Method, system and equipment for detecting bending degree of twill defect and storage medium

Abstract

The invention provides a twill defect bending degree detection method, system and device and a storage medium, and relates to the technical field of defect detection.The method comprises the steps that twill skeleton line extraction processing is conducted on an original image to obtain a twill skeleton line image; performing equal interval sampling processing on the twill skeleton line image to obtain a sampling point array; sequentially obtaining coordinate information of adjacent sampling points from the sampling point array to carry out slope calculation on the twill skeleton line so as to obtain a slope matrix; and based on the slope matrix, acquiring statistical indexes such as a total number, an average number, a median, a mode, a standard deviation, a total number of negative values, a total number of positive values and the like of slopes, and carrying out linearity calculation so as to obtain a twill defect bending judgment result. According to the method, the bending degree of the twill curve is comprehensively evaluated through statistical indexes, so that the automation degree of judgment of the bending degree of the twill defect is relatively high, and the condition of false detection is not easy to occur.

Description

Technical Field

[0001] The present invention relates to the technical field of defect detection, and in particular to a method, system, device and storage medium for detecting the bending degree of a twill defect. Background Art

[0002] At present, in the process of product production, OLED manufacturers first use measurement equipment to perform current and voltage detection using an array test method to output a current and voltage image of the back of the OLED; and then annotate the defects on the current and voltage image to generate a defect target frame; then use manual image judgment to determine the defect level of the defect target frame of the current and voltage image; finally, intercept, scrap or repair the product based on the defect level determination results to reduce material loss and manpower waste in the back-end production process; and optimize the production process and incoming materials based on existing defects to improve the yield.

[0003] When faced with twill defects, the existing technology mostly uses manual detection to determine the bending grade of the twill defects. Since the manual detection method is inefficient and the judgment standards are not unified, false detection is prone to occur. Summary of the invention

[0004] In order to solve the problem of low efficiency in determining the bending degree of a twill defect and prone to false detection, an embodiment of the present invention provides a method, system, device and storage medium for detecting the bending degree of a twill defect.

[0005] In a first aspect, an embodiment of the present invention provides a method for detecting the bending degree of a twill defect, and the method flow is as follows:

[0006] Performing twill skeleton line extraction processing on the original image to obtain a twill skeleton line image;

[0007] Performing equal-interval sampling processing on the twill skeleton line image to obtain a sampling point array of the twill skeleton line;

[0008] The coordinate information of adjacent sampling points is sequentially acquired from the sampling point array of the twill skeleton line, and the slope of the twill skeleton line is calculated according to the coordinate information of the adjacent sampling points to obtain the slope matrix of the twill skeleton line;

[0009] Based on the slope matrix of the twill skeleton line, the total number, mean, median, mode, standard deviation, total number of negative values ​​and total number of positive values ​​of the slopes are obtained, and the linearity of the twill skeleton line is calculated based on the total number, mean, median, mode, standard deviation, total number of negative values ​​and total number of positive values ​​of the slopes to obtain the twill defect bending judgment result.

[0010] In the above embodiment, the present invention first obtains the twill skeleton line through image processing technology, and then calculates the slope matrix of the twill skeleton line by equally spaced sampling on the basis of the twill skeleton line, and finally obtains the total number, mean, median, mode, standard deviation, total number of negative values ​​and total number of positive values ​​of the slope on the basis of the slope matrix of the twill skeleton line, and comprehensively evaluates the curvature of the twill curve through statistical indicators, so that the determination of the curvature degree of the twill defect is highly automated, can be clearly and easily distinguished, and is not prone to false detection.

[0011] As some optional implementations of the present application, before performing twill skeleton line extraction on the original image, it is necessary to perform image enhancement processing and grayscale conversion processing on the original image.

[0012] In the above embodiment, the present invention performs image enhancement processing and grayscale conversion processing on the original image, so that the diagonal skeleton lines of the original image are clearer.

