Cigarette package ash shrinkage rate calculation method and detection system

Abstract

The invention provides a cigarette packet ash shrinkage rate calculation method and a detection system, and belongs to the technical field of cigarette detection. The method for calculating the ash shrinkage rate of the cigarette packet ash comprises the following steps: acquiring multi-angle images before and in the combustion process of a cigarette, and preprocessing the multi-angle images; the method comprises the following steps: collecting a cigarette image area before cigarette combustion, and automatically marking the boundary of the cigarette area by using an image processing algorithm based on adaptive boundary tracking; collecting ash wrapping image areas after cigarette combustion, and ensuring the correspondence of the image areas before and after combustion through image feature point matching; respectively segmenting the cigarette image region and the ash wrapping image region based on a convolutional neural network, and obtaining segmented feature maps; in the segmented feature map, identifying the boundary of the cigarette area and the boundary of the ash wrapping area, and extracting effective connected domains in the cigarette area and the ash wrapping area; and calculating the ash shrinkage rate of the cigarette packet ash based on the extracted effective connected domain, and outputting a calculation result.

Description

Technical Field

[0001] The present invention relates to the technical field of cigarette detection, and in particular to a method for calculating the ash shrinkage rate of cigarette packages and a detection system. Background Art

[0002] In the process of cigarette production quality control, cigarette combustion performance is one of the important indicators for evaluating cigarette products. The burning process of cigarettes directly affects the consumer experience, and the ash crack rate is one of the key parameters for measuring the burning quality of cigarettes. The ash crack rate is usually determined by calculating the ratio of the crack area in the ash column area after the cigarette is burned to the total ash area. The lower the crack rate, the higher the integrity of the ash column and the stronger the ability of the cigarette to maintain its structure during the combustion process. Therefore, the detection and analysis of the crack rate can not only be used for quality control, but also provide data support for the optimization of cigarette materials and formulas.

[0003] Traditional crack rate detection methods rely on manual detection or simple image analysis techniques, usually based on visual judgment or basic image processing algorithms (such as threshold segmentation and edge detection). These methods have problems such as low detection accuracy, detection results are easily affected by lighting, and crack feature ambiguity. In addition, due to the complex surface morphology of the gray column, manual detection efficiency is low and the objectivity of the results is difficult to guarantee, especially in large-scale production detection. With the development of deep learning and image processing technology, deep learning-based detection methods have begun to show significant advantages in the field of industrial detection. These methods can automatically and accurately detect and segment complex gray column cracks through automatic feature extraction and high-precision image recognition capabilities of deep learning models.

[0004] However, in actual cigarette detection, the crack area of ​​the ash column often has diversity, including irregular shape, uneven area and blurred edges. In addition, the lighting contrast between the crack and non-crack areas is different, and the degree of burning also affects the clarity of the image. These factors pose great challenges to the detection of cigarette crack rate. Existing image segmentation methods based on convolutional neural networks (CNN) and attention mechanisms, such as YOLO, ResNeXT, Swin-Transformer, etc., have been used in similar industrial detection scenarios. However, how to further improve the detection accuracy and robustness to achieve automatic detection and accurate segmentation of cigarette cracks under complex backgrounds remains a research focus in this field.

[0005] In view of this, the inventor, based on many years of experience in production design in this field and related fields, has designed a cigarette package ash shrinkage rate calculation method and a cigarette package ash shrinkage rate detection system through repeated experiments, in order to solve the problems existing in the prior art. Summary of the invention

[0006] The object of the present invention is to provide a method for calculating the ash shrinkage rate of cigarette packages and a detection system, which can effectively improve the detection efficiency and accuracy of the ash shrinkage rate of cigarette packages.

[0007] To achieve the above-mentioned purpose, the present invention provides a method for calculating the ash shrinkage rate of cigarette packages and a detection system, wherein: Figure 1 As shown in the figure, the calculation method of cigarette package ash shrinkage rate includes:

[0008] Acquire multi-angle images of cigarettes before and during combustion, and pre-process the multi-angle images;

[0009] Collect the cigarette image area before the cigarette is burned, and use the image processing algorithm based on adaptive boundary tracking to automatically mark the cigarette area boundary;

[0010] Collect the ash image area of ​​the cigarette after burning, and ensure the correspondence of the image area before and after burning by matching the image feature points;

[0011] Based on the convolutional neural network, the cigarette image area and the ash bag image area are segmented respectively and the segmented feature maps are obtained;

[0012] In the segmented feature map, the boundaries of the cigarette area and the ash bag area are identified, and the effective connected regions in the cigarette area and the ash bag area are extracted;

[0013] The ash shrinkage rate of cigarette package is calculated based on the extracted effective connected domain and the calculation result is output.

[0014] The present invention also provides a cigarette package ash shrinkage rate detection system, characterized in that the system achieves the above-mentioned purpose method, including the following modules:

[0015] An image acquisition module, used to obtain multi-angle images before and after the cigarette is burned;

[0016] Gray area segmentation module, which segments the gray area based on parallel convolutional neural network and adaptive gating mechanism;

[0017] Feature extraction and fusion module, used to perform multi-scale feature fusion on the gray area and remove background noise;

[0018] The area calculation and gray shrinkage rate detection module calculates the gray shrinkage rate based on the gray shrinkage rate formula;

[0019] The data analysis and output module is used to generate the gray shrinkage rate change trend chart and comprehensive test report.

[0020] The present invention also provides a computer-readable storage medium on which a computer program is stored, characterized in that the computer program implements the steps of the above-mentioned calculation method when executed by a processor.

[0021] The present invention also proposes a computer device, comprising a memory and a processor, wherein a computer program that can be run on the processor is stored in the memory, and the device is characterized in that the steps of the above-mentioned calculation method are implemented when the processor executes the computer program.

