A carbon fiber cloth convex detection method, device, equipment and storage medium

Abstract

The present application relates to the technical field of carbon fiber detection, and particularly relates to a carbon fiber cloth convex detection method, device, equipment and storage medium, comprising the following steps: setting a monitoring area and setting a gray threshold value, a pixel value and a convex area value, acquiring color image data and converting the color image data into gray image data; extracting a region satisfying the set gray threshold value in the gray image data to perform a close operation, and outputting the region as region A; performing a region growing algorithm on the gray image data, merging regions greater than the set pixel value, outputting a result region and performing an open operation, performing a region classification algorithm, and outputting the result as region B; recording the intersection of region A and region B as region C, and obtaining region D by subtracting region C from region B; separating non-connected regions of region D, selecting the largest region after separation, and if the area is greater than the set convex area value, an alarm is given. The present application detects the convex of the carbon fiber cloth in a visual manner to improve the quality of the carbon fiber cloth.

Description

Technical Field

[0001] This invention relates to the field of carbon fiber testing technology, and in particular to a method, apparatus, equipment, and storage medium for detecting carbon fiber fabric bulges. Background Technology

[0002] Carbon fiber, a high-molecular fibrous carbon material with a carbon content of over 90%, boasts the highest high-temperature resistance among all chemical fibers. It is made from acrylic and viscose fibers through high-temperature oxidation and carbonization, making it an excellent material for manufacturing high-tech equipment such as aerospace equipment.

[0003] In the production process of carbon fiber, yarns are woven into a single sheet of carbon fiber fabric using a warp knitting machine. However, during production, carbon filaments or other foreign matter may be woven into the carbon fiber fabric, causing bulges. These bulges affect product quality, making bulge detection a crucial indicator of the carbon fiber fabric's production pass rate. Traditional detection methods require manual observation, which is not only labor-intensive but also prone to errors and omissions due to worker fatigue and condition, making it difficult to meet the demands of online bulge detection for large quantities of carbon fiber fabric on high-speed production lines.

[0004] Therefore, visual inspection of carbon fiber fabric for bulge detection has become a pressing technical problem that needs to be solved. Summary of the Invention

[0005] In view of at least one of the above technical problems, the present invention provides a method, apparatus, device and storage medium for detecting bulges in carbon fiber cloth, which uses vision to detect bulges in carbon fiber cloth.

[0006] According to a first aspect of the present invention, a method for detecting the bulge of carbon fiber cloth is provided, comprising the following steps: S10: Set the monitoring area, grayscale threshold, pixel value, and convex hull area value to obtain color image data of carbon fiber fabric. S20: Convert the color image data into grayscale image data; S30: Extract the region in the grayscale image data that meets the set grayscale threshold, perform a closing operation, and output the region A; S40: Perform a region growing algorithm on the grayscale image data, merge regions larger than the set pixel value, and output the result region; S50: Perform an opening operation on the result region, then perform a region classification algorithm, and output the result as region B; S60: Let the intersection of region A and region B be region C, and subtract region C from region B to obtain region D; S70: Separate the non-connected regions of region D, select the region with the largest area after separation, and if the area is greater than the set convex hull area value, issue an alarm.

[0007] In some embodiments of the present invention, step S40 further includes the following steps: S41: Set the convolution kernel size to 1×1 and the pixel grayscale difference value to 5; S42: Use the convolution kernel to scan the grayscale image data and calculate the difference between the grayscale of the center pixel of the rectangular image within the convolution kernel and the grayscale of the center pixel of the neighboring rectangular image; S43: Merge the regions where the pixel grayscale difference between the rectangular image and the neighboring rectangular image is less than 5 into a preprocessing region; S44: Judge each of the multiple preprocessed regions, and merge the regions within a single preprocessed region that contain more pixels than the set pixel value into the result region.

[0008] In some embodiments of the present invention, step S50 of the region classification algorithm further includes the following steps: S51: Create a 10×10 mask; S52: Scan the grayscale image data with the mask and calculate the number of pixels in the result area within the mask; S53: When the number of pixels is greater than or equal to 30, add the center point of the mask into the region B.

[0009] In some embodiments of the present invention, the set grayscale threshold is 200~255, the set pixel value is 150, the set convex hull area value is 1000, and the kernel radius of the closing operation and the opening operation is 3.5.