[0013] As some optional implementations of the present application, the process of performing image enhancement processing on the original image is as follows:

[0014] Perform forward Fourier transform on the original image to convert the original image from time domain to frequency domain;

[0015] The original image in the frequency domain is subjected to high-frequency filtering and inverse Fourier transform to convert the original image in the frequency domain from the frequency domain to the time domain.

[0016] In the above embodiment, the present invention can enhance the saturation of the image and filter out the noise interference of the original image by performing Fourier transform on the original image.

[0017] As some optional implementations of the present application, the process of grayscale conversion of the original image is as follows:

[0018] Preset the grayscale threshold corresponding to the original image;

[0019] Performing grayscale conversion processing on the original image to convert the color original image into a grayscale original image;

[0020] The pixels in the original image whose grayscale values ​​are less than the grayscale threshold are replaced with black, and the pixels whose grayscale values ​​are greater than the grayscale threshold are replaced with white.

[0021] In the above embodiment, the present invention can facilitate the subsequent extraction of the diagonal skeleton line by performing grayscale conversion processing on the original image.

[0022] As some optional implementations of the present application, the process of performing twill skeleton line extraction processing on the original image to obtain a twill skeleton line image is as follows:

[0023] Each pixel in the original image is taken as the central pixel, and the gray value is replaced by reconstructing the neighborhood pixel information based on the central pixel;

[0024] All the pixels of the original image are traversed, and the corresponding pixel is used as the central pixel to reconstruct the neighborhood pixel information to obtain the final twill skeleton line image.

[0025] In the above embodiments, the present invention uses neighborhood information to reconstruct feature maps to extract features from images, thereby enhancing the feature extraction capability while ensuring the integrity of feature extraction.

[0026] As some optional implementations of the present application, the process of equally spaced sampling of the twill skeleton line image to obtain the sampling point array of the twill skeleton line is as follows:

[0027] Acquire coordinate information of a first initial sampling point from one side of the diagonal skeleton line image, and translate the first initial sampling point left and right along the diagonal skeleton line image according to a preset step length to obtain coordinate information of a second primary sampling point and a third primary sampling point;

[0028] The coordinate information of a plurality of sampling points is obtained at equal intervals based on the first initial sampling point, the second initial sampling point and the third initial sampling point to obtain the first sampling point array, the second sampling point array and the third sampling point array of the twill skeleton line.

[0029] In the above embodiment, the present invention uses three different positions as initial sampling points, and performs equally spaced sampling based on the three initial sampling points, thereby obtaining three different sampling point arrays, which can effectively prevent the influence of slight breaks in the twill skeleton line image on the sampling.

[0030] As some optional implementations of the present application, the coordinate information of adjacent sampling points is sequentially obtained from the sampling point array of the twill skeleton line, and the slope of the twill skeleton line is calculated according to the coordinate information of the adjacent sampling points to obtain the slope matrix of the twill skeleton line. The process is as follows:

[0031] Acquire coordinate information of adjacent sampling points from the first sampling point array, the second sampling point array, and the third sampling point array, respectively, and calculate the slope of the twill skeleton line according to the coordinate information of the adjacent sampling points to obtain a first slope matrix, a second slope matrix, and a third slope matrix of the twill skeleton line;

[0032] The first slope matrix, the second slope matrix and the third slope matrix of the twill skeleton line are averaged to obtain the final slope matrix of the twill skeleton line; wherein, if there are missing sampling points corresponding to the first slope matrix, the second slope matrix and the third slope matrix, the corresponding parameters are defaulted to empty.

[0033] In the above embodiment, the present invention calculates the slope based on three groups of samples, and then obtains three different slope matrices. By performing mean check on the three different slope matrices, the accuracy of the slope and the influence of slight fracture of the twill skeleton line on the slope calculation can be ensured.

[0034] As some optional embodiments of the present application, the formula for calculating the linearity of the twill skeleton line based on the total number, mean, median, mode, standard deviation, total number of negative values ​​and total number of positive values ​​of the slope is as follows:

[0035]

[0036] in:

[0037]

[0038] Where L represents the linearity of the twill skeleton line, δ represents the standard deviation of the slope, represents the average of the slopes, Represents the median, M 0 represents the mode, α represents the total number of positive values ​​of the slope, β represents the total number of negative values ​​of the slope, γ represents the total number of slopes, and ε and ω represent adjustment parameters.