[0022] Compared with the prior art, the present invention has the following characteristics and advantages:

[0023] The present invention proposes a method for calculating the ash shrinkage rate of cigarette packages and a detection system. The method collects image data during cigarette burning through a multi-angle imaging system, automatically marks the boundaries of the ash column area before burning using an adaptive boundary tracking algorithm, and uses an image registration algorithm to ensure the regional consistency of the images before and after burning. By combining a parallel convolutional neural network (CNN) and an adaptive gating mechanism, the automatic segmentation of the ash column area is achieved, and non-target areas are eliminated and cracks or irregular edges are repaired through multi-scale feature fusion and connected domain analysis technology. Finally, the ash shrinkage rate is obtained by calculating the ratio of the ash package area before and after burning, and a ash shrinkage rate change trend chart is automatically generated to achieve dynamic analysis of the ash shrinkage rate of cigarette packages, thereby improving the automation level of cigarette combustion quality detection, reducing the interference of human factors, and improving the stability and reliability of the detection results, providing an important technical guarantee for cigarette production quality management. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings described herein are only for explanation purposes and are not intended to limit the scope of the present invention in any way. In addition, the shapes and proportional dimensions of the various components in the figures are only schematic, used to help understand the present invention, and are not specifically limited to the shapes and proportional dimensions of the various components of the present invention. Those skilled in the art can select various possible shapes and proportional dimensions to implement the present invention according to the teachings of the present invention.

[0025] Figure 1 Schematic diagram of the detection process of the gray shrinkage rate of the present invention;

[0026] Figure 2 It is a schematic diagram of the CSegNet network structure of the present invention;

[0027] Figure 3 It is a schematic diagram of the ResNeXTR network structure of the present invention;

[0028] Figure 4 Schematic diagram of the residual block of the present invention;

[0029] Figure 5 Schematic diagram of the encoder structure of the Swin-Transformer of the present invention;

[0030] Figure 6a It is a schematic diagram of the ECBAM module structure of the present invention;

[0031] Figure 6b It is a schematic diagram of the ECAM module structure of the present invention;

[0032] Figure 6c It is a schematic diagram of the SAM module structure of the present invention;

[0033] Figure 7 It is a schematic diagram of the JEUNet network structure of the present invention;

[0034] Figure 8 This is a schematic diagram of the structure of the joint excitation upsampling (JEU) module of the present invention;

[0035] Fig. 9 It is a schematic diagram of the method for calculating the ash shrinkage rate of cigarette packages of the present invention. DETAILED DESCRIPTION

[0036] The details of the present invention can be more clearly understood with reference to the accompanying drawings and the description of the specific embodiments of the present invention. However, the specific embodiments of the present invention described herein are only used for the purpose of explaining the present invention and cannot be understood as limiting the present invention in any way. Under the guidance of the present invention, technicians can conceive of any possible variations based on the present invention, which should all be considered to belong to the scope of the present invention.

[0037] The present invention proposes a method for calculating the ash shrinkage rate of cigarette packages and a system for detecting the ash shrinkage rate of cigarette packages, wherein the method for calculating the ash shrinkage rate of cigarette packages comprises:

[0038] Acquire multi-angle images of cigarettes before and during combustion, and pre-process the multi-angle images;

[0039] Collect the cigarette image area before the cigarette is burned, and use the image processing algorithm based on adaptive boundary tracking to automatically mark the cigarette area boundary;

[0040] Collect the ash image area of ​​the cigarette after burning, and ensure the correspondence of the image area before and after burning by matching the image feature points;

[0041] Based on the convolutional neural network, the cigarette image area and the ash bag image area are segmented respectively and the segmented feature maps are obtained;

[0042] In the segmented feature map, the boundaries of the cigarette area and the ash bag area are identified, and the effective connected regions in the cigarette area and the ash bag area are extracted;

[0043] The ash shrinkage rate of cigarette package is calculated based on the extracted effective connected domain and the calculation result is output.

[0044] The present invention proposes a method for calculating the ash shrinkage rate of cigarette packages and a system for detecting the ash shrinkage rate of cigarette packages, which ensure the quality and consistency of image data through multi-angle imaging and image preprocessing, and provide a reliable basis for subsequent image analysis. It not only improves the accuracy and efficiency of calculating the ash shrinkage rate of cigarette packages, but also improves the detection efficiency, and can realize real-time dynamic analysis of cigarette combustion quality, providing important technical guarantee for cigarette production quality management.

[0045] In an optional embodiment of the present invention, a multi-angle imaging system is used to obtain multi-angle images of the cigarette before and during combustion, and the multi-angle images include at least a front view image, a side view image, and a top view image. By adopting the technology of the multi-angle imaging system, more comprehensive and accurate image data can be obtained when calculating the ash shrinkage rate of the cigarette package, and various details of the ash column during the cigarette combustion process, including the length change of the ash column, surface cracks, and color changes, etc.

[0046] In an optional embodiment of the present invention, the cigarette area and the ash bag area are segmented separately based on a convolutional neural network, including using a multi-scale convolution processing model that combines the ResNeXT50 and Swin-Transformer network structures, combined with the Squeeze-and-Excitation module to enhance the feature channels, and realize the separation of the cigarette area and the ash bag area from the background area. The method for calculating the ash shrinkage rate of the cigarette bag using the combination of the ResNeXT50 and Swin-Transformer network structures and the Squeeze-and-Excitation module significantly improves the accuracy and efficiency of segmentation. By combining the traditional convolutional neural network and the self-attention mechanism, it is possible to not only capture local features, but also identify long-distance dependencies in the image, so that the network can understand the image content more comprehensively. The introduction of the Squeeze-and-Excitation module further enhances the network's ability to control the feature channels, allowing the model to focus more on the key information that distinguishes the cigarette area and the ash bag area.

[0047] In an optional embodiment of the present invention, the cigarette area and the ash bag area are segmented separately based on a convolutional neural network, including: in the encoder part, a convolutional neural network module is used to extract multi-scale features of the image, the feature map is divided into multiple stages according to different scales, and the feature channel correlation is enhanced by the Squeeze-and-Excitation module; in the decoder part, the feature map is upsampled by the joint excitation upsampling module, and the segmentation accuracy is improved by combining the space and channel attention mechanism. By using multi-scale feature extraction and the Squeeze-and-Excitation module in the encoder part to enhance the feature channel correlation, and upsampling by the JEU module in the decoder part and combining the space and channel attention mechanism, the accuracy of the cigarette ash bag area segmentation is significantly improved. This method can not only capture the subtle features in the image, but also understand the image content at different scales, so as to more accurately separate the cigarette area and the ash bag area. This precise segmentation capability ensures that background interference can be excluded when calculating the ash shrinkage rate, improves the accuracy of the ash shrinkage rate calculation, and provides more reliable data support for cigarette quality control. In addition, the method also improves the computational efficiency of the segmentation process, making the calculation of the ash shrinkage rate of cigarette packages faster, which helps to achieve real-time or near real-time quality monitoring.

