t , y t ) is the position coordinate of the k-th isotherm contour centered on the t-th pixel point within the contour point interval range M; I segment(k,i) is the gray value index of the i-th pixel point within the k-th isotherm contour interval where the skin lesion tissue is located in the gray data of the skin area to be detected in the skin lesion range area.

[0107] Secondly, calculate the temperature diffusion direction vector

[0108] According to the gray value centroid points (x centroid(k,i) , y centroid(k,i) ) and the position coordinates (x contour_levels(k,i) , y contour_levels(k,i) ) of the contour points on the isotherm where the skin lesion tissue is located in the skin lesion range area, construct a straight line direction vector:

[0109]

[0110] Then, use the Bayesian probability density function to predict the most likely diffusion direction of each contour point as the temperature diffusion direction, and use the temperature diffusion direction vector expression as the skin temperature centroid diffusion model. Under the given direction condition, the expected position μ i , y i ) of the observed data (x i ) is expressed as:

[0111]

[0112] where the observed data (x i , y i ) is the contour point (x contour_levels(k,i) , y contour_levels(k,i) ); f represents the transformation function, represents the observed data (x , y i ) in the directioni ) Expected position of diffusion.

[0113] Assuming that the observed data follows a Gaussian distribution, at a given direction the likelihood of the observed data is expressed as:

[0114]

[0115] where, σ i represents the standard deviation of the diffusion position of the observed data at the i-th pixel point; represents the diffusion probability of the observed data position at a given direction i ∈ [1, 2, …, N], and N represents the total number of contour points on the k-th isotherm.

[0116] Assume that the prior probability of the direction vector is a Gaussian distribution with zero mean:

[0117]

[0118] where, represents the probability density at the direction vector σ d is the standard deviation of the Gaussian distribution, representing the fluctuation range of the vector in different diffusion directions.

[0119] The marginal probability of the observed data is the weighted sum of the observed data corresponding to all possible direction vectors :

[0120]

[0121] where, P(data) represents the total probability given all possible direction vectors . represents the probability that occurs under the condition of a given direction vector .

[0122] Find the most likely diffusion direction by maximizing the posterior probability as the temperature diffusion direction:

[0123] Substitute the likelihood function and the prior probability into the Bayesian probability density function formula as:

[0124]

[0125] where, represents finding the direction vector that maximizes the conditional probability and then determining (x i , yi ) Substitute the parameters into formula (15) to obtain the skin temperature diffusion direction vector at this position, thus completing the construction of the skin temperature centroid diffusion model.

[0126] Step 7: Calculate the skin lesion diffusion distance based on the skin temperature centroid diffusion model to complete the detection of the skin lesion area.

[0127] According to the temperature diffusion direction vector and the contour point (x contour_levels(k,i) , y contour_levels(k,i) ), construct the skin lesion diffusion direction line equation:

[0128]

[0129] where d x represents the component of the temperature diffusion direction vector in the x direction; d y represents the component of the temperature diffusion direction vector in the y direction; (x, y) are the position coordinates of the points on the skin lesion diffusion direction line equation.

[0130] According to the curve Contour_levels formed by adjacent contours i+1 and the intersection position coordinates (x cross(k+1,j) , y cross(k+1,j) ) of the skin lesion diffusion direction line equation and the adjacent isotherms of the skin lesion tissue within the skin lesion range area, and obtain the skin lesion diffusion distance D i,j :

[0131]

[0132] Calculate the skin lesion diffusion distance D i,j , as Figure 10 shown, using the method in Step 5, compare the skin lesion diffusion distance D i,j with the distance judgment threshold T dis . When the skin lesion diffusion distance D i,j is greater than or equal to the distance judgment threshold T dis , it is healthy tissue; when the skin lesion diffusion distance D i,j is less than the distance judgment threshold T dis , it is diseased tissue. Combine the diseased tissue determined in Step 5, and according to the position change of the diseased tissue from Step 5 to Step 7, determine the disease development trend of the diseased tissue, as Figure 11 shown, to complete the skin detection of the skin long-wave infrared image.

