Automatic traditional Chinese medicine decoction piece drying monitoring system and method based on image recognition

Abstract

The invention discloses a traditional Chinese medicine decoction piece drying automatic monitoring system and method based on image recognition, relates to the field of traditional Chinese medicine decoction piece drying monitoring, and solves the problem that a current traditional Chinese medicine decoction piece drying mode cannot be suitable for drying work of traditional Chinese medicine decoction pieces of different specifications. Comprising a data preprocessing module, a monitoring analysis module, a feature extraction module, an intelligent analysis module and an abnormal response module, the data preprocessing module is used for preprocessing a dried image of the traditional Chinese medicine decoction piece, and a foreground image corresponding to the traditional Chinese medicine decoction piece is obtained through preprocessing; the monitoring analysis module is used for monitoring and analyzing the drying condition of the traditional Chinese medicine decoction pieces in the drying room, the abnormal response module is used for responding to the drying work of the traditional Chinese medicine decoction pieces in the drying room according to the drying stop signal or the drying abnormal signal, and the intelligent analysis module is used for analyzing the real-time drying condition of the traditional Chinese medicine decoction pieces. Intelligent monitoring of the traditional Chinese medicine decoction piece drying process is achieved based on the specification data.

Description

Technical Field

[0001] The present invention belongs to the technical field of monitoring the drying of Chinese herbal medicine slices, and in particular to an automatic monitoring system and method for the drying of Chinese herbal medicine slices based on image recognition. Background Art

[0002] Chinese herbal medicine slices are Chinese herbal medicines that have been processed and prepared according to the theory of traditional Chinese medicine and the processing methods of traditional Chinese medicine and can be directly used in clinical Chinese medicine. During the production process of Chinese herbal medicine slices, the Chinese herbal medicine slices need to be dried. The degree of dryness of Chinese herbal medicine slices is very important for the efficacy and storage of Chinese herbal medicine slices. Since the specifications of the Chinese herbal medicine slices obtained during slicing are different, when drying the Chinese herbal medicine slices, the drying environment and drying degree required for the Chinese herbal medicine slices of different specifications are different. However, the drying environment of the current Chinese herbal medicine slice drying equipment is uniformly regulated, and the uniformly regulated drying method cannot be applied to the drying work of Chinese herbal medicine slices of different specifications, thereby affecting the efficacy and quality of the Chinese herbal medicine slices. To this end, the present invention proposes an automatic monitoring system and method for drying Chinese herbal medicine slices based on image recognition. Summary of the Invention

[0003] The purpose of the present invention is to provide an automatic monitoring system and method for drying Chinese herbal medicine slices based on image recognition in order to overcome the shortcomings of the existing technology.

[0004] The technical problems to be solved by the present invention are: How to achieve intelligent monitoring of the drying process of Chinese herbal medicine slices based on specification data.

[0005] The purpose of the present invention can be achieved through the following technical solutions: The automated monitoring system for drying Chinese herbal medicine slices based on image recognition includes a data acquisition module, a data preprocessing module, a monitoring and analysis module, a feature extraction module, an intelligent analysis module, an abnormal response module, and a database; the data acquisition module is used to collect initial drying data of Chinese herbal medicine slices and real-time drying data of Chinese herbal medicine slices during drying, and sends the real-time drying data to the data preprocessing module and the database, and sends the initial drying data to the database and the monitoring and analysis module; the database is used to store the initial drying data and real-time drying data of Chinese herbal medicine slices; The data preprocessing module is used to preprocess the drying image of the Chinese herbal medicine slices, obtain the foreground image corresponding to the Chinese herbal medicine slices through preprocessing, and send the foreground image of the Chinese herbal medicine slices to the data acquisition module; During the drying process, the data acquisition module is further used to collect the real-time drying surface chromaticity value of the Chinese herbal medicine slices in the drying room according to the foreground image and send it to the monitoring and analysis module. The monitoring and analysis module is used to monitor and analyze the drying conditions of the Chinese herbal medicine slices in the drying room. If the analysis generates a drying stop signal or a drying abnormality signal, it is sent to the abnormal response module. The abnormal response module is used to respond to the drying work of the Chinese herbal medicine slices in the drying room according to the drying stop signal or the drying abnormality signal. After the Chinese herbal medicine slices are dried, the feature extraction module is also used to obtain real-time feature data of the Chinese herbal medicine slices after drying and send it to the intelligent analysis module; the intelligent analysis module is used to analyze the real-time drying status of the Chinese herbal medicine slices. If the analysis generates a work abnormality signal, the abnormal proportion of the Chinese herbal medicine slices during drying is calculated and sent to the abnormal response module. The abnormal response module is used to respond to abnormal conditions during the drying of the Chinese herbal medicine slices.

[0006] Furthermore, the initial drying data are the initial area, initial weight and initial surface chromaticity value of the Chinese herbal medicine slices; The real-time drying data includes the total number of Chinese herbal medicine slices during drying and the drying image of each piece of Chinese herbal medicine slice during drying; The real-time characteristic data include the real-time surface color value, real-time area and real-time weight of the Chinese herbal medicine slices after drying.

[0007] Furthermore, the preprocessing includes image denoising, color correction, foreground thinning and foreground segmentation of the dried images corresponding to the Chinese herbal medicine pieces; The preprocessing of the drying image comprises the following steps: Step S1, performing image denoising on the dried image of the Chinese herbal medicine slices to obtain a denoised image corresponding to the Chinese herbal medicine slices; Step S2, then color correction is performed on the denoised image to obtain a correction image corresponding to the Chinese herbal medicine slices; Step S3, performing foreground thinning processing on the correction image corresponding to the Chinese herbal medicine slices to obtain a thinned image of the Chinese herbal medicine slices; Step S4, performing foreground segmentation processing on the refined image of the Chinese herbal medicine slices to obtain a foreground image corresponding to the Chinese herbal medicine slices.