[0048] In an optional embodiment of the present invention, the cigarette area and the ash bag area are segmented separately based on a convolutional neural network, including dynamically enhancing the boundaries of the cigarette area and the ash bag area using an adaptive gating mechanism based on a parallel convolutional neural network, and identifying multi-scale regional features through a multi-scale feature extraction module. The method for calculating the ash shrinkage rate of cigarette ash bags using a parallel convolutional neural network and an adaptive gating mechanism significantly improves the accuracy of boundary recognition and the quality of segmentation. The adaptive gating mechanism enables the network to dynamically adjust according to the actual image features, effectively enhances the boundary features, and reduces the influence of noise and interference. The application of the multi-scale feature extraction module enables the network to consider features of different scales at the same time, which not only improves the ability to recognize small-scale cracks and defects, but also enhances the ability to capture large-scale structural changes. Through a comprehensive segmentation method, it is ensured that a more accurate regional definition can be obtained when calculating the ash shrinkage rate, thereby improving the accuracy of the ash shrinkage rate calculation and providing more reliable data support for cigarette quality control.

[0049] In an optional embodiment of the present invention, in the feature map after segmentation, the boundaries of the cigarette area and the boundaries of the ash pack area are identified, including fine identification of the boundaries of the cigarette area and the boundaries of the ash pack area through processing by an image enhancement module with depth estimation and adaptive weight allocation. By applying the image enhancement module with depth estimation and adaptive weight allocation in the feature map after segmentation, the recognition accuracy of the boundaries of the cigarette area and the ash pack area is improved. It can automatically adapt to different image features and environmental conditions and provide more accurate boundary positioning, thereby providing a solid foundation for subsequent area measurement and ash shrinkage rate calculation. Through this fine identification, the errors caused by inaccurate boundary identification can be effectively reduced, and the reliability and accuracy of the ash shrinkage rate calculation can be improved. In addition, the system's adaptability to different brands and types of cigarettes is also enhanced.

[0050] In an optional embodiment of the present invention, effective connected domains in the cigarette area and the ash bag area are extracted, including using multi-scale feature fusion and connected domain analysis technology to eliminate non-target areas in the background. By adopting multi-scale feature fusion and connected domain analysis technology, the accuracy of extracting effective connected domains in the cigarette ash bag area is improved. The non-target areas in the background are effectively removed, and the interference of irrelevant information is reduced, thereby ensuring the accuracy and reliability of the ash shrinkage rate calculation. By accurately identifying and extracting areas that are directly related to the combustion quality of cigarettes, the present invention not only improves the accuracy of the ash shrinkage rate calculation, but also enhances the system's adaptability to different combustion stages and different types of cigarettes.

[0051] In an optional example of this embodiment, multi-scale feature fusion is used, including, through a multi-scale feature fusion module, fusing the features extracted by the multi-scale convolution kernel into a unified feature map, and combining the Squeeze-and-Excitation module to adaptively adjust the weights of each feature channel to highlight the gray column area features. The method for calculating the gray shrinkage rate of cigarette packages using multi-scale feature fusion and the Squeeze-and-Excitation module effectively improves the quality of feature extraction and the accuracy of segmentation. By integrating feature maps of different scales, the network can capture local details and global contextual information at the same time, which helps to understand the image content more comprehensively. The adaptive weight adjustment of the SE module further enhances the network's ability to recognize gray column area features, making the feature map more prominent in features related to gray columns, thereby improving the accuracy of segmentation.

[0052] In an optional example of this embodiment, extracting effective connected domains in the cigarette area and the ash pack area also includes repairing cracks or irregular edges through a region filling algorithm. By introducing a region filling algorithm in the process of extracting effective connected domains, the accuracy and reliability of the calculation of the ash shrinkage rate of the cigarette ash pack can be improved, and cracks or irregular edges in the image can be effectively repaired, thereby avoiding the negative impact of these defects on the calculation of the ash shrinkage rate. By filling the cracks, the present invention ensures the integrity of the ash column area, making the calculation results closer to the actual combustion quality, and providing more accurate data support for quality control in the cigarette production process.

[0053] In an optional example, based on the adaptive gating mechanism and the connected domain analysis of the convolutional network, the cracks are removed by edge detection and connected domain filling. By combining the adaptive gating mechanism and the connected domain analysis technology, the cracks in the ash area of ​​the cigarette package can be removed efficiently, which not only improves the accuracy of crack detection, but also repairs the image discontinuity caused by the cracks through intelligent filling technology, thereby ensuring the integrity of the ash column area and the accuracy of calculating the ash shrinkage rate.

[0054] Preferably, the removal of cracks includes: extracting crack edges using the Sobel operator or the Canny edge detection algorithm; embedding an adaptive gating module in a deep convolutional network to enhance crack features and suppress non-crack features; extracting connected domains in the crack area and screening feature areas by area and shape; filling the crack area and performing color measurement. By comprehensively using edge detection algorithms, adaptive gating modules, and connected domain analysis techniques, efficient and accurate removal of cracks in the ash area of ​​cigarette packages is achieved. This method not only improves the accuracy of crack detection, but also repairs the image discontinuity caused by cracks through intelligent filling technology, thereby ensuring the integrity of the ash column area and the accuracy of calculating the ash shrinkage rate.

[0055] In an optional embodiment of the present invention, the method for calculating the ash shrinkage rate of cigarette packages further includes: performing integrity detection on the cigarette area and the ash package area based on color channel analysis. By introducing the integrity detection step based on color channel analysis, the method for calculating the ash shrinkage rate of cigarette packages can more comprehensively evaluate the combustion quality of cigarettes. Color differences caused by uneven combustion or ash column structural defects can be identified, thereby providing important information about the combustion characteristics of cigarettes. Through color channel analysis, the present invention not only improves the accuracy of ash shrinkage rate calculation, but also enhances the comprehensive evaluation capability of cigarette product quality.

[0056] In an optional embodiment of the present invention, the formula for calculating the ash shrinkage rate of cigarette packages is:

[0057] SR=(1-S1 / S0)×100

[0058] In the formula, S0 is the area of ​​the cigarette before burning, in square millimeters, and S1 is the area of ​​the cigarette after burning, in square millimeters. By accurately measuring the area of ​​the ash pack before and after cigarette burning and applying a specific calculation formula, this method can reliably reflect the integrity and stability of the ash column during cigarette burning. The use of quantitative evaluation methods not only improves the accuracy of quality control, but also helps manufacturers optimize cigarette design and production processes, thereby improving the overall quality of the product and consumer experience.