[0039] In the above embodiment, the present invention uses statistical indicators to comprehensively evaluate the bending degree of the twill curve, so that the bending degree determination of the twill defect is highly automated, can be clearly and easily distinguished, and is less likely to cause false detection problems.

[0040] In a second aspect, the present invention provides a system for detecting the bending degree of a twill defect, wherein the functions of the system correspond one-to-one to the method, and the system comprises:

[0041] A twill skeleton line extraction unit, the twill skeleton line extraction unit is used to perform twill skeleton line extraction processing on the original image to obtain a twill skeleton line image;

[0042] An equally spaced sampling unit, the equally spaced sampling unit is used to perform equally spaced sampling processing on the twill skeleton line image to obtain a sampling point array of the twill skeleton line;

[0043] A slope matrix construction unit, the slope matrix construction unit is used to sequentially obtain the coordinate information of adjacent sampling points from the sampling point array of the twill skeleton line, and calculate the slope of the twill skeleton line according to the coordinate information of the adjacent sampling points to obtain a slope matrix of the twill skeleton line;

[0044] A twill defect bending judgment unit, wherein the twill defect bending judgment unit obtains the total number, average number, median number, mode, standard deviation, total number of negative values ​​and total number of positive values ​​of the slopes based on the slope matrix of the twill skeleton line, and calculates the linearity of the twill skeleton line based on the total number, average number, median number, mode, standard deviation, total number of negative values ​​and total number of positive values ​​of the slopes to obtain a twill defect bending judgment result.

[0045] In a third aspect, the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the method for detecting the degree of bending of a twill defect.

[0046] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and the computer program, when executed by a processor, implements the method for detecting the degree of bending of a twill defect.

[0047] The beneficial effects of the present invention are as follows: the present invention first obtains the twill skeleton line through image processing technology, and then calculates the slope matrix of the twill skeleton line by equally spaced sampling on the basis of the twill skeleton line, and finally obtains the total number, mean, median, mode, standard deviation, total number of negative values ​​and total number of positive values ​​of the slope on the basis of the slope matrix of the twill skeleton line, and comprehensively evaluates the curvature of the twill curve through statistical indicators, so that the determination of the curvature degree of the twill defect is highly automated, can be clearly and easily distinguished, and is not prone to false detection problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 is a schematic diagram of the computer device structure of the hardware operating environment described in the embodiment of the present invention;

[0050] Figure 2 is a flow chart of a method for detecting the bending degree of a twill defect according to an embodiment of the present invention;

[0051] Figure 3 is a schematic diagram of comparison between an original image and a twill skeleton line according to an embodiment of the present invention;

[0052] Figure 4 It is a structural block diagram of the bending degree detection system of the twill defect described in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0054] In order to solve the problem of low efficiency and easy misdetection in determining the bending degree of twill defects, the present application provides a method, system, device and medium for detecting the bending degree of twill defects. Before introducing the specific technical solution of the present application, the hardware operating environment involved in the embodiment of the present application is first introduced.

[0055] See also Figure 1 , Figure 1 A schematic diagram of the computer device structure of the hardware operating environment involved in the embodiment of the present application.

[0056] like Figure 1 As shown, the computer device may include: a processor, such as a central processing unit (CPU), a communication bus, a user interface, a network interface, and a memory. Among them, the communication bus is used to realize the connection and communication between these components. The user interface may include a display screen (Display), an input unit such as a keyboard (Keyboard), and optionally, the user interface may also include a standard wired interface and a wireless interface. The network interface may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity interface). The memory may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory may optionally be a storage device independent of the aforementioned processor.

[0057] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the computer device, and may include more or less components than shown in the figure, or combine some components, or arrange the components differently.

[0058] like Figure 1 As shown, the memory as a storage medium may include an operating system module, a network communication module, a user interface module and a data storage module.