[0010] According to a second aspect of the present invention, a carbon fiber cloth bulge detection device is also provided, comprising: Acquisition module: used to set the monitoring area, grayscale threshold, pixel value, and convex hull area value to acquire color image data of carbon fiber fabric; Image processing module: used to convert the color image data into grayscale image data; First extraction module: used to extract the region in the grayscale image data that meets the set grayscale threshold, perform a closing operation, and output the region A; Merging module: used to perform a region growing algorithm on the grayscale image data, merge regions larger than the set pixel value, and output the result region; The second extraction module is used to perform an opening operation on the result region, and then perform a region classification algorithm. The result output is region B. Algorithm module: Used to denote the intersection of region A and region B as region C, and to obtain region D by subtracting region C from region B; Judgment module: Used to separate the non-connected regions of region D, select the region with the largest area after separation, and issue an alarm if the area is greater than the set convex hull area value.

[0011] In some embodiments of the present invention, the merging module further includes the following units: Setting unit: used to set the convolution kernel size of 1×1 and the pixel grayscale difference value of 5; Scanning unit: used to scan the grayscale image data using the convolution kernel, and to calculate the difference between the grayscale value of the center pixel of the rectangular image within the convolution kernel and the grayscale value of the center pixel of the neighboring rectangular images; Filtering unit: used to merge regions where the pixel grayscale difference between the rectangular image and the neighboring rectangular image is less than 5 into a preprocessing region; Recombination unit: used to judge multiple preprocessed regions respectively, and merge regions within a single preprocessed region that contain more than the set pixel value into the result region.

[0012] In some embodiments of the present invention, the region classification algorithm in the second extraction module further includes the following unit: Preset cell: Used to create a 10×10 mask; Calculation unit: used to scan the grayscale image data with the mask and calculate the number of pixels in the result area within the mask; Output unit: used to add the center point of the mask into the region B when the number of pixels is greater than or equal to 30.

[0013] In some embodiments of the present invention, the set grayscale threshold is 200~255, the set pixel value is 150, the set convex hull area value is 1000, and the kernel radius of the closing operation and the opening operation is 3.5.

[0014] According to a third aspect of the present invention, a carbon fiber fabric bulge detection device is also provided, comprising a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements the method described above.

[0015] According to a fourth aspect of the present invention, a carbon fiber cloth bulge detection storage medium is also provided, comprising a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the above-described method.

[0016] The beneficial effects of this invention are as follows: This invention photographs carbon fiber cloth and converts it into grayscale image data. Due to light reflection, the grayscale values ​​of the convex and flat parts of the carbon fiber cloth are different. First, region A within the grayscale threshold is extracted and closed. Then, a region growing algorithm is applied to the grayscale image data to merge regions with a pixel count greater than a set pixel value into a result region. An opening operation and a region classification algorithm are then applied to the result region, and the result region is output as region B. Then, region C is recorded as the intersection of region A and region B. Region D is obtained by subtracting region C from region B. Region D contains regions with convex hulls. Finally, the non-connected regions of region D are separated, and the largest area is selected for judgment. If the number of pixels in the area is greater than the set convex hull area value, an alarm is triggered. In this way, the convex hull of the carbon fiber cloth is detected visually. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the steps of the carbon fiber cloth bulge detection method in an embodiment of the present invention. Figure 2 This is a flowchart illustrating the calculation process of the carbon fiber cloth bulge detection method in an embodiment of the present invention. Figure 3 This is a diagram showing the relationship between different regions in the carbon fiber cloth convex hull detection method in this embodiment of the invention. Figure 4 This is a grayscale image data diagram of the carbon fiber cloth convex hull detection method in an embodiment of the present invention; Figure 5 This is a diagram of the region with the largest area in region D of the carbon fiber cloth convex hull detection method in this embodiment of the invention; Figure 6 This is a schematic diagram of the carbon fiber cloth bulge detection device in an embodiment of the present invention; Figure 7 This is a schematic diagram of the computer equipment for detecting carbon fiber cloth bulges in an embodiment of the present invention. Detailed Implementation

[0019] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0020] like Figures 1 to 5 The method for detecting the bulge of carbon fiber cloth shown includes the following steps: S10: Set the monitoring area and set the grayscale threshold, pixel value, and convex hull area value to obtain color image data of carbon fiber fabric. When performing convex hull detection on carbon fiber fabric, the image acquisition device takes pictures of the carbon fiber on the machine, and sets various data before detection. It should be noted that the values ​​of setting the grayscale threshold, pixel value, and convex hull area value can be adjusted according to the real-time background grayscale value.