[0059] In an optional embodiment of the present invention, outputting the calculation results includes: outputting the ash shrinkage rate calculation results and generating a ash shrinkage rate change trend graph during the combustion process. By outputting the ash shrinkage rate calculation results and generating a change trend graph, a comprehensive and intuitive cigarette combustion quality analysis tool is provided to the user. This output method not only makes complex data information easy to understand and analyze, but also helps cigarette manufacturers and researchers identify and analyze the performance of cigarettes at different combustion stages. With this information, manufacturers can improve product design and optimize combustion characteristics in a targeted manner, thereby improving the overall quality of cigarettes.

[0060] The present invention also provides a cigarette package ash shrinkage rate detection system, wherein the system implements the above method and includes the following modules:

[0061] An image acquisition module, used to obtain multi-angle images before and after the cigarette is burned;

[0062] Gray area segmentation module, which segments the gray area based on parallel convolutional neural network and adaptive gating mechanism;

[0063] Feature extraction and fusion module, used to perform multi-scale feature fusion on the gray area and remove background noise;

[0064] The area calculation and gray shrinkage rate detection module calculates the gray shrinkage rate based on the gray shrinkage rate formula;

[0065] The data analysis and output module is used to generate the gray shrinkage rate change trend chart and comprehensive test report.

[0066] The present invention also provides a computer-readable storage medium on which a computer program is stored, wherein the computer program implements the steps of the above-mentioned calculation method when executed by a processor.

[0067] The present invention further provides a computer device, comprising a memory and a processor, wherein a computer program that can be run on the processor is stored in the memory, wherein the processor implements the steps of the above-mentioned calculation method when executing the computer program.

[0068] Specifically, Figure 1 As shown, a method for calculating the ash shrinkage rate of cigarette packages comprises the following steps:

[0069] 1) Input the sample image of the cigarette combustion process to be tested, and obtain the ash package images at different angles and combustion stages through the multi-angle imaging system to ensure the comprehensiveness and accuracy of the image data;

[0070] 2) Obtain the image area of ​​the ash-encased area before combustion, use an image processing algorithm based on adaptive boundary tracking to automatically mark the boundary of the ash-encased area, and ensure the regional consistency of the images before and after combustion through an image registration algorithm;

[0071] 3) After the cigarette is burned, the ash area image is collected again, and the correspondence of the images before and after burning is ensured by matching the image feature points to improve the accuracy of the ash shrinkage rate calculation;

[0072] 4) Automatic segmentation of gray-enclosed areas is achieved through parallel convolutional neural networks (CNNs) and adaptive gating mechanisms. A multi-scale convolution processing model combining ResNeXT50 and Swin-Transformer network structures is used, combined with the Squeeze-and-Excitation (SE) module for feature channel enhancement to ensure accurate separation of gray column areas from background areas.

[0073] 5) In the segmented feature map, the gray column area boundary is refined, and the image enhancement module with depth estimation and adaptive weight allocation is used to achieve fine recognition of the gray area boundary to ensure the accuracy of area measurement;

[0074] 6) Use multi-scale feature fusion and connected domain analysis technology to remove non-target areas in the background, extract the effective connected domain of the gray area, and repair the cracks or irregular edges through the area filling algorithm;

[0075] 7) After dividing the ash-encapsulated areas before and after combustion, calculate the ash shrinkage rate SR by SR = (1-S1 / S0) × 100;

[0076] Where S0 is the area of ​​the ash-packing zone before combustion, in square millimeters (mm 2 ), S1 is the area of ​​the ash packing area after combustion, in square millimeters (mm 2 );

[0077] 8) Output the ash shrinkage rate detection results and generate the ash shrinkage rate change trend chart during the combustion process for dynamic analysis of the ash shrinkage rate of cigarette packages.

[0078] 1.1 Image processing

[0079] 1.1.1 Image acquisition module

[0080] A high-resolution still imaging camera used to obtain static images of the char lines during cigarette burning.

[0081] A dynamic imaging camera is used to capture real-time images of the changing char lines as a cigarette burns.

[0082] Through dual-camera collaborative imaging, the charcoal line characteristics of cigarette burning can be captured at different time points and viewing angles, ensuring clear images even under complex background conditions.

[0083] 1.1.2 Image Preprocessing

[0084] The collected raw image data is processed by the preprocessing module, including:

[0085] Color calibration: Use a standard color chart to calibrate the image to eliminate color deviations under different lighting conditions.

[0086] Light uniformity adjustment: According to the changes in ambient light, adjust the light uniformity of the image to ensure the clarity and consistency of the cigarette charcoal line image during the burning process.

[0087] Image denoising: Use noise filtering algorithms to remove interference factors such as smoke and ash generated during cigarette burning, thereby enhancing the quality and effectiveness of the image.

[0088] 1.2 Image acquisition and annotation of the ash-enclosing area before combustion

[0089] Before the cigarette is lit, an initial image of the ash area is obtained. The boundary of the ash area is automatically marked by an adaptive boundary tracking algorithm. The algorithm performs boundary detection on the initial image to accurately mark the outline of the ash area before combustion, ensuring effective distinction between the ash area and the background in subsequent analysis. Then, an image registration algorithm is used to align the images before and after combustion to ensure consistency of the image area before and after combustion.

[0090] 1.3 Image collection and feature point matching of the ash area after combustion

[0091] After the cigarette is burned or at a certain stage, the image of the ash area is collected again. The images before and after burning are compared through image feature point matching technology to ensure the regional alignment and correspondence of the images. The purpose of this step is to reduce the image deviation caused by angle changes or ash column shrinkage and improve the accuracy of ash shrinkage calculation.

[0092] 1.4CSegNet Network

[0093] In order to achieve accurate segmentation of the cracks in the packet, this paper proposes a crack segmentation algorithm (Crack Segmentation Network, CSegNet) that combines convolutional neural network CNN and Transformer self-attention mechanism. The CSegNet network uses an Encoder-Decoder encoding and decoding framework similar to DeepLab V3+, and includes the following steps:

[0094] 1) Obtain crack images during cigarette burning and preprocess the images, including noise removal, grayscale calibration, and contrast enhancement;

[0095] 2) The ResNeXt-Transformer (ResNeXTR) module is used in the encoder, which includes the ResNeXt50 convolutional network and the Swin-Transformer network to extract local and global features in the image;

[0096] 3) In the decoder, an efficient convolutional block attention module (ECBAM) is combined, including an efficient channel attention module (ECAM) and a spatial attention module (SAM) to enhance the salient features of the gap area;

[0097] 4) Use average pooling and point-wise convolution operations to reduce the dimension of the encoder output to reduce the cost of self-attention calculation;

[0098] 5) Using the combined loss function of Binary Cross-Entropy with Logits and Dice loss, the Binary Cross-Entropy with Logits loss and Dice loss functions are combined with a weight of 0.5 each to optimize the segmentation accuracy and edge detection effect.