[0059] exist Figure 1In the computer device shown, the network interface is mainly used for data communication with the network server; the user interface is mainly used for data interaction with the user; the processor and memory in the computer device of the present application can be set in the computer device, and the computer device calls the twill defect bending degree detection system stored in the data storage module in the memory through the processor, and executes the twill defect bending degree detection method provided in the embodiment of the present application.

[0060] Based on the hardware environment of the aforementioned embodiment, the embodiment of the present application provides a method for detecting the bending degree of a twill defect. Figure 2 , Figure 2 The flowchart of the method for detecting the bending degree of the twill defect is as follows:

[0061] (1) Performing diagonal skeleton line extraction processing on the original image to be detected to obtain a diagonal skeleton line image.

[0062] In the embodiment of the present invention, in order to make the diagonal skeleton lines of the original image clearer, before performing diagonal skeleton line extraction processing on the original image to be detected, it is necessary to perform image enhancement processing and grayscale conversion processing on the original image.

[0063] In the embodiment of the present invention, by performing image enhancement processing on the original image, the saturation of the image can be enhanced and the noise interference of the original image can be filtered out. Specifically, the process of performing image enhancement processing on the original image is as follows:

[0064] (1.1) Perform forward Fourier transform on the original image to convert the original image from time domain to frequency domain.

[0065] (1.2) The original image in the frequency domain is subjected to high-frequency filtering and inverse Fourier transform to convert the original image in the frequency domain from the frequency domain to the time domain.

[0066] In the embodiment of the present invention, by performing grayscale conversion processing on the original image, the background effect of the original image can be filtered out, making the twill skeleton line clearer. Specifically, the process of performing grayscale conversion processing on the original image is as follows:

[0067] (1.3) A grayscale threshold corresponding to the original image is preset, wherein the grayscale threshold may be an average grayscale value of the original image.

[0068] (1.4) Perform grayscale conversion on the original image to convert the color original image into a grayscale original image.

[0069] (1.5) In the original image, the pixels whose grayscale values ​​are less than the grayscale threshold are replaced with black, and the pixels whose grayscale values ​​are greater than the grayscale threshold are replaced with white.

[0070] In the embodiment of the present invention, in order to enhance the feature extraction capability while ensuring the integrity of the feature extraction, the feature extraction of the twill skeleton line of the original image is performed by reconstructing the feature map using neighborhood information. Specifically, the process of performing twill skeleton line extraction processing on the original image to obtain a twill skeleton line image is as follows:

[0071] (1.6) Each pixel in the original image is taken as the central pixel, and the gray value is replaced based on the central pixel by reconstructing the neighborhood pixel information.

[0072] (1.7) Traverse all the pixels of the original image and use the corresponding pixel as the center pixel to reconstruct the neighborhood pixel information to obtain the final twill skeleton line image.

[0073] (2) The twill skeleton line image is sampled at equal intervals to obtain a sampling point array of the twill skeleton line.

[0074] In the embodiment of the present invention, in order to effectively prevent the influence of slight breaks of the twill skeleton line image on the sampling, three different positions are used as initial sampling points, and equally spaced sampling is performed based on the three initial sampling points. Specifically, the process of equally spaced sampling processing of the twill skeleton line image is as follows:

[0075] (2.1) Acquire coordinate information of a first initial sampling point from one side of the diagonal skeleton line image, and translate the first initial sampling point left and right along the diagonal skeleton line image according to a preset step length to obtain coordinate information of a second primary sampling point and a third primary sampling point; wherein the preset step length is set according to actual conditions, and the embodiment of the present invention does not limit this.

[0076] (2.2) Based on the first initial sampling point, the second initial sampling point and the third initial sampling point, coordinate information of a plurality of sampling points is obtained at equal intervals to obtain a first sampling point array, a second sampling point array and a third sampling point array of the twill skeleton line.

[0077] (3) The coordinate information of adjacent sampling points is sequentially obtained from the sampling point array of the twill skeleton line, and the slope of the twill skeleton line is calculated according to the coordinate information of the adjacent sampling points to obtain the slope matrix of the twill skeleton line.