[0133] In summary, the skin detection method based on long-wave infrared images of the present application can quickly judge the diseased tissues and the development trend of the disease of the skin, effectively improving the accuracy of skin detection. In addition, the skin detection method based on long-wave infrared images provided by the present application can be used not only to detect the skin disease trend of mice or other animals, but also to detect the diseased areas and development trend of human skin.

[0134] As Figure 12 shown, the present application also provides a skin detection device based on long-wave infrared images, including: a constant-temperature stage, a hardware controller, a long-wave infrared camera, a first stepping motor, a second stepping motor, and a computer. Among them, the computer is electrically connected to the constant-temperature stage, the hardware controller, and the long-wave infrared camera through control lines respectively, and is used for linkage control of each part. The computer is used to control the temperature of the constant-temperature stage. The hardware controller is electrically connected to the first stepping motor and the second stepping motor through control lines respectively. The first stepping motor and the second stepping motor are orthogonally distributed around the constant-temperature stage and are connected to the constant-temperature stage through threaded rods. The computer controls the operation of the first stepping motor and the second stepping motor through the hardware controller, so as to control the movement of the constant-temperature stage to ensure that the skin area to be detected is within the field of view of the long-wave infrared camera. The long-wave infrared camera is supported directly above the constant-temperature stage by a bracket, and is used for long-wave infrared imaging of the skin area to be detected of the test sample placed on the constant-temperature stage to obtain a long-wave infrared image. The computer performs skin detection according to the long-wave infrared image.

[0135] During the detection by the skin disease detection device based on long-wave infrared images, the skin area to be detected is placed on the constant-temperature stage. The computer controls the first stepping motor and the second stepping motor through the hardware controller to move the constant-temperature stage to ensure that the skin area to be detected is within the field of view of the long-wave infrared camera. According to the relative position of the constant-temperature stage, the focal length of the long-wave infrared camera is adjusted so that it can obtain a clear long-wave infrared image of the skin. Then the computer adjusts and controls the temperature of the constant-temperature stage according to the temperature data of the long-wave infrared image of the skin to be detected and keeps it stable. The purpose is to remove the interference of the background temperature to be measured on the long-wave infrared image of the skin area to be measured. After the temperature of the constant-temperature stage is stable, the long-wave infrared camera takes a long-wave infrared image of the skin area to be measured. Subsequently, the computer uses the skin detection method based on long-wave infrared images to analyze the skin disease of the image, and finally realizes the detection of scleroderma disease.

[0136] This application uses the diffusion distance of adjacent isotherms of the skin in long-wave infrared images to construct a skin temperature centroid diffusion model, calculate the diffusion distance of skin lesions, and detect the development trend of lesions. By using a simple skin detection method and device based on long-wave infrared imaging to perform long-wave infrared imaging and processing on the skin area to be detected, it is possible to effectively and quickly image and detect skin diseases in skin areas including low-temperature skin areas with unclear temperature characteristics, low blood perfusion or non-perfused skin areas, realizing the judgment of the skin lesion range and the detection of the development trend with simple detection equipment, low detection cost, and wide application fields.

[0137] In some embodiments, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the skin detection method based on long-wave infrared images.

[0138] In some embodiments, this application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the skin detection method based on long-wave infrared images.

[0139] In some embodiments, this application also provides a computer device, including a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), a communication interface, and a computer program stored on the memory and executable on the processor. The processor executes the computer program to implement the skin detection method based on long-wave infrared images.

[0140] Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of this computer device is used to provide computing and control capabilities. The memory of this computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of this computer device is used to store transactions to be processed. The input / output interface of this computer device is used to exchange information between the processor and external devices. The communication interface of this computer device is used to communicate with external terminals through a network connection. The computer program, when executed by the processor, implements the skin detection method based on long-wave infrared images.

