Linear defect detection method, system and equipment and storage medium

Through technologies such as guide filtering, local enhancement and edge detection, combined with directional verification, the missed detection and over-checking problems in linear defect detection of organic electro laser displays are solved, and more accurate defect detection is achieved.

CN118941543APending Publication Date: 2024-11-12GUANGDONG SHULIAN INTELLIGENT MANUFACTURING TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411081634.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-08
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

During the production process, linear defect detection of organic electro laser displays is prone to missed and over-checking problems, and due to background noise interference, it is difficult to accurately identify.

Method used

The original image is processed by guide filtering, local enhancement, edge detection and defect directional verification. The noise is removed through guide filtering, local enhancement data is extracted, and features are extracted by Robinson edge detection, and the directionality and distance verification are combined to correct slight truncation. linear defect.

Benefits of technology

Effectively prevent missed inspection and over-inspection, improve the accuracy and reliability of linear defect detection, and ensure high-quality inspection of organic electro laser displays.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941543A_ABST
    Figure CN118941543A_ABST
Patent Text Reader

Abstract

The invention provides a linear defect detection method, system and device and a storage medium, and relates to the technical field of linear defect detection.The method comprises the steps that directional denoising is conducted on an original image in a guiding filtering mode to obtain a linear defect filtering image; performing image enhancement on the linear defect filtered image by adopting a local enhancement mode to obtain a linear defect enhanced image; performing feature extraction on the linear defect enhanced image by adopting an edge detection mode to obtain a linear defect feature image; and performing feature connectivity verification on the linear defect feature image by adopting a defect directivity verification mode to obtain a linear defect detection result. According to the method, noise of an original image is firstly removed, then data enhancement is carried out on local linear defects, feature extraction is carried out on the linear defects, finally, the slightly-truncated linear defects are corrected in combination with the directivity and the distance of the linear defects, and the problem that missing detection and over detection are prone to occurring in linear defect detection is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

[0002] Organic Light-Emitting Diode (OLED) has gradually become a new favorite display screen for the public due to its advantages such as flexible screen, low energy consumption, and self-luminescence, and its application scope is becoming more and more extensive. In the production and lighting process of organic laser displays, linear defects are more likely to occur. Although linear defects have a single form, they are prone to missed detection due to the different depths of the features of linear defects on the screen; in addition, due to the interference of background noise similar to linear defects, it is easy to over-inspect. Summary of the invention

[0003] The present invention provides a linear defect detection method, system, device and storage medium, which solve the problem that linear defect detection of an organic laser display is prone to missed detection and over-detection.

[0004] In a first aspect, an embodiment of the present invention provides a linear defect detection method, the method comprising the following steps:

[0005] The original image is denoised in a direction by using guided filtering to obtain a linear defect filtered image.

[0006] The linear defect filter image is enhanced by using a local enhancement method to obtain a linear defect enhanced image;

[0007] The edge detection method is used to extract the features of the linear defect enhanced image to obtain the linear defect feature image;

[0008] The defect directionality verification method is used to perform feature connectivity verification on the linear defect feature image to obtain the linear defect detection result.

[0009] In the above embodiment, the present invention combines the linear characteristics of linear defects to first remove the noise of the original image itself by means of guided filtering to restore the true defect characteristics; secondly, data enhancement is performed on local linear defects to facilitate subsequent extraction; then the Robinson defect detection method is used to extract linear defects to highlight the defects; finally, the slightly truncated linear defects are corrected in combination with the directionality and distance of the linear defects to prevent missed detection.

[0010] As some optional implementations of the present application, the process of using guided filtering to perform direction denoising on the original image to obtain a linear defect filtered image is as follows:

[0011] A guide image is constructed based on the original image, and the guide image and the original image are simultaneously input into a local linear model to obtain a linear relationship between the guide image and the original image;

[0012] Based on the linear relationship between the guide image and the original image, the original image is directionally denoised to obtain a linear defect filtered image.

[0013] In the above embodiment, the present invention uses guided filtering to perform directional filtering and denoising on the input original image. When the original image needs to be filtered and denoised, the traditional linear filtering method often blurs the image details or cannot effectively remove the noise. The guided filtering solves this problem by using the reference image in the guided image, and can remove the noise and enhance the contrast of the image while maintaining the details of the original image. The core idea of ​​the guided filtering is to use the information in the guided image to guide the filtering and denoising process of the input original image. The guided image can better understand the structure and texture in the image, so as to more accurately balance the contradiction between maintaining details and removing noise in the filtering process.