[0078] In the embodiment of the present invention, in order to ensure the accuracy of the slope and the influence of slight fracture of the twill skeleton line on the slope calculation, the slope is calculated based on three groups of sampling, and then three different slope matrices are obtained, and the mean value of the three different slope matrices is checked. Specifically, the process of calculating the slope of the twill skeleton line according to the coordinate information of adjacent sampling points is as follows:

[0079] (3.1) Obtaining coordinate information of adjacent sampling points from the first sampling point array, the second sampling point array, and the third sampling point array, respectively, and calculating the slope of the twill skeleton line according to the coordinate information of the adjacent sampling points to obtain a first slope matrix, a second slope matrix, and a third slope matrix of the twill skeleton line.

[0080] (3.2) The first slope matrix, the second slope matrix and the third slope matrix of the twill skeleton line are averaged to obtain the final slope matrix of the twill skeleton line; wherein, if there are missing sampling points corresponding to the first slope matrix, the second slope matrix and the third slope matrix, the corresponding parameters are defaulted to empty.

[0081] (4) Based on the slope matrix of the twill skeleton line, the total number, mean, median, mode, standard deviation, total number of negative values ​​and total number of positive values ​​of the slopes are obtained, and based on the total number, mean, median, mode, standard deviation, total number of negative values ​​and total number of positive values ​​of the slopes, the linearity of the twill skeleton line is calculated to obtain the twill defect bending judgment result.

[0082] In an embodiment of the present invention, the linearity calculation formula of the twill skeleton line based on the total number, mean, median, mode, standard deviation, total number of negative values ​​and total number of positive values ​​of the slope is as follows:

[0083]

[0084] in:

[0085]

[0086] Where L represents the linearity of the twill skeleton line, δ represents the standard deviation of the slope, represents the average of the slopes, Represents the median, M 0 represents the mode, α represents the total number of positive values ​​of the slope, β represents the total number of negative values ​​of the slope, γ represents the total number of slopes, ε and ω represent adjustment parameters, ω=2, ε=10, and specifically, ε and ω are obtained based on experience and can be adjusted according to actual conditions.

[0087] Specifically, the calculation formula for the standard deviation is as follows:

[0088]

[0089] Among them, M i represents the parameters of the slope matrix, i represents the i-th parameter of the slope matrix, and n represents the total number of parameters of the slope matrix.

[0090] In the embodiment of the present invention, after the linearity of the twill skeleton line is obtained, the linearity is determined according to the preset twill defect bending determination threshold, see Figure 3 , Figure 3 Schematic diagram of the comparison between four groups of original images and twill skeleton line images, wherein (a) corresponds to the linearity L=0.0653 of the twill skeleton line, (b) corresponds to the linearity L=0.0971 of the twill skeleton line, (c) corresponds to the linearity L=15.674 of the twill skeleton line, and (d) corresponds to the linearity L=33684.505 of the twill skeleton line. For example, the twill defect bending determination threshold can be set to multiple values, such as 1, 10, 100, etc. When the linearity is less than 1, it can be determined that the defect is not bent, when the linearity is between 1 and 10, it is determined to be slightly bent, when the linearity is between 10 and 100, it is determined to be moderately bent, and when the linearity is greater than 100, it is determined to be severely bent. The specific determination threshold and determination rule can be set according to the actual situation, and the embodiment of the present invention does not limit this.

[0091] In summary, the present invention first obtains the twill skeleton line through image processing technology, and then calculates the slope matrix of the twill skeleton line by equally spaced sampling on the basis of the twill skeleton line, and finally obtains statistical indicators such as the total number, mean, median, mode, standard deviation, total number of negative values ​​and total number of positive values ​​of the slope based on the slope matrix of the twill skeleton line, and comprehensively evaluates the curvature of the twill curve through statistical indicators, so that the determination of the curvature degree of the twill defect is highly automated, can be clearly and easily distinguished, and is not prone to false detection problems.