[0008] Furthermore, step S2 includes the following specific steps: Step S201, dividing the denoised image into N color blocks, where N is the maximum number of color blocks; Step S202: Calculate the color tristimulus values ​​Ri, Gi, and Bi of each color block in the denoised image using the following formula, where i is the number of the color block, i=1, 2, 3, ..., N. The calculation formula is as follows: Ri=a 11 *V 1i +a 12*V 2i +……+a 1i *V ji ①; Gi=a 21 *V 1i +a 22 *V 2i +……+a 2i *V ji ②; Bi=a 31 *V 1i +a 32 *V 2i +……+a 3i *V ji ③; Among them, V ji It is composed of polynomials, j is the number of the polynomial, j=1, 2, ..., J. In this example, V=[R, G, B, 1], and the matrix form of formulas ①, ②, and ③ is: X=A T *V, where A T is the transposed matrix of matrix A; Among them, X is the color standard tristimulus value matrix with a dimension of 3*N, and the matrix is ​​as follows: ; A is a conversion coefficient matrix with a dimension of J*3, and the matrix is ​​as follows: ; V is a polynomial regression matrix with dimension J*N, which is as follows: ; Matrix A can be optimized using the least squares method. The calculation formula is as follows: A=(V*V T ) -1 *(V*X T )④; Where V T is the transposed matrix of matrix V; Step S203, calculate the RGB value of each pixel in the color-corrected image by a formula, and form a correction image corresponding to the Chinese herbal medicine slices by the RGB value of each pixel in the color-corrected image. The calculation formula is as follows: X out =A T *V⑤; Specifically, substitute formula ④ into formula ⑤ to calculate the RGB value of each pixel in the color-corrected image, where X out It is the RGB tristimulus value matrix of the color-corrected image, with a dimension of 3*M, where M is the total number of pixels in the denoised image.

[0009] Furthermore, the area containing the Chinese herbal medicine pieces in the refined image is defined as the foreground area, and the other areas excluding the foreground area are defined as the background area. The foreground segmentation is achieved using the region growing technique. The specific steps are as follows: Step S401, selecting a pixel point in the thinned image corresponding to the Chinese herbal medicine slice as a starting point, and setting a growth criterion and a stop criterion; The growth criterion is that the absolute value of the difference between the pixel value of the current pixel point and the pixel value of the previous pixel point is less than or equal to the first pixel threshold; the stopping criterion is that the absolute value of the difference between the pixel value of the current pixel point and the pixel value of the previous pixel point is greater than the first pixel threshold; Step S402, starting from the starting point, gradually merge adjacent pixels into the same region according to the growth criterion. If the adjacent pixels meet the growth criterion, they are added to the current region; if the adjacent pixels meet the stop criterion, the current region is recorded as the segmented region, and the current pixel point is used as the starting point. Foreground segmentation is continued until the last pixel in the thinned image of the Chinese herbal medicine piece is segmented; Step S403: Obtain all segmented areas, traverse all segmented areas, select the segmented area with the largest proportion of Chinese herbal medicine pieces among the segmented areas as the foreground area, and generate a foreground map of the Chinese herbal medicine pieces based on the foreground area.

[0010] Furthermore, the monitoring and analysis process of the monitoring and analysis module is specifically as follows: Step P1, obtaining the real-time drying surface chromaticity value of the Chinese herbal medicine slices in the drying room, and then obtaining the initial surface chromaticity value of the Chinese herbal medicine slices in the drying room; Step P2, subtracting the initial surface chromaticity value from the real-time drying surface chromaticity value to obtain the surface chromaticity change value of the Chinese herbal medicine pieces in the drying room; Step P3, setting a surface chromaticity change critical value of the Chinese herbal medicine slices according to the initial surface chromaticity value, initial weight and initial area of ​​the Chinese herbal medicine slices; Step P4, comparing the surface chromaticity change value with the surface chromaticity change threshold value; Step P5: If the surface chromaticity change value is less than the surface chromaticity change threshold value, no operation is performed; If the surface chromaticity change value is equal to the surface chromaticity change critical value, a drying stop signal is generated; If the surface chromaticity change value is greater than the surface chromaticity change critical value, a drying abnormality signal is generated.

[0011] Furthermore, the process of setting the surface chromaticity change critical value is as follows: Step P31, using the initial surface chromaticity value as the first judgment factor, if the initial surface chromaticity value belongs to the first surface chromaticity value interval, the Chinese herbal medicine pieces are divided into the first set; if the initial surface chromaticity value belongs to the second surface chromaticity value interval, the Chinese herbal medicine pieces are divided into the second set; if the initial surface chromaticity value belongs to the third surface chromaticity value interval, the Chinese herbal medicine pieces are divided into the third set; wherein the right endpoint of the first surface chromaticity value interval is less than or equal to the left endpoint of the second surface chromaticity value interval, and the right endpoint of the second surface chromaticity value interval is less than or equal to the left endpoint of the third surface chromaticity value interval; Step P32: Three sets of surface chromaticity change thresholds are set for each of the first, second, and third sets of Chinese herbal medicine pieces, namely, a first surface chromaticity change threshold, a second surface chromaticity change threshold, and a third surface chromaticity change threshold; wherein the first surface chromaticity change threshold is less than the second surface chromaticity change threshold, and the second surface chromaticity change threshold is less than the third surface chromaticity change threshold. Step P33: If the initial weight of the Chinese herbal medicine pieces in the first set is less than the weight threshold, and the initial area of ​​the Chinese herbal medicine pieces in the first set is less than the area threshold, then the surface chromaticity change critical value of the Chinese herbal medicine pieces is the first surface chromaticity change critical value; Step P34: If the initial weight of the Chinese herbal medicine pieces in the first set is greater than or equal to the weight threshold, and the initial area of ​​the Chinese herbal medicine pieces in the first set is less than the area threshold, or if the initial weight of the Chinese herbal medicine pieces in the first set is less than the weight threshold, and the initial area of ​​the Chinese herbal medicine pieces in the first set is greater than or equal to the area threshold, then the surface chromaticity change critical value of the Chinese herbal medicine pieces is the second surface chromaticity change critical value; Step P35: If the initial weight of the Chinese herbal medicine pieces in the first set is greater than or equal to the weight threshold, and the initial area of ​​the Chinese herbal medicine pieces in the first set is greater than or equal to the area threshold, then the surface chromaticity change critical value of the Chinese herbal medicine pieces is the third surface chromaticity change critical value; Step P36: Similarly, according to steps P31 to P35, the critical values ​​of surface chromaticity change corresponding to the Chinese herbal medicine pieces in the second set and the third set are obtained.