[0099] The main innovations of CSegNet are as follows:

[0100] (1) In the encoder part, a ResNeXt-Transformer (ResNeXTR) feature extraction module is designed as the backbone network. ResNeXTR enhances the feature extraction capability of the crack area in the gray-encapsulated image by combining the flexibility of Transformers in modeling long-term dependencies with the ability of CNN to capture local contextual information through local receptive fields, weight sharing, and spatial subsampling. In addition, in order to reduce the computational cost of Transformers, an average pooling layer is introduced to downsample the dimension of the encoded features.

[0101] (2) In the decoder part, the Efficient Channel Attention Module (ECAM) and the Spatial Attention Module (SAM) are combined to design an Efficient Convolutional Block Attention Module (ECBAM) to further optimize the feature expression and focus on the key information of the cracks under different background colors.

[0102] (3) ReLU activation function, SGD gradient descent and Binary Cross Entropy with Logits hybrid loss function are used to speed up convergence and improve segmentation accuracy.

[0103] 1.4.1 CSegNet Algorithm Overview

[0104] The CSegNet network model adopts the basic codec architecture of DeepLab V3+, such as Figure 2 As shown. Given that Transformer is flexible in modeling long-term dependencies, and CNN can use local receptive fields, shared weights, and spatial subsampling to obtain local contextual information, a ResNeXt-Transfomer (ResNeXTR) feature extraction module is designed in the encoder part as the backbone network to enhance the feature extraction capability of the input image. The CNN part of the ResNeXTR feature extraction module uses the ResNeXt50 network as a convolutional feature extractor, and the Transformer part uses the Swin-Transformer network based on the self-attention mechanism. In order to reduce the computational cost of self-attention calculations, average pooling is introduced to downsample the encoded dimensions. As shown Figure 5 As shown in the figure, after the image passes through the encoder, in order to further enrich the feature information and enhance the feature extraction ability of the model, the shallow features from ResNeXt50 are cascaded with the output of Swin Transformer as shallow outputs, which are then input into the decoder and fused with the deep feature maps output by ResNet50 to become the comprehensive output of the encoder.

[0105] The decoder retains the structure of DeepLab V3+, but an ECBAM attention module is designed before outputting the classification label to strengthen the long-range interaction between low-level feature maps without significantly increasing the parameter size, thereby further optimizing the feature representation. After obtaining the multi-scale semantic feature map, the decoder performs 4x upsampling, and then fuses it with the shallow semantic information output by the ResNeXTR module. After 3×3 convolution and 4x upsampling, the feature obtains the semantic segmentation result through the ECBAM attention module.

[0106] 1.4.2 ResNeXTR Network Structure

[0107] The structure of the ResNeXTR feature extraction module used for feature extraction in the encoder is as follows Figure 3 As shown in the figure, ResNeXTR uses the ResNeXt50 network as a CNN feature extractor, which can learn more extensive and rich local features from the gray crack image; on the other hand, the Swin-Transformer network based on the self-attention mechanism is used as the Transformer component in the module, which enables the network to capture the long-distance correlation between different regions in the crack image. By combining the features output by these two networks, ResNeXTR constructs a feature engineering with rich shallow features and strong local feature correlation, which balances segmentation efficiency and accuracy to a certain extent.

[0108] 1.4.2.1ResNeXt

[0109] The use of ResNeXt network is mainly based on the following factors.

[0110] (1) ResNeXt50 introduces “cardinality” as a new dimension, alongside depth and width, which improves the representation capability of the model without increasing its complexity.

[0111] (2) The modular design of ResNeXt50 makes the model more flexible, easier to expand, and more efficient to train.

[0112] (3) ResNeXt50 performs better on the ImageNet dataset than Xception, the initial encoder network of DeepLab V3+, and demonstrates excellent generalization capabilities in multi-task learning and different datasets. Therefore, using ResNeXt50 as part of the feature extraction network can improve model performance and enhance the stability and robustness of the model. The ResNet network of ResNeXt50 consists of multiple unique residual blocks, such as Figure 4As shown in Figure 1, the residual blocks are distributed in four stages according to the configuration of [3, 4, 6, 3]. Through these residual blocks, the ResNeXt50 network performs in-depth feature analysis on the input image and generates multi-scale feature maps, ensuring accurate and rich semantic representation of the cracks in the input image. In actual training, we first use the ResNeXt50 network pre-trained on the public dataset ImageNet to perform preliminary feature extraction on the input image.

[0113] 1.4.2.2 Transformer with Average Pooling Layer Embedded

[0114] In addition to the above-mentioned ResNeXt module, Swin TransformerV2, which is also pre-trained on ImageNet, is introduced to parse the shallow features of the input image and construct a detailed feature map. Swin-Transformer V2 is an efficient visual Transformer network structure. Unlike traditional Transformer networks, SwinTransformer V2 processes images by using a windowed self-attention mechanism and introduces local information exchange to reduce computational complexity. In our model, the self-attention mechanism of Swin-Transformer helps capture more local and global details, thereby providing a more refined feature representation for the generation of semantic labels for cracks. Since the computational complexity of the original attention is relatively large and the requirements for the equipment are high, in order to reduce the computational complexity of the model, CSegNet has made improvements to the basic attention calculation and downsampled after calculating the K and V vectors. The specific structure is as follows: Figure 4 shown.

[0115] In order to reduce the amount of computation in self-attention calculation, an average pooling layer O is introduced S The encoded dimension is downsampled. In order to further reduce the amount of calculation, point-by-point convolution is used to further reduce the feature dimension. The specific calculation process of self-attention SA is as follows:

[0116] SA(X)=Attention(X·W Q ,P S (X.W K ),P S (X.W V )) (2.1)

[0117] Where W Q , W K , W V It represents the linear layer used for encoding, and Attention is the attention calculation method, which can be expressed as:

[0118] Attention(Q,K,V)=softmax(SIM(Q,K))V (2.2)

[0119] SIM(Q,K) is the similarity calculation of Q and K, using cosine similarity, and its calculation formula is as follows:

[0120]

[0121] Where B ij is the relative position bias between pixel i and pixel j; τ is a learnable scaling parameter; B is obtained by the continuous relative position bias method, which does not directly optimize the parameterized bias, but uses a small meta-network update on the relative coordinates:

[0122]

[0123] In the formula, Represents a small network, such as a 2-layer MLP with ReLU activation by default. The Transformer block consists of a self-attention (SA) and MLP module, and the calculation flow is as follows:

[0124]

[0125]

[0126]

[0127]

[0128] in, Represents the result of layer normalization (LN) of the output of self-attention SA. represents the output of MLP after layer normalization (LN), z l Represents the final output result of the Transformer block.