[0021] S20: Convert color image data to grayscale image data; e.g. Figure 4 As shown, by converting color image data into grayscale image data, the difference in grayscale values ​​between impurities on the carbon fiber cloth and the convex bulges formed by light refraction is used to filter and judge the data.

[0022] S30: Extract regions from the grayscale image data that meet the set grayscale threshold, perform a closing operation, and output region A; by setting a grayscale threshold, extract a portion of regions that do not have a convex hull, perform a closing operation, and finally output region A. It should be noted that the closing operation is a processing method in morphological processing, which is existing technology and will not be elaborated here.

[0023] S40: Perform a region growing algorithm on the grayscale image data, merge regions with pixel values ​​greater than a set limit, and output the result region; calculate the grayscale image data using the region growing algorithm, select regions with pixel values ​​greater than a set limit value for merging, and the merged region awaits the next step of processing. It should be noted that the result region includes the black areas with convex hulls displayed on the grayscale image data and the white areas caused by lighting.

[0024] S50: Perform an opening operation on the resulting region, then perform a region classification algorithm, and output the result as region B; perform an opening operation on the above-mentioned resulting region, then perform a region classification algorithm to connect the closely separated regions in the above-mentioned resulting region. It should also be noted here that the opening operation is a processing method in morphological processing, which is existing technology and will not be elaborated here.

[0025] S60: Let region C be the intersection of region A and region B. Subtract region C from region B to obtain region D; for example... Figure 3 As shown, the region D with a convex hull is obtained through calculations between the regions.

[0026] S70: Separate the disconnected regions in region D, select the region with the largest area after separation, and trigger an alarm if the area exceeds the set convex hull area value. Region D may contain multiple regions with convex hulls. Separate region D to separate the disconnected regions, and select the region with the largest area for judgment. Figure 5 As shown, an alarm is triggered when the area exceeds the set convex hull area value.

[0027] like Figures 1 to 5 As shown, this invention uses carbon fiber cloth to capture images and convert them into grayscale image data. Due to light reflection, the grayscale values ​​of the convex and flat parts of the carbon fiber cloth differ. First, region A within a set grayscale threshold is extracted and closed. Then, a region growing algorithm is applied to the grayscale image data, merging regions with more pixels than a set pixel value into a result region. An opening operation and region classification algorithm are then performed on the result region, outputting region B. Region C is the intersection of region A and region B. Subtracting region C from region B yields region D, which contains regions with convex hulls. Finally, disconnected regions in region D are separated, and the largest area is selected for judgment. If the number of pixels within this area exceeds a set convex hull area value, an alarm is triggered. This allows for visual detection of convex hulls on the carbon fiber cloth. It should be noted that the opening and closing operations are existing technologies and will not be elaborated upon here.

[0028] S40 performs a region growing algorithm on the grayscale image data, merges regions larger than a set pixel value, and outputs the result region, including the following steps: S41: Set the convolution kernel size to 1×1 and the pixel grayscale difference value to 5; S42: Use a convolution kernel to scan the grayscale image data and calculate the difference between the grayscale value of the center pixel of the rectangular image within the convolution kernel and the grayscale value of the center pixel of the neighboring rectangular images. S43: Merge regions in the rectangular image and neighboring rectangular images with a pixel grayscale difference of less than 5 into a preprocessing region; S44: Judge multiple preprocessing regions separately, and merge the regions within a single preprocessing region that contain more than a set number of pixels into the result region.

[0029] like Figure 2As shown, a 1×1 convolution kernel is used to scan the entire grayscale image data. When the difference between the grayscale value of the center pixel of the rectangular image within the convolution kernel and the grayscale value of the center pixel of the neighboring rectangular images is less than a set pixel value of 5, the rectangular image and the neighboring rectangular images are merged to form a preprocessing region. The preprocessing region is then judged: if the pixel value within the preprocessing region is less than or equal to the set pixel value, the preprocessing region is discarded; if the pixel value within the preprocessing region is greater than the set pixel value, it is retained. After judging multiple preprocessing regions, all preprocessing regions with pixel values ​​greater than the set pixel value are merged to form the result region. This result region includes the black area containing the convex hull and the white area caused by the lighting.

[0030] In S50, the resulting region is opened and then classified using a region classification algorithm. The output is region B. The region classification algorithm includes the following steps: S51: Create a 10×10 mask; S52: Scan grayscale image data with a mask and calculate the number of pixels in the resulting region within the mask; S53: When the number of pixels is greater than or equal to 30, add the center point of the mask to region B.