[0012] Furthermore, the analysis process of the intelligent analysis module is as follows: Step Q1, obtaining the initial area, initial surface color value and initial weight of the Chinese herbal medicine slices, and then obtaining the real-time area, real-time surface color value and real-time weight of the Chinese herbal medicine slices; Step Q2, calculating the dehydration ratio A of the Chinese herbal medicine slices by a formula, the calculation formula is as follows: Dehydration ratio = (initial weight - real-time weight) / initial weight * first weight coefficient + (initial area - real-time area) / initial area * second weight coefficient; where the first weight coefficient is greater than the second weight coefficient; Step Q3, calculate the dryness B of the Chinese herbal medicine slices by the formula, the calculation formula is as follows: Dryness = |real-time surface color value-initial surface color value| / initial surface color value*100%; Step Q4, combining the dehydration ratio and dryness of the Chinese herbal medicine slices, calculate the drying excellence value HG of the Chinese herbal medicine slices by the formula, and the calculation formula is as follows: HG=α*A+β*B; where α is the dehydration ratio weight and β is the dryness weight; Step Q5: setting a drying threshold for the Chinese herbal medicine slices based on their initial weight and initial area. The drying threshold is obtained as follows: If the initial weight is less than the weight threshold, and the initial area is less than the area threshold, the drying threshold of the Chinese herbal medicine slices is Q1; If the initial weight is greater than or equal to the weight threshold, and the initial area is less than the area threshold, or if the initial weight is less than the weight threshold, and the initial area is greater than or equal to the area threshold, the drying threshold of the Chinese herbal medicine slice is Q2; If the initial weight is greater than or equal to the weight threshold, and the initial area is greater than or equal to the area threshold, the drying threshold of the Chinese herbal medicine slices is Q3; where 0<Q1<Q2<Q3; Step Q6: If the drying excellence value of the Chinese herbal medicine slices is greater than or equal to the drying threshold value of the Chinese herbal medicine slices, it means that the drying of the Chinese herbal medicine slices is normal, and no operation is performed; If the drying excellence value of a Chinese herbal medicine piece is less than the drying threshold of the Chinese herbal medicine piece, the Chinese herbal medicine piece is recorded as an abnormal Chinese herbal medicine piece and a work abnormality signal is generated. The number of abnormal Chinese herbal medicine pieces is counted and recorded as the number of abnormal Chinese herbal medicine pieces, and the abnormal proportion of the Chinese herbal medicine pieces is calculated by the formula. The calculation formula is as follows: Abnormal proportion = number of abnormal Chinese herbal medicine pieces / total number of Chinese herbal medicine pieces.

[0013] Furthermore, the working process of the abnormal response module is as follows: When a drying stop signal is received, a stop instruction is generated and loaded into the drying room. When the drying room receives the stop instruction, the drying work of the Chinese herbal medicine pieces is stopped. When a drying abnormality signal is received, a stop instruction is generated and loaded into the drying room, and the drying abnormality signal is sent to the management terminal at the same time. When the management terminal receives the drying abnormality signal, it checks the abnormality of the drying of the Chinese herbal medicine slices; When a work abnormality signal and an abnormality ratio are received, the abnormality ratio is compared with a preset abnormality ratio; If the abnormality ratio is greater than or equal to the preset abnormality ratio, a first alarm signal is generated; If the abnormality ratio is less than the preset abnormality ratio, a second alarm signal is generated; wherein the first alarm signal is greater than the second alarm signal; The first alarm signal or the second alarm signal is sent to the management terminal, and the management terminal checks the abnormal situation during the drying of the Chinese herbal medicine slices according to the first alarm signal or the second alarm signal.

[0014] Secondly, the automated monitoring method for drying Chinese herbal medicine slices based on image recognition is as follows: Step S100, collecting initial drying data of the Chinese herbal medicine slices and real-time drying data of the Chinese herbal medicine slices during drying; Step S200, pre-processing the dried image of the Chinese herbal medicine slices to obtain a foreground image corresponding to the Chinese herbal medicine slices; Step S300, collecting the real-time drying surface chromaticity values ​​of the Chinese herbal medicine slices in the drying room according to the foreground image, and monitoring and analyzing the drying conditions of the Chinese herbal medicine slices in the drying room in combination with the real-time drying surface chromaticity values, analyzing to obtain a drying stop signal or a drying abnormality signal, and responding to the drying work of the Chinese herbal medicine slices in the drying room according to the signal; Step S400, after the Chinese herbal medicine pieces are dried, extracting real-time feature data of the dried Chinese herbal medicine pieces; Step S500: Analyze the real-time drying status of the Chinese herbal medicine slices based on the real-time characteristic data. If the analysis generates a work abnormality signal, calculate the abnormal ratio of the drying of the Chinese herbal medicine slices, and respond to the abnormal situation during the drying of the Chinese herbal medicine slices according to the abnormal ratio.

[0015] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention first pre-processes the drying image of the Chinese herbal medicine slices to obtain a foreground image corresponding to the Chinese herbal medicine slices, and then collects the real-time drying surface chromaticity value of the Chinese herbal medicine slices in the drying room according to the foreground image, and monitors and analyzes the drying conditions of the Chinese herbal medicine slices in the drying room in combination with the real-time drying surface chromaticity value, obtains a drying stop signal or a drying abnormality signal through analysis, and responds to the drying work of the Chinese herbal medicine slices in the drying room according to the signal. The present invention performs intelligent monitoring of the Chinese herbal medicine slices in the drying process based on specification data; 2. After the Chinese herbal medicine slices are dried, the present invention extracts the real-time characteristic data of the dried Chinese herbal medicine slices, and then analyzes the real-time drying status of the Chinese herbal medicine slices based on the real-time characteristic data. If the analysis generates a work abnormality signal, the abnormal ratio of the drying of the Chinese herbal medicine slices is calculated, and the abnormal situation during the drying of the Chinese herbal medicine slices is responded to according to the abnormal ratio. The present invention realizes accurate analysis of the drying status of the dried Chinese herbal medicine slices and ensures the drying quality of the Chinese herbal medicine slices. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0017] Figure 1 is a block diagram of the overall system of the present invention; Figure 2 It is a top view of the drying process of the Chinese herbal medicine slices of the present invention; Figure 3 This is a diagram showing the working principle of the foreground image in the present invention; Figure 4 Flow chart of the method of the present invention. DETAILED DESCRIPTION

[0018] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0019] Example 1: Please refer to Figure 1-Figure 3 As shown, the technical solution provided by the present invention is: an automatic monitoring system for drying Chinese herbal medicine slices based on image recognition, including a drying room, a management terminal, a data acquisition module, a data preprocessing module, a monitoring and analysis module, an abnormal response module and a database; In this example, Chinese herbal medicine slices are placed in a drying room for drying operation. The drying room is equipped with various data acquisition devices, including but not limited to cameras, sensor components, etc. The database is respectively connected to the data acquisition module and the intelligent analysis module for data connection. The data acquisition module is used to collect the initial drying data of the Chinese herbal medicine slices and the real-time drying data of the Chinese herbal medicine slices during drying, and the real-time drying data is sent to the data preprocessing module and the database, and the initial drying data is sent to the database and the monitoring and analysis module. The database is used to store the initial drying data and the real-time drying data of the Chinese herbal medicine slices; It should be specifically explained that the initial drying data is the initial area, initial weight and initial surface chromaticity value of the Chinese herbal medicine slices. In fact, the initial weight can be used to obtain the real-time weight corresponding to the Chinese herbal medicine slices through a weighing meter, and the initial surface chromaticity value of the Chinese herbal medicine slices can be obtained through a color analyzer; the real-time drying data is the total number of Chinese herbal medicine slices when they are dried and the drying image of each piece of Chinese herbal medicine when it is dried; among them, when actually collecting data, the drying image of the Chinese herbal medicine slices can be captured by a camera in the drying room, and the data acquisition module can collect real-time drying data every half a minute or one minute.