[0129] 1.4.4 Efficient Convolutional Block Attention Module ECBAM

[0130] In order to enable the network to effectively focus on the key information of the crack in a complex background while suppressing irrelevant information from different channels, CSegNet designs an Efficient Convolutional Block Attention Module (ECBAM) at the output of the decoder. The ECBAM structure is as follows: Figure 6aIn order to reduce the problem of increasing model parameter count caused by adding the hybrid attention mechanism module, ECBAM first inputs the feature map into the ECAM (Efficient Channel Attention Module) module, as shown in Figure 6b As shown in the figure, ECAM uses 1D convolution to effectively realize the cross-channel interaction of local information; then, the feature map is input into the SAM (Spatial Attention Module) module, as shown in Figure 6c As shown in Figure 1, SAM performs maximum pooling and average pooling on the feature map at the same time, concatenates the results and performs an overall weighted operation on the feature map. This design enables ECBAM to focus on the global semantic information of the defect area while introducing the channel correlation of the feature map.

[0131] 1.4.5 Loss Function

[0132] During the training and validation phases of the model, a joint combined loss function consisting of the Binary Cross-Entropy with Logits (BCE With Logits Loss) loss function and the Dice loss function was designed.

[0133] (1) Binary Cross-Entropy with Logits loss function is a loss function commonly used for binary classification problems, which combines the Sigmoid activation function and the binary cross entropy loss. In the crack segmentation task, the BCEWithLogits function provides clear feedback to the model, and its definition is shown in Equation 2.9:

[0134]

[0135] Where N represents the total number of samples; y i represents the true label of the i-th sample, 1 means that the pixel is a crack, and 0 means that the pixel does not belong to a crack; p i is the original output predicted by the model for the i-th pixel. i ) represents the result obtained by processing the original output of the model's prediction for the i-th pixel through the sigmoid function.

[0136] (2) The Dice loss function is different from the Binary Cross-Entropy function. The Dice loss function measures the overlap between the label and the prediction. Assuming that X represents the true label of the true crack segmentation image, and Y represents the pixel category of the model predicted segmentation image, the definition of the Dice loss function is shown in Equation 2.10 and Equation 2.11:

[0137] L Dice=1-Dice Coefficient (2.10)

[0138]

[0139] In the formula, |X∩Y| represents the number of elements in the intersection of X and Y, and |X| and |Y| represent the number of elements in X and Y respectively. The final loss function used by the model is shown in formula 2.12:

[0140] L=0.5L BCEwtihlogits +0.5L Dice (2.12)

[0141] This formula combines the BCE With Logits loss and the Dice loss function with a weight of 0.5 each. The combination of these two loss functions helps to balance the accuracy of crack detection and boundary delineation in the segmentation task.

[0142] 1.5 Research on gap semantic segmentation algorithm based on JEUNet

[0143] The research motivation of CSegNet is to achieve accurate segmentation of the bag crack area. However, since it is embedded with modules such as ResNeXt50, Swin-Transformer V2, and ECBAM, the parallel operation of these modules consumes a lot of computing resources, which is not conducive to the engineering of the algorithm. Therefore, it is necessary to study efficient semantic segmentation algorithms in order to provide a fast and accurate algorithm for the engineering implementation of bag crack detection.

[0144] In order to solve the problem that existing semantic segmentation algorithms need to consume large computing resources while achieving accurate segmentation, this section designs a Joint Excitation Up-sampling Network (JEUNet) for cleft segmentation. JEUNet is a network with an encoder-decoder symmetric structure. In the decoder stage, spatial attention and joint upsampling are integrated to replace the general layer-by-layer upsampling method. At the same time, feature information at multiple scales and the correlation of channel directions are considered, which improves the upsampling speed and enhances the accuracy of semantic segmentation.

[0145] 1.5.1 Overview of JEUNet Algorithm

[0146] Packet crack detection can be described as a pixel-level anomaly prediction task. The proposed joint excitation upsampling network JEUNet has a classic encoder-decoder symmetric structure. Its network framework is as follows: Figure 7As shown. The yellow arrow indicates direct input; the black arrow indicates a 3×3 convolution operation with a stride of 1, which uses the zero-padding strategy to keep the feature maps of the same level at the same size; the gray arrow indicates a cut and connect operation, which cuts the left feature map to the size corresponding to the right and then connects it; the blue arrow indicates a 1×1 operation for final classification, and the last two layers of output are the result and the background; the red arrow indicates downsampling the feature map by 2×2 maximum pooling; the green arrow indicates upsampling the feature map by a factor of 2 using a 2×2 deconvolution operation. k indicates the number of base channels of the convolution feature map (in this article, k = 32).

[0147] The encoder part of JEUNet is consistent with the backbone network of UNet. The original input image is encoded in 4 stages through continuous convolutional layers, and is transmitted through 2× maximum pooling downsampling between every 2 stages. Therefore, there are 5 scales including the original image. The feature map of each scale contains information with different receptive fields. The shallow feature map is mainly the detailed texture information of local pixels, while the deep feature map contains the local semantic information in the image. In the decoding process of JEUNet, the outputs of the 2nd, 3rd and 4th stages are input to the designed JEU (Joint Excitation Up-sampling block) module, which replaces the continuous upsampling of convolutions at three scales in the original UNet. The output of the JEU module is upsampled once and cascaded with the output of the first stage of the encoder, and then two 3×3 convolution operations are performed in the same layer. Finally, it is upsampled to the original image size and connected with the initial convolution result of the original image. After two convolution operations, the prediction result is obtained. In the decoder part, the cascade operation of the upsampled feature map and the shallow features of the encoder part can improve the local prediction accuracy of the pixel.