[0031] In this invention, such as Figure 5 As shown, a 10×10 mask is used to scan the entire grayscale image data, and the number of pixels in the resulting region within the mask is calculated. When the number of pixels is greater than or equal to 30, the center point of the mask is added to region B; when the number of pixels is less than or equal to 30, this region is skipped, and the calculation continues for the next region. This process is repeated to completely scan the grayscale image data to determine the range of region B.

[0032] Based on the above embodiments, the grayscale threshold is set to 200-255, the pixel value is set to 150, the convex hull area is set to 1000, and the kernel radius for both closing and opening operations is 3.5. When marking region A, the white area in the grayscale image data is selected, the grayscale threshold is set to 200-255, and all white areas and areas with a grayscale value difference of 5 from white are selected into region A. Region A is a region without a convex hull. By merging the center point of the rectangular image with a pixel grayscale difference of 5 in the convolution kernel with the center point of the neighboring rectangular image, if the number of pixels in the preprocessing region is greater than the set pixel value of 150, they are retained; if they are less than or equal to 150, they are discarded. Then, they are merged again to form the result region. After separating the non-connected regions of region D, the largest area region is selected for judgment. If the pixel convex hull area value of the area region is less than or equal to 1000, it is ignored; if the pixel convex hull area value of the area region is greater than 1000, an alarm is triggered. When performing opening and closing operations on the result region, the kernel for both opening and closing operations is set to a radius of 3.5.

[0033] Those skilled in the art should know that the embodiments of this application can be provided as methods, devices, electronic devices or computer storage media products. Therefore, the embodiments of this application can be completely hardware embodiments, hardware and software combined embodiments or pure software embodiments. The test and detection process data processing device in the embodiments of this application will be described below. The device embodiments in the following text correspond to the method embodiments in the above text. Those skilled in the art can understand the implementation process in the following text based on the above description, and will not be described in detail here.

[0034] like Figure 6 The carbon fiber bulge detection device shown includes: Acquisition module: used to set the monitoring area, grayscale threshold, pixel value, and convex hull area value to acquire color image data of carbon fiber fabric; Image processing module: used to convert color image data into grayscale image data; First extraction module: used to extract the region in grayscale image data that meets the set grayscale threshold, perform a closing operation, and output the region A; Merging module: Used to perform region growing algorithm on grayscale image data, merge regions larger than a set pixel value, and output the result region; The second extraction module is used to perform an opening operation on the result region, then perform a region classification algorithm, and output the result as region B. Algorithm module: Used to denote the intersection of region A and region B as region C, and to obtain region D by subtracting region C from region B; Judgment module: Used to separate the non-connected regions of region D, select the region with the largest area after separation, and trigger an alarm if the area is greater than the set convex hull area value.

[0035] In some embodiments of the present invention, the merging module further includes the following units: Setting unit: used to set the convolution kernel size of 1×1 and the pixel grayscale difference value of 5; Scanning unit: Used to scan grayscale image data using a convolution kernel and calculate the difference between the grayscale value of the center pixel of the rectangular image within the convolution kernel and the grayscale value of the center pixel of the neighboring rectangular images; Filtering unit: Used to merge regions where the pixel grayscale difference between a rectangular image and its neighboring rectangular images is less than 5 into a preprocessing region; Recombination unit: Used to judge multiple preprocessed regions separately, and merge the regions in a single preprocessed region that contain more than a set number of pixels into the result region.

[0036] In some embodiments of the present invention, the region classification algorithm in the second extraction module further includes the following unit: Preset cell: Used to create a 10×10 mask; Calculation unit: used to scan grayscale image data with a mask and calculate the number of pixels in the result area within the mask; Output unit: Used to add the center point of the mask into region B when the number of pixels is greater than or equal to 30.

[0037] In some embodiments of the present invention, the grayscale threshold is set to 200~255, the pixel value is set to 150, the convex hull area is set to 1000, and the kernel radius of both the closing and opening operations is 3.5.

[0038] The following sections of the embodiments of the present invention will describe the embodiments of the electronic devices and computer storage media of the present invention. The embodiments of the electronic devices and computer storage media described below correspond to the method embodiments described above. Those skilled in the art can understand the implementation process described below based on the above description, and will not be described in detail here.