[0014] As some optional implementations of the present application, the process of constructing a guide image based on the original image is as follows:

[0015] The original image is subjected to binarization processing, edge contour extraction processing and pixel value expansion processing to obtain an edge contour image;

[0016] The edge contour image and the original image are superimposed to obtain a guiding image.

[0017] In the above embodiment, the present invention performs binarization processing on the original image in order to convert the original image into a binary image, performs edge contour extraction processing on the binary image of the original image in order to extract the defect contour in the image; performs pixel value expansion processing on the defect contour in the image in order to make the edge contour image contain more defect structure information; specifically, performs pixel value expansion processing on the defect contour in the image to deepen and thicken the defect contour to make the defect contour more obvious.

[0018] As some optional implementations of the present application, the local linear model is expressed as:

[0019] q i =a k I i +b k

[0020] Among them, a k and b k represents the local window w of the local linear model kThe linear coefficient, q i Represents the pixels of the original image, I i Represents the pixels of the guidance image.

[0021] As some optional implementations of the present application, the process of performing image enhancement on the linear defect filtered image by using a local enhancement method to obtain a linear defect enhanced image is as follows:

[0022] Performing image segmentation on the linear defect filter image to obtain a plurality of linear defect filter sub-images;

[0023] Dynamically adjust the brightness or contrast of each pixel in the area based on the mean and variance information in the linear defect filtering sub-image area to obtain a number of linear defect enhanced sub-images;

[0024] The image merging process is performed on several linear defect enhanced sub-images to obtain a final linear defect enhanced image.

[0025] In the above embodiment, the present invention takes into account the missing of some weak linear defects after removing the noise, so it is necessary to locally enhance the extracted and denoised linear defects. Local enhancement is a flexible and effective image enhancement technology. By adjusting the statistical characteristics of the local area, the visual quality of the image can be significantly improved.

[0026] As some optional implementations of the present application, the process of extracting features from the linear defect enhanced image by edge detection to obtain the linear defect feature image is as follows:

[0027] Binarization is performed on the linear defect enhanced image to obtain a binary image of the linear defect enhanced image;

[0028] The edge contour extraction process is performed on the binary image of the linear defect enhanced image to obtain a linear defect feature image.

[0029] In the above embodiment, the present invention performs edge detection on the linear defect enhanced image after local enhancement, wherein the edge detection uses the Robinson edge detection algorithm to extract the edge. The Robinson edge detection algorithm can effectively detect the edges in various directions in the image, and compared with some simple edge detection algorithms, the Robinson edge detection has a certain ability to suppress image noise.

[0030] As some optional implementations of the present application, the process of performing feature connectivity verification on the linear defect feature image by defect directionality verification to obtain the linear defect detection result is as follows:

[0031] Acquire a plurality of defect sub-images from the linear defect feature image, and perform comprehensive verification on the distance and directionality of the defect based on the plurality of defect sub-images to obtain a comprehensive verification result between the defects;

[0032] Different defects are combined based on the comprehensive verification results between defects to obtain linear defect detection results.

[0033] In the above-mentioned embodiment, the present invention can correct slightly truncated linear defects by performing feature connectivity check on the linear defect feature image to prevent missed detection.

[0034] In a second aspect, the present invention provides a linear defect detection system, the system comprising:

[0035] A guided filtering unit, wherein the guided filtering unit performs direction denoising on the original image by using a guided filtering method to obtain a linear defect filtered image;

[0036] A local enhancement unit, wherein the local enhancement unit performs image enhancement on the linear defect filtered image in a local enhancement manner to obtain a linear defect enhanced image;

[0037] An edge detection unit, wherein the edge detection unit extracts features from the linear defect enhanced image by edge detection to obtain a linear defect feature image;

[0038] A directionality verification unit is used to perform feature connectivity verification on the linear defect feature image in a defect directionality verification manner to obtain a linear defect detection result.

[0039] 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 linear defect detection method.

[0040] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the linear defect detection method when executed by a processor.

[0041] The beneficial effects of the present invention are as follows: the present invention combines the linear characteristics of linear defects to first remove the noise of the original image itself by means of guided filtering, thereby restoring the true defect characteristics; secondly, data enhancement is performed on local linear defects, thereby facilitating subsequent extraction; then the Robinson defect detection method is used to extract linear defects, thereby highlighting the defects; finally, the slightly truncated linear defects are corrected in combination with the directionality and distance of the linear defects to prevent missed detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be 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 paying creative work.