[0020] Furthermore, the data preprocessing module is used to preprocess the drying image of the Chinese herbal medicine slices, obtain a foreground image corresponding to the Chinese herbal medicine slices by preprocessing, and send the foreground image of the Chinese herbal medicine slices to the data acquisition module; Specifically, in the process of image analysis and recognition, the quality of the image directly affects the recognition accuracy of the dried Chinese herbal medicine slices recognition algorithm. Therefore, the dried images of the Chinese herbal medicine slices need to be preprocessed before the feature extraction of the Chinese herbal medicine slices; image preprocessing is mainly to eliminate irrelevant information in the image and enhance the detectability of relevant information, thereby improving the accuracy of the feature extraction module in feature extraction, image segmentation, and matching recognition of the dried images of the Chinese herbal medicine slices.

[0021] In this embodiment, the preprocessing includes image denoising, color correction, foreground thinning and foreground segmentation of the dried image corresponding to the Chinese herbal medicine slices; Specifically, the preprocessing of the drying image includes the following steps: Step S1, performing image denoising on the dried image of the Chinese herbal medicine slices to obtain a denoised image corresponding to the Chinese herbal medicine slices; In step S1, the main purpose of image denoising is to improve image quality while preserving the important features of the original image as much as possible. ‌ During the acquisition, transmission or processing of images, they may be interfered with by various noises. The presence of noise will reduce the quality of the image, making the image blurry, losing details, and even affecting the usability of the image. Commonly used image denoising algorithms include mean filtering, median filtering and Gaussian filtering. Mean filtering is suitable for removing mild Gaussian noise, but may cause blurred image details; median filtering is suitable for removing impulsive noise such as salt and pepper noise while protecting image edge information; Gaussian filtering is suitable for removing Gaussian noise and can remove noise while preserving image details. In this example, based on the display of the acquired image, the Gaussian filtering algorithm is used to eliminate the noise of the dried image of Chinese herbal medicine slices to obtain a clearer denoised image;‌ Step S2, then color correction is performed on the denoised image to obtain a correction image corresponding to the Chinese herbal medicine slices; Specifically, the images collected by the camera in the drying room are affected by factors such as lighting. The collected images will affect the drying feature extraction of Chinese herbal medicine slices by the feature extraction module, resulting in errors in the extracted drying features, which in turn affects the analysis of the drying details of Chinese herbal medicine slices by the intelligent analysis module, resulting in unqualified quality of the Chinese herbal medicine slices obtained by drying. Therefore, it is necessary to perform color correction on the denoised image to obtain a clearer denoised image. In this embodiment, step S2 includes the following specific steps: Step S201, dividing the denoised image into N color blocks, where N is the maximum number of color blocks; Step S202: Calculate the color tristimulus values ​​Ri, Gi, and Bi of each color block in the denoised image using the following formula, where i is the number of the color block, i=1, 2, 3, ..., N. The calculation formula is as follows: Ri=a 11 *V 1i+a 12 *V 2i +……+a 1i *V ji ①; Gi=a 21 *V 1i +a 22 *V 2i +……+a 2i *V ji ②; Bi=a 31 *V 1i +a 32 *V 2i +……+a 3i *V ji ③; Among them, V ji It is composed of polynomials, j is the number of the polynomial, j=1, 2, ..., J. In this example, V=[R, G, B, 1], and the matrix form of formulas ①, ②, and ③ is: X=A T *V, where A T is the transposed matrix of matrix A; Among them, X is the color standard tristimulus value matrix with a dimension of 3*N, and the matrix is ​​as follows: ; A is a conversion coefficient matrix with a dimension of J*3, and the matrix is ​​as follows: ; V is a polynomial regression matrix with dimension J*N, which is as follows: ; Matrix A can be optimized using the least squares method. The calculation formula is as follows: A=(V*V T ) -1 *(V*X T )④; Where V T is the transposed matrix of matrix V; Step S203, calculate the RGB value of each pixel in the color-corrected image by a formula, and form a correction image corresponding to the Chinese herbal medicine slices by the RGB value of each pixel in the color-corrected image. The calculation formula is as follows: X out =A T *V⑤; Specifically, substitute formula ④ into formula ⑤ to calculate the RGB value of each pixel in the color-corrected image, where X out is the RGB tristimulus value matrix of the color-corrected image, with a dimension of 3*M, where M is the total number of pixels in the denoised image; Step S3, performing foreground thinning processing on the correction image corresponding to the Chinese herbal medicine slices to obtain a thinned image of the Chinese herbal medicine slices; Specifically, image foreground refinement mainly involves fine segmentation of the target area, eliminating interference factors in the target area, and improving the accuracy of foreground segmentation. In this example, an iterative algorithm of morphological operations is selected to perform foreground refinement processing on the correction image of Chinese herbal medicine slices; Step S4, performing foreground segmentation processing on the refined image of the Chinese herbal medicine slices to obtain a foreground image corresponding to the Chinese herbal medicine slices; In this example, the area containing Chinese herbal medicine pieces in the refinement image is defined as the foreground area, and the other areas excluding the foreground area are defined as the background area. The foreground segmentation is achieved using the region growing technique. The specific steps are as follows: Step S401, selecting a pixel point in the thinned image corresponding to the Chinese herbal medicine slice as a starting point, and setting a growth criterion and a stop criterion; It should be specifically noted that the growth criterion is that if the absolute value of the difference between the pixel value of the current pixel point and the pixel value of the previous pixel point is less than or equal to the first pixel threshold; the stopping criterion is that if the absolute value of the difference between the pixel value of the current pixel point and the pixel value of the previous pixel point is greater than the first pixel threshold; Step S402, starting from the starting point, gradually merge adjacent pixels into the same region according to the growth criterion. If the adjacent pixels meet the growth criterion, they are added to the current region; if the adjacent pixels meet the stop criterion, the current region is recorded as the segmented region, and the current pixel point is used as the starting point. Foreground segmentation is continued until the last pixel in the thinned image of the Chinese herbal medicine piece is segmented; It should be specifically noted that the current region is the region when the refined image of the Chinese herbal medicine slices is currently segmented, and the segmented region is the region obtained by completing a foreground segmentation of the refined image of the Chinese herbal medicine slices; Step S403: Obtain all segmented areas, traverse all segmented areas, select the segmented area with the largest proportion of Chinese herbal medicine pieces among the segmented areas as the foreground area, and generate a foreground map of the Chinese herbal medicine pieces based on the foreground area.