[0148] 1.5.2JEUNet Module

[0149] The Jointly Excited Upsampling (JEU) module is a computational unit that integrates spatial attention into the joint upsampling network. On the one hand, three feature maps with different receptive fields are resized to the same size and connected as a joint feature map T; on the other hand, a transformation vector W is constructed to excite each channel in the tensor T. During the upsampling process, the JEU module simultaneously considers the correlation of multi-scale feature information and channel direction, improving the accuracy of semantic segmentation while reducing the complexity of upsampling calculations. Figure 8 The structural diagram of the JEU block is shown, the purple arrow indicates the joint upsampling path, and the red arrow indicates the feature map excitation path for multi-level feature map joint upsampling.

[0150] The JEUNet of the present invention uses joint upsampling to replace the initial two layer-by-layer upsampling in the decoder link of UNet. Through embedding vector extraction, the multi-level feature maps output by the 2nd, 3rd and 4th stages are respectively input into the designed JEU module, and the feature maps of stage 4 (w×w) and stage 3 (2w×2w) are upsampled to 4w×4w of the same size as stage 2. The feature maps after joint upsampling are concat-operated to obtain a multi-level feature map T of size 4w×4w×X (X=4k+8k+16k=28k=896). After joint upsampling, the new three feature maps are concatenated and merged into a multi-level feature map T of size 4w×4w×X, where X=4k+8k+16k=28k=896. The multi-level feature map T contains 4w×4w embedding vectors of size 1×X, each of which contains semantic information of three different receptive fields and corresponds one-to-one to each position (x, y) in the original image.

[0151] 1.5.3 Multi-level feature map spatial channel excitation

[0152] After joint upsampling, the JPU block then uses 4 dilated convolutions with different expansion rates to extract features and concatenate them. The purpose is to capture feature information at different scales in the multi-level feature map to ensure the accuracy of the semantic segmentation upsampling decoder. However, each scale of the feature map in the multi-level feature map itself contains semantic information of different receptive fields. The use of multiple dilated convolutions may be repeated with the multi-level embedding vector itself, resulting in no significant improvement in the accuracy of semantic segmentation. In addition, the multi-level feature map T contains X channels, each of which is obtained by convolution kernels with different parameters. The correlation between these channels has not been paid attention to, so the accuracy improvement of the semantic segmentation prediction results is limited.

[0153] In order to adaptively recalibrate the feature response in the channel direction and model the interdependence between different channels. We introduced the SE (Squeeze-and-Excitation) module in the JEU block to integrate spatial attention into the structure of the upsampling network, which is also a significant difference between the JEU and JPU modules. As shown in Formula 2.13, for a 4w×4w×X Tensor T, a global average pooling function is used to compress it into a 1×X feature vector F, and the xth element F in F x The calculation method is as follows:

[0154]

[0155] In the formula, F(x) corresponds to the x-th channel in Tensor T, and I and J are the x-th channel feature map T respectively. xThe length and width of (I = J = 4w), i and j represent the coordinates of each point on the feature map. In order to establish the correlation between the features of different channels, F is connected to two fully connected layers to calculate the contribution weights of different channels during the learning process and to activate the corresponding channels in the feature map during prediction, as shown in formula (2.14).

[0156]

[0157] Where δ() represents the ReLU activation function and σ() represents the Sigmoid activation function.

[0158] During the learning process, the feature vector F is mapped through two fully connected layers to form the final weight vector W, where the weight of each channel in W is W x The importance of the corresponding channel x in the multi-level feature map T is predicted to model the correlation between feature channels. In the two fully connected layer operations, the vector F is scaled (1 / 2) and restored once to reduce the amount of calculation. w1 is the mapping weight vector of the first fully connected layer, and w2 is the mapping weight vector of the second fully connected layer. Represents the feature map T corresponding to the xth channel x With the weight vector W x Weighted multiplication of the excitation feature map, the JEU block assigns a new response weight to each channel c in the multi-level feature map T obtained by joint upsampling through the weight vector W, and finally obtains the multi-level feature map after spatial channel excitation

[0159] 1.6 Removal of the rift area

[0160] 1) Crack edge detection: Apply the Sobel operator or Canny edge detection algorithm to the gray column segmentation image to extract the edge information in the image. By analyzing the connectivity of the edge image, the edge features of the crack area can be preliminarily identified.

[0161] 2) Application of adaptive gating mechanism: Introduce an adaptive gating mechanism into the feature extraction layer of the convolutional neural network. This module adjusts the feature points through a dynamic gating function (such as the Sigmoid function), gives higher weights to the edge features of the crack area, and attenuates the noise interference of the gray column to improve the accuracy of crack detection.

[0162] 3) Connected domain analysis: Connected domain analysis is performed on the image after adaptive gating processing. First, all connected domains that may belong to the cracks are extracted, and these connected domains are filtered according to criteria such as area size, shape outline, etc., and small or irregular connected domains are eliminated to ensure that only the real crack areas are retained.

[0163] 4) Rip filling: After determining the crack area, fill the crack area through morphological closing operation and other regional filling algorithms. If the crack area is large, a multi-scale filling strategy is adopted, that is, filling from the center to the edge layer by layer to ensure that the gray image after filling is intact for subsequent color detection.

[0164] 1.7 Color feature extraction

[0165] 1) Color space conversion: The gray area image after the cracks are removed is converted from the RGB color space to the CIELAB color space. This conversion process can better simulate the human eye's perception of color and adapt to changes in different lighting environments.

[0166] 2) Color channel separation: In CIELAB space, extract L (brightness), a (red and green components) and b (yellow and blue components). On this basis, calculate the average L value of all pixels in the gray area to represent the grayscale information of the gray column. The average L value can accurately reflect the depth of the gray color.

[0167] 1.7 Color Calibration and Grayscale Balance

[0168] 1) D65 light source calibration: The image color is calibrated based on the D65 light source of the CIELAB color space standard to ensure that the detection results are not affected by changes in external light, especially to maintain consistent color measurement under different ambient lighting.

[0169] 2) Grayscale balance: The grayscale histogram equalization method is used to process the ash bag image after the cracks are removed. By dynamically adjusting the image brightness and contrast, the grayscale distribution is made more uniform, thereby ensuring the stability of the ash bag color detection at different combustion stages.

[0170] 1.8 Detection of ash shrinkage rate

[0171] After the ash column area is segmented and the cracks are removed, the ash shrinkage rate is calculated based on the area of ​​the segmented ash-enclosed area before and after combustion. The specific calculation formula (2.15) is used for calculation:

[0172]

[0173] Where S0 is the area of ​​the ash-packing zone before combustion, in square millimeters (mm 2 ), S1 is the area of ​​the ash packing area after combustion, in square millimeters (mm 2 ).