[0092] In addition, in one embodiment, based on the same inventive concept as the above embodiment, the embodiment of the present invention provides a system for detecting the bending degree of a twill defect, and the system corresponds one-to-one with the method of embodiment 1, see Figure 4 , Figure 4 The structural block diagram of the twill defect bending degree detection system is as follows:

[0093] A twill skeleton line extraction unit, the twill skeleton line extraction unit is used to perform twill skeleton line extraction processing on the original image to obtain a twill skeleton line image;

[0094] An equally spaced sampling unit, the equally spaced sampling unit is used to perform equally spaced sampling processing on the twill skeleton line image to obtain a sampling point array of the twill skeleton line;

[0095] A slope matrix construction unit, the slope matrix construction unit is used to sequentially obtain the coordinate information of adjacent sampling points from the sampling point array of the twill skeleton line, and calculate the slope of the twill skeleton line according to the coordinate information of the adjacent sampling points to obtain a slope matrix of the twill skeleton line;

[0096] A twill defect bending judgment unit, wherein the twill defect bending judgment unit obtains the total number, average number, median number, mode, standard deviation, total number of negative values ​​and total number of positive values ​​of the slopes based on the slope matrix of the twill skeleton line, and calculates the linearity of the twill skeleton line based on the total number, average number, median number, mode, standard deviation, total number of negative values ​​and total number of positive values ​​of the slopes to obtain a twill defect bending judgment result.

[0097] It should be noted that each unit in the twill defect bending degree detection system in this embodiment corresponds one-to-one to each step in the twill defect bending degree detection method in the aforementioned embodiment. Therefore, the specific implementation method and technical effects achieved in this embodiment can refer to the implementation method of the aforementioned twill defect bending degree detection method, which will not be repeated here.

[0098] In addition, in one embodiment, the present application also provides a computer device, which includes a processor, a memory, and a computer program stored in the memory, and the computer program implements the method in the aforementioned embodiment when executed by the processor.

[0099] In addition, in one embodiment, the present application further provides a computer storage medium, on which a computer program is stored, and the computer program implements the method in the aforementioned embodiment when executed by a processor.

[0100] In some embodiments, the computer readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories. The computer may be various computing devices including intelligent terminals and servers.

[0101] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0102] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0103] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices located at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0104] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0105] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0106] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a multimedia terminal device (which can be a mobile phone, a computer, a television receiver, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0107] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for detecting the bending degree of twill defects, characterized in that: The method flow is as follows: Performing twill skeleton line extraction processing on the original image to obtain a twill skeleton line image; Performing equal-interval sampling processing on the twill skeleton line image to obtain a sampling point array of the twill skeleton line; The coordinate information of adjacent sampling points is sequentially acquired from the sampling point array of the twill skeleton line, and the slope of the twill skeleton line is calculated according to the coordinate information of the adjacent sampling points to obtain the slope matrix of the twill skeleton line; Based on the slope matrix of the twill skeleton line, the total number, mean, median, mode, standard deviation, total number of negative values ​​and total number of positive values ​​of the slopes are obtained, and the linearity of the twill skeleton line is calculated based on the total number, mean, median, mode, standard deviation, total number of negative values ​​and total number of positive values ​​of the slopes to obtain the twill defect bending judgment result.

2. A method for detecting the bending degree of twill defects according to claim 1, characterized in that: Before performing twill skeleton line extraction on the original image, the original image needs to be subjected to image enhancement and grayscale conversion processing.

3. A method for detecting the bending degree of twill defects according to claim 2, characterized in that: The process of image enhancement processing on the original image is as follows: Perform forward Fourier transform on the original image to convert the original image from time domain to frequency domain; The original image in the frequency domain is subjected to high-frequency filtering and inverse Fourier transformation, and the original image subjected to high-frequency filtering in the frequency domain is converted from the frequency domain to the time domain.

4. A method for detecting the bending degree of twill defects according to claim 2, characterized in that: The process of grayscale conversion of the original image is as follows: Preset the grayscale threshold corresponding to the original image; Performing grayscale conversion processing on the original image to convert the color original image into a grayscale original image; The pixels in the original image whose grayscale values ​​are less than the grayscale threshold are replaced with black, and the pixels whose grayscale values ​​are greater than the grayscale threshold are replaced with white.