[0022] During the drying process, the data acquisition module is also used to collect the real-time drying surface chromaticity value of the Chinese herbal medicine slices in the drying room according to the foreground image, and send the real-time drying surface chromaticity value to the monitoring and analysis module. The monitoring and analysis module is used to monitor and analyze the drying conditions of the Chinese herbal medicine slices in the drying room. The monitoring and analysis process is as follows: Step P1, obtaining the real-time drying surface chromaticity value of the Chinese herbal medicine slices in the drying room, and then obtaining the initial surface chromaticity value of the Chinese herbal medicine slices in the drying room; Step P2, subtracting the initial surface chromaticity value from the real-time drying surface chromaticity value to obtain the surface chromaticity change value of the Chinese herbal medicine pieces in the drying room; Step P3, setting a surface chromaticity change critical value of the Chinese herbal medicine slices according to the initial surface chromaticity value, initial weight and initial area of ​​the Chinese herbal medicine slices; Specifically, the process of setting the critical value of surface chromaticity change is as follows: Step P31, using the initial surface chromaticity value as the first judgment factor, if the initial surface chromaticity value belongs to the first surface chromaticity value interval, the Chinese herbal medicine pieces are divided into the first set; if the initial surface chromaticity value belongs to the second surface chromaticity value interval, the Chinese herbal medicine pieces are divided into the second set; if the initial surface chromaticity value belongs to the third surface chromaticity value interval, the Chinese herbal medicine pieces are divided into the third set; wherein the right endpoint of the first surface chromaticity value interval is less than or equal to the left endpoint of the second surface chromaticity value interval, and the right endpoint of the second surface chromaticity value interval is less than or equal to the left endpoint of the third surface chromaticity value interval; Step P32: Three sets of surface chromaticity change thresholds are set for each of the first, second, and third sets of Chinese herbal medicine pieces, namely, a first surface chromaticity change threshold, a second surface chromaticity change threshold, and a third surface chromaticity change threshold; wherein the first surface chromaticity change threshold is less than the second surface chromaticity change threshold, and the second surface chromaticity change threshold is less than the third surface chromaticity change threshold. Step P33: If the initial weight of the Chinese herbal medicine pieces in the first set is less than the weight threshold, and the initial area of ​​the Chinese herbal medicine pieces in the first set is less than the area threshold, then the surface chromaticity change critical value of the Chinese herbal medicine pieces is the first surface chromaticity change critical value; Step P34: If the initial weight of the Chinese herbal medicine pieces in the first set is greater than or equal to the weight threshold, and the initial area of ​​the Chinese herbal medicine pieces in the first set is less than the area threshold, or if the initial weight of the Chinese herbal medicine pieces in the first set is less than the weight threshold, and the initial area of ​​the Chinese herbal medicine pieces in the first set is greater than or equal to the area threshold, then the surface chromaticity change critical value of the Chinese herbal medicine pieces is the second surface chromaticity change critical value; Step P35: If the initial weight of the Chinese herbal medicine pieces in the first set is greater than or equal to the weight threshold, and the initial area of ​​the Chinese herbal medicine pieces in the first set is greater than or equal to the area threshold, then the surface chromaticity change critical value of the Chinese herbal medicine pieces is the third surface chromaticity change critical value; Step P36: Similarly, according to steps P31 to P35, the critical values ​​of surface chromaticity change corresponding to the Chinese herbal medicine pieces in the second set and the third set are obtained; Step P4, comparing the surface chromaticity change value with the surface chromaticity change threshold value; Step P5: If the surface chromaticity change value is less than the surface chromaticity change threshold value, no operation is performed; If the surface chromaticity change value is equal to the surface chromaticity change critical value, a drying stop signal is generated; If the surface chromaticity change value is greater than the surface chromaticity change critical value, a drying abnormality signal is generated; The monitoring and analysis module sends the drying stop signal or the drying abnormality signal to the abnormality response module, and the abnormality response module is used to respond to the drying work of the Chinese herbal medicine pieces in the drying room according to the drying stop signal or the drying abnormality signal. The working process is as follows: When a drying stop signal is received, a stop instruction is generated and loaded into the drying room; When a drying abnormality signal is received, a stop instruction is generated and loaded into the drying room, and the drying abnormality signal is sent to the management terminal at the same time; When the drying room receives a stop command, it stops drying the Chinese herbal medicine slices. When the management terminal receives a drying abnormality signal, it checks the abnormal situation during the drying of the Chinese herbal medicine slices.

[0023] Example 2: As a further embodiment of the present invention, Figure 1 and Figure 2 As shown, the system also includes a feature extraction module and an intelligent analysis module. After the Chinese herbal medicine slices are dried, the feature extraction module is also used to obtain real-time feature data of the Chinese herbal medicine slices after drying, and send the real-time feature data to the intelligent analysis module; wherein, the real-time feature data is the real-time surface chromaticity value, real-time area and real-time weight of the Chinese herbal medicine slices after drying. During the drying process, dehydration will cause the overall volume of the Chinese herbal medicine slices to continue to decrease, and the real-time surface chromaticity value will also change with time. The real-time surface chromaticity value can express the degree of dryness of the Chinese herbal medicine slices, and the area ratio of the initial area to the real-time area and the weight ratio of the initial weight to the real-time weight can express the dehydration of the Chinese herbal medicine slices.