[0174] The detailed explanation of the above-mentioned embodiments is only intended to explain the present invention so as to facilitate a better understanding of the present invention. However, these descriptions cannot be interpreted as limitations on the present invention for any reason. In particular, the various features described in different embodiments may also be arbitrarily combined with each other to form other embodiments. Unless there is a clear description to the contrary, these features should be understood to be applicable to any embodiment and are not limited to the described embodiments.

Claims

1. A method for calculating the ash shrinkage rate of cigarette packages, characterized in that: The method for calculating the ash shrinkage rate of cigarette packages comprises: Acquire multi-angle images of cigarettes before and during combustion, and pre-process the multi-angle images; Collect the cigarette image area before the cigarette is burned, and use the image processing algorithm based on adaptive boundary tracking to automatically mark the cigarette area boundary; Collect the ash image area of ​​the cigarette after burning, and ensure the correspondence of the image area before and after burning by matching the image feature points; Based on the convolutional neural network, the cigarette image area and the ash bag image area are segmented respectively and the segmented feature maps are obtained; In the segmented feature map, the boundaries of the cigarette area and the ash bag area are identified, and the effective connected regions in the cigarette area and the ash bag area are extracted; The ash shrinkage rate of cigarette package is calculated based on the extracted effective connected domain and the calculation result is output.

2. The method for calculating the ash shrinkage rate of cigarette packages according to claim 1, characterized in that: Multi-angle images of the cigarette before and during combustion are acquired through a multi-angle imaging system, and the multi-angle images at least include a front view image, a side view image and a top view image.

3. The method for calculating the ash shrinkage rate of cigarette packages according to claim 1, characterized in that: Based on the convolutional neural network, the cigarette area and the ash area are segmented respectively. include, A multi-scale convolution processing model combining ResNeXT50 and Swin-Transformer network structures is adopted, combined with the Squeeze-and-Excitation module to enhance feature channels and separate the cigarette area and ash area from the background area.

4. The method for calculating the ash shrinkage rate of cigarette packages according to claim 1, characterized in that: Based on the convolutional neural network, the cigarette area and the ash area are segmented respectively. include, In the encoder part, the convolutional neural network module is used to extract multi-scale features of the image, the feature map is divided into multiple stages according to different scales, and the feature channel correlation is enhanced through the Squeeze-and-Excitation module; In the decoder part, the feature map is upsampled through the joint excitation upsampling module, and the spatial and channel attention mechanisms are combined to improve the segmentation accuracy.

5. The method for calculating the ash shrinkage rate of cigarette packages according to claim 1, characterized in that: Based on the convolutional neural network, the cigarette area and the ash area are segmented separately, including: Based on a parallel convolutional neural network, an adaptive gating mechanism is used to dynamically enhance the boundaries of the cigarette area and the ash area, and a multi-scale feature extraction module is used to identify multi-scale regional features.

6. The method for calculating the ash shrinkage rate of cigarette packages according to claim 1, characterized in that: In the segmented feature map, identify the boundaries of the cigarette area and the ash area, including, Through the image enhancement module processing of depth estimation and adaptive weight allocation, the boundaries of the cigarette area and the ash bag area are finely identified.

7. The method for calculating the ash shrinkage rate of cigarette packages according to claim 1, characterized in that: Extract the effective connected areas in the cigarette area and ash bag area, include, Multi-scale feature fusion and connected domain analysis techniques are used to eliminate non-target areas in the background.

8. The method for calculating the ash shrinkage rate of cigarette packages according to claim 7, characterized in that: Using multi-scale feature fusion, include, Through the multi-scale feature fusion module, the features extracted by the multi-scale convolution kernel are fused into a unified feature map, and the weight of each feature channel is adaptively adjusted in combination with the Squeeze-and-Excitation module to highlight the characteristics of the gray column area.

9. The method for calculating the ash shrinkage rate of cigarette packages according to claim 7, characterized in that: Extracting effective connected areas in the cigarette area and the ash bag area also includes repairing cracks or irregular edges through a region filling algorithm.

10. The method for calculating the ash shrinkage rate of cigarette packages according to claim 9, characterized in that: Based on the adaptive gating mechanism and connected domain analysis of the convolutional network, the gaps are removed through edge detection and connected domain filling.

11. The method for calculating the ash shrinkage rate of cigarette package according to claim 10, characterized in that: Removal of the rift includes: Use the Sobel operator or Canny edge detection algorithm to extract the crack edge; An adaptive gating module is embedded in the deep convolutional network to enhance the crack features and suppress the non-crack features; Extract the connected domain of the crack area and filter the characteristic area according to area and shape; Fill the rip area and take color measurements.

12. The method for calculating the ash shrinkage rate of cigarette packages according to claim 1, characterized in that: The method for calculating the ash shrinkage rate of cigarette packages also includes: Integrity detection of cigarette area and ash area is performed based on color channel analysis.

13. The method for calculating the ash shrinkage rate of cigarette package according to claim 1, characterized in that: The formula for calculating the ash shrinkage rate of cigarette packages is: SR=(1-S1 / S0)×100 Where S0 is the area of ​​the cigarette before burning, in square millimeters, and S1 is the area of ​​the cigarette after burning, in square millimeters.

14. The method for calculating the ash shrinkage rate of cigarette package according to claim 1, characterized in that: Output calculation results, including: Output the ash shrinkage rate calculation results and generate the ash shrinkage rate change trend chart during the combustion process.

15. A cigarette pack ash shrinkage rate detection system, characterized in that: The system implements the method described in any one of claims 1 to 14, and includes the following modules: An image acquisition module, used to obtain multi-angle images before and after the cigarette is burned; Gray area segmentation module, which segments the gray area based on parallel convolutional neural network and adaptive gating mechanism; Feature extraction and fusion module, used to perform multi-scale feature fusion on the gray area and remove background noise; The area calculation and gray shrinkage rate detection module calculates the gray shrinkage rate based on the gray shrinkage rate formula; The data analysis and output module is used to generate the gray shrinkage rate change trend chart and comprehensive test report.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the computing method according to any one of claims 1 to 14 are implemented.

17. A computer device comprising a memory and a processor, wherein a computer program capable of running on the processor is stored in the memory, characterized in that: When the processor executes the computer program, the steps of the computing method according to any one of claims 1 to 14 are implemented.

Images