[0039] like Figure 7 The diagram shows the structure of a computer device provided in this application embodiment. A computer device 400 provided in this application embodiment includes: a memory 420, a processor 410, and a computer program stored in the memory 420 and executable on the processor 410. When the processor 410 executes the computer program, it implements the above-described method.

[0040] This application embodiment also provides a storage medium 430 on which a computer program is stored, and when the computer program is executed by the processor 410, it implements the above-described method.

[0041] The storage medium 430 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0042] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. "A plurality of" means two or more, unless otherwise explicitly specified.

[0043] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0044] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0045] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0046] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0047] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0048] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0049] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for detecting the bulge of carbon fiber cloth, characterized in that, The steps include the following: S10: Set the monitoring area, grayscale threshold, pixel value, and convex hull area value to obtain color image data of carbon fiber fabric. S20: Convert the color image data into grayscale image data; S30: Extract the region in the grayscale image data that meets the set grayscale threshold, perform a closing operation, and output the region A; S40: Perform a region growing algorithm on the grayscale image data, merge regions larger than the set pixel value, and output the result region; S50: Perform an opening operation on the result region, then perform a region classification algorithm, and output the result as region B; S60: Let the intersection of region A and region B be region C, and subtract region C from region B to obtain region D; S70: Separate the non-connected regions of region D, select the region with the largest area after separation, and if the area is greater than the set convex hull area value, issue an alarm; Step S40 also includes the following steps: S41: Set the convolution kernel size to 1×1 and the pixel grayscale difference value to 5; S42: Use the convolution kernel to scan the grayscale image data and calculate the difference between the grayscale of the center pixel of the rectangular image within the convolution kernel and the grayscale of the center pixel of the neighboring rectangular image; S43: Merge the regions where the pixel grayscale difference between the rectangular image and the neighboring rectangular image is less than 5 into a preprocessing region; S44: Judge the multiple preprocessing regions respectively, and merge the regions in a single preprocessing region that contain more than the set pixel value into the result region; In step S50, the region classification algorithm further includes the following steps: S51: Create a 10×10 mask; S52: Scan the grayscale image data with the mask and calculate the number of pixels in the result area within the mask; S53: When the number of pixels is greater than or equal to 30, add the center point of the mask into the region B.

2. The carbon fiber cloth bulge detection method according to claim 1, characterized in that, The grayscale threshold is set to 200~255, the pixel value is set to 150, the convex hull area is set to 1000, and the kernel radius of both the closing and opening operations is 3.

5.

3. A carbon fiber cloth bulge detection device, characterized in that, include: Acquisition module: used to set the monitoring area, grayscale threshold, pixel value, and convex hull area value to acquire color image data of carbon fiber fabric; Image processing module: used to convert the color image data into grayscale image data; First extraction module: used to extract the region in the grayscale image data that meets the set grayscale threshold, perform a closing operation, and output the region A; Merging module: used to perform a region growing algorithm on the grayscale image data, merge regions larger than the set pixel value, and output the result region; The second extraction module is used to perform an opening operation on the result region, and then perform a region classification algorithm. The result output is region B. Algorithm module: used to denote the intersection of region A and region B as region C, and to obtain region D by subtracting region C from region B; Judgment module: used to separate the non-connected regions of region D, select the region with the largest area after separation, and issue an alarm if the area is greater than the set convex hull area value; The merging module also includes the following units: Setting unit: used to set the convolution kernel size of 1×1 and the pixel grayscale difference value of 5; Scanning unit: used to scan the grayscale image data using the convolution kernel, and to calculate the difference between the grayscale value of the center pixel of the rectangular image within the convolution kernel and the grayscale value of the center pixel of the neighboring rectangular images; Filtering unit: used to merge regions where the pixel grayscale difference between the rectangular image and the neighboring rectangular image is less than 5 into a preprocessing region; Recombination unit: used to judge multiple preprocessed regions respectively, and merge the regions in a single preprocessed region that contain more than the set pixel value into the result region; In the second extraction module, the region classification algorithm further includes the following units: Preset cell: Used to create a 10×10 mask; Calculation unit: used to scan the grayscale image data with the mask and calculate the number of pixels in the result area within the mask; Output unit: used to add the center point of the mask into the region B when the number of pixels is greater than or equal to 30.

4. The carbon fiber cloth bulge detection device according to claim 3, characterized in that, The grayscale threshold is set to 200~255, the pixel value is set to 150, the convex hull area is set to 1000, and the kernel radius of both the closing and opening operations is 3.

5.

5. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1-2.

6. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-2.

Images