[0024] In this embodiment, the intelligent analysis module is used to analyze the real-time drying status of Chinese herbal medicine slices. During the drying process of Chinese herbal medicine slices, the collected data is analyzed in real time, an abnormal signal is generated for an abnormal situation and sent to the abnormal response module, and drying adjustments are made to improve the drying quality of Chinese herbal medicine slices. The steps for analyzing the real-time drying status of Chinese herbal medicine slices are as follows: Step Q1, obtaining the initial area, initial surface color value and initial weight of the Chinese herbal medicine slices, and then obtaining the real-time area, real-time surface color value and real-time weight of the Chinese herbal medicine slices; Step Q2, calculating the dehydration ratio A of the Chinese herbal medicine slices by a formula, the calculation formula is as follows: Dehydration ratio = (initial weight - real-time weight) / initial weight * first weight coefficient + (initial area - real-time area) / initial area * second weight coefficient; The first weight coefficient is greater than the second weight coefficient, and the dehydration of the Chinese herbal medicine slices, that is, the dryness of the Chinese herbal medicine slices, can be expressed by combining the area ratio of the initial area to the real-time area and the weight ratio of the initial weight to the real-time weight; Step Q3, calculate the dryness B of the Chinese herbal medicine slices by the formula, the calculation formula is as follows: Dryness = |real-time surface color value-initial surface color value| / initial surface color value*100%; Step Q4, combining the dehydration ratio and dryness of the Chinese herbal medicine slices, calculate the drying excellence value HG of the Chinese herbal medicine slices by the formula, and the calculation formula is as follows: HG=α*A+β*B; Among them, α is the dehydration ratio weight, and β is the dryness weight. This example combines the dehydration ratio and dryness of Chinese herbal medicine slices to calculate the drying excellence value to accurately describe the drying status of Chinese herbal medicine slices. Step Q5: setting a drying threshold for the Chinese herbal medicine slices based on their initial weight and initial area. The drying threshold is obtained as follows: If the initial weight is less than the weight threshold, and the initial area is less than the area threshold, the drying threshold of the Chinese herbal medicine slices is Q1; If the initial weight is greater than or equal to the weight threshold, and the initial area is less than the area threshold, or if the initial weight is less than the weight threshold, and the initial area is greater than or equal to the area threshold, the drying threshold of the Chinese herbal medicine slice is Q2; If the initial weight is greater than or equal to the weight threshold, and the initial area is greater than or equal to the area threshold, the drying threshold of the Chinese herbal medicine slices is Q3; where 0<Q1<Q2<Q3; Step Q6: If the drying excellence value of the Chinese herbal medicine slices is greater than or equal to the drying threshold value of the Chinese herbal medicine slices, it means that the drying of the Chinese herbal medicine slices is normal, and no operation is performed; If the drying excellence value of a Chinese herbal medicine piece is less than the drying threshold of the Chinese herbal medicine piece, the Chinese herbal medicine piece is recorded as an abnormal Chinese herbal medicine piece and a work abnormality signal is generated. The number of abnormal Chinese herbal medicine pieces is counted and recorded as the number of abnormal Chinese herbal medicine pieces, and the abnormal proportion of the Chinese herbal medicine pieces is calculated by the formula. The calculation formula is as follows: Abnormal proportion = number of abnormal Chinese herbal medicine pieces / total number of Chinese herbal medicine pieces; Furthermore, the intelligent analysis module sends the abnormal working signal and abnormal ratio to the abnormal response module, and the abnormal response module is used to respond to abnormal conditions during the drying of Chinese herbal medicine slices. The working process is as follows: Acquire a work abnormality signal and an abnormality ratio, and generate a first alarm signal if the abnormality ratio is greater than or equal to a preset abnormality ratio; If the abnormality ratio is less than the preset abnormality ratio, a second alarm signal is generated; wherein the first alarm signal is greater than the second alarm signal; The first alarm signal or the second alarm signal is sent to the management terminal, and the management terminal checks the abnormal situation during the drying of the Chinese herbal medicine slices according to the first alarm signal or the second alarm signal.

[0025] In this application, if a corresponding calculation formula appears, the above calculation formula is dimensionless and its numerical calculation is performed. The weight coefficient, proportional coefficient and other coefficients in the formula are set to a result value obtained by quantifying each parameter. Regarding the size of the weight coefficient and the proportional coefficient, as long as it does not affect the proportional relationship between the parameter and the result value, it is acceptable.

[0026] Example 3: Another concept based on the same invention, such as Figure 4 As shown, this embodiment proposes an automated monitoring method for drying Chinese herbal medicine slices based on image recognition, comprising the following steps: Step S100, collecting initial drying data of the Chinese herbal medicine slices and real-time drying data of the Chinese herbal medicine slices during drying; Step S200, pre-processing the dried image of the Chinese herbal medicine slices to obtain a foreground image corresponding to the Chinese herbal medicine slices; Step S300, collecting the real-time drying surface chromaticity values ​​of the Chinese herbal medicine slices in the drying room according to the foreground image, and monitoring and analyzing the drying conditions of the Chinese herbal medicine slices in the drying room in combination with the real-time drying surface chromaticity values, analyzing to obtain a drying stop signal or a drying abnormality signal, and responding to the drying work of the Chinese herbal medicine slices in the drying room according to the signal; Step S400, after the Chinese herbal medicine pieces are dried, extracting real-time feature data of the dried Chinese herbal medicine pieces; Step S500: Analyze the real-time drying status of the Chinese herbal medicine slices based on the real-time characteristic data. If the analysis generates a work abnormality signal, calculate the abnormal ratio of the drying of the Chinese herbal medicine slices, and respond to the abnormal situation during the drying of the Chinese herbal medicine slices according to the abnormal ratio.

[0027] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An automated monitoring system for drying Chinese herbal medicine slices based on image recognition, characterized in that: It includes a data acquisition module, a data preprocessing module, a monitoring and analysis module, a feature extraction module, an intelligent analysis module, an abnormal response module and a database; the data acquisition module is used to collect the initial drying data of the Chinese herbal medicine slices and the real-time drying data of the Chinese herbal medicine slices during drying, and sends the real-time drying data to the data preprocessing module and the database and sends the initial drying data to the database and the monitoring and analysis module, and the database is used to store the initial drying data and real-time drying data of the Chinese herbal medicine slices; The data preprocessing module is used to preprocess the drying image of the Chinese herbal medicine slices, obtain the foreground image corresponding to the Chinese herbal medicine slices through preprocessing, and send the foreground image of the Chinese herbal medicine slices to the data acquisition module; During the drying process, the data acquisition module is further used to collect the real-time drying surface chromaticity value of the Chinese herbal medicine slices in the drying room according to the foreground image and send it to the monitoring and analysis module. The monitoring and analysis module is used to monitor and analyze the drying conditions of the Chinese herbal medicine slices in the drying room. If the analysis generates a drying stop signal or a drying abnormality signal, it is sent to the abnormal response module. The abnormal response module is used to respond to the drying work of the Chinese herbal medicine slices in the drying room according to the drying stop signal or the drying abnormality signal. After the Chinese herbal medicine slices are dried, the feature extraction module is also used to obtain real-time feature data of the Chinese herbal medicine slices after drying and send it to the intelligent analysis module; the intelligent analysis module is used to analyze the real-time drying status of the Chinese herbal medicine slices. If the analysis generates a work abnormality signal, the abnormal proportion of the Chinese herbal medicine slices during drying is calculated and sent to the abnormal response module. The abnormal response module is used to respond to abnormal conditions during the drying of the Chinese herbal medicine slices.