[0141] It should be noted that the object information (including but not limited to object device information, object personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the object or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0142] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memories can include random access memory (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0143] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0144] In this text, specific examples are used to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A skin detection method based on long-wave infrared images, characterized in that, Including: Obtain the long-wave infrared image of the skin area to be detected; Convert the long-wave infrared image from the RGB space to the HIS space and extract the I-channel image; Determine the characteristic image of the skin area to be detected based on the long-wave infrared image and the I-channel image; Determine the temperature diffusion distance of adjacent isotherms based on the characteristic image of the skin area to be detected; Use the Hausdorff distance to measure the difference in the temperature diffusion distance of adjacent isotherms and determine the skin lesion range; Calculate the gray value centroid point of the isotherm contour point interval in the skin lesion range area, and construct a skin temperature centroid diffusion model in combination with the Bayesian probability density function; Calculate the skin lesion diffusion distance based on the skin temperature centroid diffusion model to complete the detection of the skin lesion area.

2. The skin detection method based on long-wave infrared images according to claim 1, wherein The step of converting the long-wave infrared image from the RGB space to the HIS space and extracting the I-channel image specifically includes: Convert the long-wave infrared image of the skin area to be detected to the gray value space and perform preprocessing to obtain the preprocessed gray image; the preprocessing includes filtering, denoising, contrast enhancement, and correction processing; Perform normalization processing on the preprocessed gray image to obtain the normalized image; Extract the gray value data of the normalized image, and sequentially convert the normalized image to the RGB space and the HIS space according to the gray value data and extract the I-channel data of the I-channel image in the HIS space.

3. The skin detection method based on long-wave infrared images according to claim 2, wherein The step of determining the characteristic image of the skin area to be detected based on the long-wave infrared image and the I-channel image specifically includes: Perform image fusion on the long-wave infrared image and the I-channel image to obtain the fused image; Calculate and statistically analyze the statistical histogram data of the fused image; Based on the statistical histogram data of the fused image, through the formula peak_index e = max{e|H(e) > H(e - 1) and H(e) > H(e + 1), 1 ≤ e < Q}, determine the position of the maximum value peak_index in the statistical histogram data e ; through the formula start_index g = max{g|H(g) < H(g - 1) and H(g) < H(g + 1), 1 ≤ g < peak_index e}, determine the position of the first minimum value start_index in the left interval of the maximum value in the statistical histogram data g ; through the formula descent_index o = min{o|H(o) < H(o - 1) and H(o) < H(o + 1), peak_index e < o < Q}, determine the position of the first minimum value descent_index in the right interval of the maximum value in the statistical histogram data o ; where, e is the index of the position of the maximum value in the statistical histogram data; g is the index of the position of the first minimum value in the left interval of the maximum value in the statistical histogram data; o is the index of the position of the first minimum value in the right interval of the maximum value in the statistical histogram data; H(·) is the corresponding statistical histogram data at each place in the statistical histogram of the fused image; Q is the maximum gray value in the statistical histogram data of the fused image; Determine according to start_index g and descent_index o to determine the gray value range of the fused image, assign the values outside the gray value range to 0, and perform binarization processing to obtain the binarized image; Perform dot product fusion on the binarized image and the gray value data of the I-channel image to obtain the characteristic image of the skin area to be detected.

4. The skin detection method based on long-wave infrared images according to claim 3, wherein The step of determining the temperature diffusion distance of adjacent isotherms based on the characteristic image of the skin area to be detected specifically includes: Based on the characteristic image of the skin area to be detected, the formula is used to determine the temperature diffusion distance d of adjacent isotherms inter (A, B); where, sup represents the supremum; inf represents the infimum; a ∈ A = {contour_levels k,1 , contour_levels k,2 ,..., contour_levels k,n}; b ∈ B = {contour_levels k+1,1 , contour_levels k+1,2 ,..., contour_levels k+1,m}; contour_levels k,n is the nth contour point on the kth isotherm, and contour_levels k+1,m is the mth contour point on the (k + 1)th isotherm.