[0043] Figure 1 is a schematic diagram of the computer device structure of the hardware operating environment described in the embodiment of the present invention;

[0044] Figure 2 is a flow chart of a linear defect detection method according to an embodiment of the present invention;

[0045] Figure 3 is a schematic diagram of an original image according to an embodiment of the present invention;

[0046] Figure 4 is a schematic diagram of a linear defect detection result according to an embodiment of the present invention;

[0047] Figure 5 It is a system block diagram of the linear defect detection system described in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] 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.

[0049] In order to solve the problem of missed detection and over-detection in linear defect detection of organic laser displays, the embodiment of the present invention provides a linear defect detection method, system, device and storage medium. 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.

[0050] See also Figure 1 , Figure 1 The figure is a schematic diagram of the computer device structure of the hardware operating environment involved in the embodiment of the present invention.

[0051] like Figure 1As 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 be a wired interface or 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.

[0052] 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.

[0053] 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.

[0054] exist Figure 1 In 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 linear defect detection system stored in the data storage module through the processor, and executes the linear defect detection method provided in the embodiment of the present application.

[0055] Based on the hardware environment of the aforementioned embodiment, the embodiment of the present application provides a linear defect detection method, see Figure 2 , Figure 2 The flowchart of the linear defect detection method is as follows:

[0056] (1) Directional denoising is performed on the original image using guided filtering to obtain a linear defect filtered image. Figure 3 , Figure 3 is a schematic diagram of the original image.

[0057] In the embodiment of the present invention, the process of performing directional denoising on the original image by using guided filtering is as follows:

[0058] (1.1) A guidance image is constructed based on the original image, and the guidance image and the original image are simultaneously input into the local linear model to obtain a linear relationship between the guidance image and the original image.

[0059] Among them, the process of building a guide image is as follows:

[0060] (1.11) The original image is subjected to binarization processing, edge contour extraction processing and pixel value expansion processing to obtain an edge contour image.

[0061] Among them, the binarization processing of the original image is to convert the original image into a binary image, the edge contour extraction processing of the binary image of the original image is to extract the defect contour in the image; the pixel value expansion processing of the defect contour in the image is to make the edge contour image contain more defect structure information; specifically, the pixel value expansion processing of the defect contour in the image is to deepen and thicken the defect contour to make the defect contour more obvious.

[0062] (1.12) The edge contour image and the original image are superimposed to obtain a guiding image.

[0063] The image superposition processing of the edge contour image and the original image is performed so as to make the guide image contain the image information of the original image while containing more defect structure information.

[0064] In the embodiment of the present invention, the local linear model is expressed as:

[0065] q i =a k I i +b k

[0066] Among them, a k and b k represents the local window w of the local linear model k The linear coefficient, q i represents the linear defect filtered image after directional denoising, I i Represents the pixels of the guidance image.

[0067] In the embodiment of the present invention, the local linear model is obtained by using the local window w k The energy function in solves the linear parameter a k and b k , where the energy function is expressed as:

[0068] E(a k ,b k )=∑ i ((a k Ii +b k -p i ) 2 +εa k 2 ), i∈w k

[0069] Among them, p i represents the pixels of the original image, and ε represents the pre-set local window w k The positive parameter of .

[0070] Specifically, solve the linear parameter a k and b k In the process, we can first solve b by the condition that the partial derivative is zero. k , and then solve for a k .

[0071] (1.2) Based on the linear relationship between the guide image and the original image, the original image is directionally denoised to obtain a linear defect filtered image.

[0072] Specifically, the directional denoising is to use the local window w where each pixel i is located. k The linear parameter a within k and b k Calculate the pixel value q of the output image i =a k I i +b k .

[0073] (2) The linear defect filtered image is enhanced by local enhancement to obtain a linear defect enhanced image.

[0074] In the embodiment of the present invention, after removing the noise, considering that some weak linear defects are missing, it is necessary to perform local enhancement on the extracted and denoised linear defects. Local enhancement is a flexible and effective image enhancement technology that can significantly improve the visual quality of the image by adjusting the statistical characteristics of the local area.

[0075] In the embodiment of the present invention, the process of performing image enhancement on the linear defect filter image by using the local enhancement method is as follows:

[0076] (2.1) Perform image segmentation on the linear defect filter image to obtain a number of linear defect filter sub-images.