2. The automatic monitoring system for drying Chinese herbal medicine slices based on image recognition according to claim 1, characterized in that: The initial drying data are the initial area, initial weight and initial surface color value of the Chinese herbal medicine slices; The real-time drying data includes the total number of Chinese herbal medicine slices during drying and the drying image of each piece of Chinese herbal medicine slice during drying; The real-time characteristic data include the real-time surface color value, real-time area and real-time weight of the Chinese herbal medicine slices after drying.

3. The automatic monitoring system for drying Chinese herbal medicine slices based on image recognition according to claim 2, characterized in that: Preprocessing includes image denoising, color correction, foreground thinning and foreground segmentation of dried images of Chinese herbal medicine pieces; The preprocessing of the drying image comprises the following steps: Step S1, performing image denoising on the dried image of the Chinese herbal medicine slices to obtain a denoised image corresponding to the Chinese herbal medicine slices; Step S2, then color correction is performed on the denoised image to obtain a correction image corresponding to the Chinese herbal medicine slices; Step S3, performing foreground thinning processing on the correction image corresponding to the Chinese herbal medicine slices to obtain a thinned image of the Chinese herbal medicine slices; Step S4, performing foreground segmentation processing on the refined image of the Chinese herbal medicine slices to obtain a foreground image corresponding to the Chinese herbal medicine slices.

4. The automatic monitoring system for drying Chinese herbal medicine slices based on image recognition according to claim 3, characterized in that: The step S2 includes the following specific steps: Step S201, dividing the denoised image into N color blocks, where N is the maximum number of color blocks; Step S202: Calculate the color tristimulus values ​​Ri, Gi, and Bi of each color block in the denoised image using the following formula, where i is the number of the color block, i=1, 2, 3, ..., N. The calculation formula is as follows: Ri=a 11 *V 1i +a 12 *V 2i +……+a 1i *V ji ①; You=a 21 *V 1i +a 22 *V 2i +……+a 2i *V ji ②; Would=a 31 *In 1i +a 32 *In 2i +……+a 3i *In ji ③; Among them, V ji It is composed of polynomials, j is the number of the polynomial, j=1, 2, ..., J. In this example, V=[R, G, B, 1], and the matrix form of formulas ①, ②, and ③ is: X=A T *V, where A T is the transposed matrix of matrix A; Among them, X is the color standard tristimulus value matrix with a dimension of 3*N, and the matrix is ​​as follows: ； A is a conversion coefficient matrix with a dimension of J*3, and the matrix is ​​as follows: ； V is a polynomial regression matrix with dimension J*N, which is as follows: ； Matrix A can be optimized using the least squares method. The calculation formula is as follows: A=(V*V) T ) -1 *(V*X) T )④; Where V T is the transposed matrix of matrix V; Step S203, calculate the RGB value of each pixel in the color-corrected image by a formula, and form a correction image corresponding to the Chinese herbal medicine slices by the RGB value of each pixel in the color-corrected image. The calculation formula is as follows: X out =A T *V⑤; Specifically, substitute formula ④ into formula ⑤ to calculate the RGB value of each pixel in the color-corrected image, where X out It is the RGB tristimulus value matrix of the color-corrected image, with a dimension of 3*M, where M is the total number of pixels in the denoised image.

5. The automatic monitoring system for drying Chinese herbal medicine slices based on image recognition according to claim 3, characterized in that: The area containing Chinese herbal medicine pieces in the refined image is defined as the foreground area, and the other areas excluding the foreground area are defined as the background area. The foreground segmentation is achieved using the region growing technique. The specific steps are as follows: Step S401, selecting a pixel point in the thinned image corresponding to the Chinese herbal medicine slice as a starting point, and setting a growth criterion and a stop criterion; The growth criterion is that the absolute value of the difference between the pixel value of the current pixel point and the pixel value of the previous pixel point is less than or equal to the first pixel threshold; the stopping criterion is that the absolute value of the difference between the pixel value of the current pixel point and the pixel value of the previous pixel point is greater than the first pixel threshold; Step S402, starting from the starting point, gradually merge adjacent pixels into the same region according to the growth criterion. If the adjacent pixels meet the growth criterion, they are added to the current region; if the adjacent pixels meet the stop criterion, the current region is recorded as the segmented region, and the current pixel point is used as the starting point. Foreground segmentation is continued until the last pixel in the thinned image of the Chinese herbal medicine piece is segmented; Step S403: Obtain all segmented areas, traverse all segmented areas, select the segmented area with the largest proportion of Chinese herbal medicine pieces among the segmented areas as the foreground area, and generate a foreground map of the Chinese herbal medicine pieces based on the foreground area.

6. The automatic monitoring system for drying Chinese herbal medicine slices based on image recognition according to claim 3, characterized in that: The monitoring and analysis process of the monitoring and analysis module is as follows: Step P1, obtaining the real-time drying surface chromaticity value of the Chinese herbal medicine slices in the drying room, and then obtaining the initial surface chromaticity value of the Chinese herbal medicine slices in the drying room; Step P2, subtracting the initial surface chromaticity value from the real-time drying surface chromaticity value to obtain the surface chromaticity change value of the Chinese herbal medicine pieces in the drying room; Step P3, setting a surface chromaticity change critical value of the Chinese herbal medicine slices according to the initial surface chromaticity value, initial weight and initial area of ​​the Chinese herbal medicine slices; Step P4, comparing the surface chromaticity change value with the surface chromaticity change threshold value; Step P5: If the surface chromaticity change value is less than the surface chromaticity change threshold value, no operation is performed; If the surface chromaticity change value is equal to the surface chromaticity change critical value, a drying stop signal is generated; If the surface chromaticity change value is greater than the surface chromaticity change critical value, a drying abnormality signal is generated.