5. A method for detecting the bending degree of twill defects according to claim 1, characterized in that: The process of extracting the twill skeleton line of the original image to obtain the twill skeleton line image is as follows: Each pixel in the original image is taken as the central pixel, and the gray value is replaced by reconstructing the neighborhood pixel information based on the central pixel; All the pixels of the original image are traversed, and the corresponding pixel is used as the central pixel to reconstruct the neighborhood pixel information to obtain the final twill skeleton line image.

6. A method for detecting the bending degree of twill defects according to claim 1, characterized in that: The process of equally spaced sampling of the twill skeleton line image to obtain the sampling point array of the twill skeleton line is as follows: Acquire coordinate information of a first initial sampling point from one side of the diagonal skeleton line image, and translate the first initial sampling point left and right along the diagonal skeleton line image according to a preset step length to obtain coordinate information of a second primary sampling point and a third primary sampling point; The coordinate information of a plurality of sampling points is obtained at equal intervals based on the first initial sampling point, the second initial sampling point and the third initial sampling point to obtain the first sampling point array, the second sampling point array and the third sampling point array of the twill skeleton line.

7. A method for detecting the bending degree of a twill defect according to claim 6, characterized in that: The coordinate information of adjacent sampling points is sequentially obtained from the sampling point array of the twill skeleton line, and the slope of the twill skeleton line is calculated according to the coordinate information of the adjacent sampling points to obtain the slope matrix of the twill skeleton line. The process is as follows: Acquire coordinate information of adjacent sampling points from the first sampling point array, the second sampling point array, and the third sampling point array, respectively, and calculate the slope of the twill skeleton line according to the coordinate information of the adjacent sampling points to obtain a first slope matrix, a second slope matrix, and a third slope matrix of the twill skeleton line; The first slope matrix, the second slope matrix and the third slope matrix of the twill skeleton line are averaged to obtain the final slope matrix of the twill skeleton line; wherein, if there are missing sampling points corresponding to the first slope matrix, the second slope matrix and the third slope matrix, the corresponding parameters are defaulted to empty.

8. A method for detecting the bending degree of twill defects according to claim 1, characterized in that: The linearity calculation formula for the twill skeleton line based on the total number of slopes, mean, median, mode, standard deviation, total number of negative values, and total number of positive values ​​is as follows: in: Where δ represents the standard deviation of the slope, represents the average of the slopes, represents the median, M0 represents the mode, α represents the total number of positive values ​​of the slope, β represents the total number of negative values ​​of the slope, γ represents the total number of slopes, and ε and ω represent adjustment parameters.

9. A system for detecting the bending degree of twill defects, characterized in that: The system comprises: A twill skeleton line extraction unit, the twill skeleton line extraction unit is used to perform twill skeleton line extraction processing on the original image to obtain a twill skeleton line image; An equally spaced sampling unit, the equally spaced sampling unit is used to perform equally spaced sampling processing on the twill skeleton line image to obtain a sampling point array of the twill skeleton line; A slope matrix construction unit, the slope matrix construction unit is used to sequentially obtain the coordinate information of adjacent sampling points from the sampling point array of the twill skeleton line, and calculate the slope of the twill skeleton line according to the coordinate information of the adjacent sampling points to obtain a slope matrix of the twill skeleton line; A twill defect bending judgment unit, wherein the twill defect bending judgment unit obtains the total number, average number, median number, mode, standard deviation, total number of negative values ​​and total number of positive values ​​of the slopes based on the slope matrix of the twill skeleton line, and calculates the linearity of the twill skeleton line based on the total number, average number, median number, mode, standard deviation, total number of negative values ​​and total number of positive values ​​of the slopes to obtain a twill defect bending judgment result.

10. 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, the method for detecting the bending degree of twill defects as described in any one of claims 1 to 7 is implemented.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for detecting the bending degree of a twill defect according to any one of claims 1 to 7 is implemented.

Images