5. The skin detection method based on long-wave infrared images according to claim 4, wherein, The step of using the Hausdorff distance to measure the difference in the temperature diffusion distance of adjacent isotherms and determine the skin lesion range specifically includes: The Hausdorff distance is used to measure the temperature diffusion distance of adjacent isotherms between healthy tissues and diseased tissues, analyze the differences in the temperature diffusion distances of adjacent isotherms between healthy tissues and diseased tissues, and set a distance judgment threshold T dis ; when the temperature diffusion distance d inter (A,B) of adjacent isotherms is greater than or equal to the distance judgment threshold T dis , it is a healthy tissue. When the temperature diffusion distance d inter (A,B) of adjacent isotherms is less than the distance judgment threshold T dis , it is a skin diseased tissue, thereby determining the scope of skin lesions.

6. The skin detection method based on long-wave infrared images according to claim 5, wherein The step of calculating the gray value centroid point of the isotherm contour point interval in the skin lesion range area and constructing a skin temperature centroid diffusion model in combination with the Bayesian probability density function specifically includes: Through the formula and Calculate the centroid point (x centroid(k,i) , y centroid(k,i) ) of the gray values within the range of different isothermal contour points in the skin lesion area; where M is the range of the contour point interval; (x t , y t ) is the position coordinate of the k-th isothermal contour centered on the t-th pixel point within the contour point interval range M; I segment(k,i) is the gray value index of the i-th pixel point within the k-th isothermal contour interval where the skin lesion tissue is located in the skin lesion area of the gray data of the skin area to be detected; Based on the centroid point (x centroid(k,i) , y centroid(k,i) ) of the gray value, the Bayesian probability density function is used to determine the most likely diffusion direction of the temperature centroid point as the temperature diffusion direction vector and the expression of the temperature diffusion direction vector is used as the skin temperature centroid diffusion model; among them, (x contour_levels(k,i) , y contour_levels(k,i) ) is the position coordinate of the contour point on the isotherm where the skin lesion tissue is located within the skin lesion range area.

7. The skin detection method based on long-wave infrared images according to claim 5, characterized in that, The step of calculating the skin lesion diffusion distance based on the skin temperature centroid diffusion model to complete the detection of the skin lesion area specifically includes: Construct a straight line equation for the skin lesion diffusion direction based on the skin temperature centroid diffusion model Among them, d x represents the component of the temperature diffusion direction vector in the x - direction; d y represents the component of the temperature diffusion direction vector in the y - direction; (x, y) is the position coordinate of a point on the straight - line equation of the skin lesion diffusion direction; Based on the straight line equation for the skin lesion diffusion direction and the distance measurement formula Calculate the skin lesion diffusion distance D i,j ; where, (x cross(k+1,j) , y cross(k+1,j) ) is the intersection position coordinates of the straight line equation of the skin lesion diffusion direction and the adjacent isotherm of the skin lesion tissue within the skin lesion range area.

8. A skin detection device based on long-wave infrared images, characterized in that, Including: A constant temperature stage, a hardware controller, a long-wave infrared camera, a first stepping motor, a second stepping motor, and a computer; The computer is electrically connected to the constant temperature stage, the hardware controller, and the long-wave infrared camera through control lines respectively; the computer is used to control the temperature of the constant temperature stage; the hardware controller is electrically connected to the first stepping motor and the second stepping motor through control lines respectively; the first stepping motor and the second stepping motor are orthogonally distributed around the constant temperature stage and are connected to the constant temperature stage through threaded rods; The computer controls the operation of the first stepping motor and the second stepping motor through the hardware controller, so as to control the movement of the constant temperature sample stage to ensure that the skin area to be detected is within the field of view of the long-wave infrared camera; The long-wave infrared camera is supported directly above the constant temperature sample stage by a bracket; The long-wave infrared camera is configured to perform long-wave infrared imaging on the skin area to be detected of the test sample placed on the constant temperature sample stage to obtain a long-wave infrared image; the computer performs skin detection according to the long-wave infrared image by using the skin detection method based on long-wave infrared image according to any one of claims 1-7.

9. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the skin detection method based on long-wave infrared image according to any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the skin detection method based on long-wave infrared image according to any one of claims 1-7.

Images