7. The automatic monitoring system for drying Chinese herbal medicine slices based on image recognition according to claim 6, characterized in that: The process of setting the critical value of surface chromaticity change is as follows: Step P31, using the initial surface chromaticity value as the first judgment factor, if the initial surface chromaticity value belongs to the first surface chromaticity value interval, the Chinese herbal medicine pieces are divided into the first set; if the initial surface chromaticity value belongs to the second surface chromaticity value interval, the Chinese herbal medicine pieces are divided into the second set; if the initial surface chromaticity value belongs to the third surface chromaticity value interval, the Chinese herbal medicine pieces are divided into the third set; wherein the right endpoint of the first surface chromaticity value interval is less than or equal to the left endpoint of the second surface chromaticity value interval, and the right endpoint of the second surface chromaticity value interval is less than or equal to the left endpoint of the third surface chromaticity value interval; Step P32: Three sets of surface chromaticity change thresholds are set for each of the first, second, and third sets of Chinese herbal medicine pieces, namely, a first surface chromaticity change threshold, a second surface chromaticity change threshold, and a third surface chromaticity change threshold; wherein the first surface chromaticity change threshold is less than the second surface chromaticity change threshold, and the second surface chromaticity change threshold is less than the third surface chromaticity change threshold. Step P33: If the initial weight of the Chinese herbal medicine pieces in the first set is less than the weight threshold, and the initial area of ​​the Chinese herbal medicine pieces in the first set is less than the area threshold, then the surface chromaticity change critical value of the Chinese herbal medicine pieces is the first surface chromaticity change critical value; Step P34: If the initial weight of the Chinese herbal medicine pieces in the first set is greater than or equal to the weight threshold, and the initial area of ​​the Chinese herbal medicine pieces in the first set is less than the area threshold, or if the initial weight of the Chinese herbal medicine pieces in the first set is less than the weight threshold, and the initial area of ​​the Chinese herbal medicine pieces in the first set is greater than or equal to the area threshold, then the surface chromaticity change critical value of the Chinese herbal medicine pieces is the second surface chromaticity change critical value; Step P35: If the initial weight of the Chinese herbal medicine pieces in the first set is greater than or equal to the weight threshold, and the initial area of ​​the Chinese herbal medicine pieces in the first set is greater than or equal to the area threshold, then the surface chromaticity change critical value of the Chinese herbal medicine pieces is the third surface chromaticity change critical value; Step P36: Similarly, according to steps P31 to P35, the critical values ​​of surface chromaticity change corresponding to the Chinese herbal medicine pieces in the second set and the third set are obtained.

8. The automatic monitoring system for drying Chinese herbal medicine slices based on image recognition according to claim 1, characterized in that: The analysis process of the intelligent analysis module is as follows: Step Q1, obtaining the initial area, initial surface color value and initial weight of the Chinese herbal medicine slices, and then obtaining the real-time area, real-time surface color value and real-time weight of the Chinese herbal medicine slices; Step Q2, calculating the dehydration ratio A of the Chinese herbal medicine slices by a formula, the calculation formula is as follows: Dehydration ratio = (initial weight - real-time weight) / initial weight * first weight coefficient + (initial area - real-time area) / initial area * second weight coefficient; where the first weight coefficient is greater than the second weight coefficient; Step Q3, calculate the dryness B of the Chinese herbal medicine slices by the formula, the calculation formula is as follows: Dryness = |real-time surface color value-initial surface color value| / initial surface color value*100%; Step Q4, combining the dehydration ratio and dryness of the Chinese herbal medicine slices, calculate the drying excellence value HG of the Chinese herbal medicine slices by the formula, and the calculation formula is as follows: HG=α*A+β*B; where α is the dehydration ratio weight and β is the dryness weight; Step Q5: setting a drying threshold for the Chinese herbal medicine slices based on their initial weight and initial area. The drying threshold is obtained as follows: If the initial weight is less than the weight threshold, and the initial area is less than the area threshold, the drying threshold of the Chinese herbal medicine slices is Q1; If the initial weight is greater than or equal to the weight threshold, and the initial area is less than the area threshold, or if the initial weight is less than the weight threshold, and the initial area is greater than or equal to the area threshold, the drying threshold of the Chinese herbal medicine slice is Q2; If the initial weight is greater than or equal to the weight threshold, and the initial area is greater than or equal to the area threshold, the drying threshold of the Chinese herbal medicine slices is Q3; where 0<Q1<Q2<Q3; Step Q6: If the drying excellence value of the Chinese herbal medicine slices is greater than or equal to the drying threshold value of the Chinese herbal medicine slices, it means that the drying of the Chinese herbal medicine slices is normal, and no operation is performed; If the drying excellence value of a Chinese herbal medicine piece is less than the drying threshold of the Chinese herbal medicine piece, the Chinese herbal medicine piece is recorded as an abnormal Chinese herbal medicine piece and a work abnormality signal is generated. The number of abnormal Chinese herbal medicine pieces is counted and recorded as the number of abnormal Chinese herbal medicine pieces, and the abnormal proportion of the Chinese herbal medicine pieces is calculated by the formula. The calculation formula is as follows: Abnormal proportion = number of abnormal Chinese herbal medicine pieces / total number of Chinese herbal medicine pieces.

9. The automatic monitoring system for drying Chinese herbal medicine slices based on image recognition according to claim 1, characterized in that: The working process of the abnormal response module is as follows: When a drying stop signal is received, a stop instruction is generated and loaded into the drying room. When the drying room receives the stop instruction, the drying work of the Chinese herbal medicine pieces is stopped. When a drying abnormality signal is received, a stop instruction is generated and loaded into the drying room, and the drying abnormality signal is sent to the management terminal at the same time. When the management terminal receives the drying abnormality signal, it checks the abnormality of the drying of the Chinese herbal medicine slices; When a work abnormality signal and an abnormality ratio are received, the abnormality ratio is compared with a preset abnormality ratio; If the abnormality ratio is greater than or equal to the preset abnormality ratio, a first alarm signal is generated; If the abnormality ratio is less than the preset abnormality ratio, a second alarm signal is generated; wherein the first alarm signal is greater than the second alarm signal; The first alarm signal or the second alarm signal is sent to the management terminal, and the management terminal checks the abnormal situation during the drying of the Chinese herbal medicine slices according to the first alarm signal or the second alarm signal.

10. An automated monitoring method for drying Chinese herbal medicine slices based on image recognition, characterized in that: In combination with the automatic monitoring system for drying Chinese herbal medicine slices based on image recognition according to any one of claims 1 to 9, the automatic monitoring method for drying Chinese herbal medicine slices is as follows: Step S100, collecting initial drying data of the Chinese herbal medicine slices and real-time drying data of the Chinese herbal medicine slices during drying; Step S200, pre-processing the dried image of the Chinese herbal medicine slices to obtain a foreground image corresponding to the Chinese herbal medicine slices; Step S300, collecting the real-time drying surface chromaticity values ​​of the Chinese herbal medicine slices in the drying room according to the foreground image, and monitoring and analyzing the drying conditions of the Chinese herbal medicine slices in the drying room in combination with the real-time drying surface chromaticity values, analyzing to obtain a drying stop signal or a drying abnormality signal, and responding to the drying work of the Chinese herbal medicine slices in the drying room according to the signal; Step S400, after the Chinese herbal medicine pieces are dried, extracting real-time feature data of the dried Chinese herbal medicine pieces; Step S500: Analyze the real-time drying status of the Chinese herbal medicine slices based on the real-time characteristic data. If the analysis generates a work abnormality signal, calculate the abnormal ratio of the drying of the Chinese herbal medicine slices, and respond to the abnormal situation during the drying of the Chinese herbal medicine slices according to the abnormal ratio.

Images