[0077] (2.2) Based on the mean and variance information in the linear defect filtering sub-image area, the brightness or contrast of each pixel in the area is dynamically adjusted to obtain several linear defect enhanced sub-images.

[0078] (2.3) Perform image merging processing on several linear defect enhanced sub-images to obtain a final linear defect enhanced image.

[0079] In the embodiment of the present invention, the mean and variance respectively represent the brightness and contrast information of the image in the local area, and the enhancement coefficient can be determined according to the size of the local variance. Generally speaking, the larger the local variance, the higher the contrast of the local area and the richer the details, so the enhancement coefficient can be set to a smaller value to avoid distortion caused by over-enhancement. On the contrary, the smaller the local variance, the lower the contrast of the local area and the more blurred the details, and a larger enhancement coefficient is needed to enhance the contrast.

[0080] (3) The edge detection method is used to extract features of the linear defect enhanced image to obtain a linear defect feature image.

[0081] In the embodiment of the present invention, the process of extracting features from the linear defect enhanced image by edge detection is as follows:

[0082] (3.1) The linear defect enhanced image is binarized to obtain a binarized image of the linear defect enhanced image.

[0083] (3.2) Perform edge contour extraction on the binary image of the linear defect enhanced image to obtain a linear defect feature image.

[0084] In the embodiment of the present invention, edge detection is performed on the linear defect enhanced image after local enhancement, wherein the edge detection uses the Robinson edge detection algorithm for edge extraction. The Robinson edge detection algorithm can effectively detect edges in various directions in the image, and compared with some simple edge detection algorithms, the Robinson edge detection has a certain ability to suppress image noise.

[0085] (4) Use defect directionality verification to perform feature connectivity verification on the linear defect feature image to obtain the linear defect detection result. Please refer to Figure 4 , Figure 4 It is a schematic diagram of the linear defect detection result.

[0086] In an embodiment of the present invention, the process of performing feature connectivity verification on a linear defect feature image by using defect directionality verification is as follows:

[0087] (4.1) A plurality of defect sub-images are obtained from the linear defect feature image, and the distance and directionality of the defects are comprehensively verified based on the plurality of defect sub-images to obtain a comprehensive verification result between the defects.

[0088] (4.2) Different defects are combined based on the comprehensive verification results between defects to obtain linear defect detection results.

[0089] Specifically, the overall directionality of each defect and the connectivity between any two defects are obtained according to the coordinate information of each defect sub-image.

[0090] ① If the directional difference between any two defects is within the threshold range, and the distance between the two defects is also within the threshold range, the two defects are connected; conversely, if the directional difference between any two defects is within the threshold range, but the distance between the two defects is not within the threshold range, the length of the corresponding defect is obtained according to the coordinate information of the corresponding sub-defect sub-image. If the length of the defect is greater than the threshold, the defect is retained, otherwise, the defect is removed.

[0091] ② If the directional difference between any two defects is not within the threshold range, but the distance between the two defects is within the threshold range, the two defects will be connected; in contrast, if the directional difference between any two defects is not within the threshold range, and the distance between the two defects is also not within the threshold range, the two defects will not be processed separately.

[0092] In the embodiment of the present invention, slight truncated linear defects can be corrected by performing feature connectivity check on the linear defect feature image to prevent missed detection.

[0093] In summary, the present invention combines the linear characteristics of linear defects. First, the noise of the original image itself is removed by guided filtering to restore the true defect characteristics. Secondly, data enhancement is performed on local linear defects to facilitate subsequent extraction. Thirdly, the Robinson defect detection method is used to extract linear defects to highlight the defects. Finally, the directionality and distance of the linear defects are combined to correct slight truncated linear defects to prevent missed detection.

[0094] In addition, in one embodiment, based on the same inventive concept as the above embodiment, the embodiment of the present invention provides a linear defect detection system. The system corresponds to the method of embodiment 1 one by one, please refer to Figure 5 , Figure 5 is a system block diagram of the linear defect detection system, the system comprising:

[0095] The guided filtering unit performs directionality denoising on the original image by using a guided filtering method to obtain a linear defect filtered image.

[0096] A local enhancement unit is used to enhance the linear defect filtered image in a local enhancement manner to obtain a linear defect enhanced image.

[0097] An edge detection unit is used to extract features from the linear defect enhanced image by edge detection to obtain a linear defect feature image.

[0098] A directionality verification unit is used to perform feature connectivity verification on the linear defect feature image in a defect directionality verification manner to obtain a linear defect detection result.

[0099] It should be noted that each unit in the linear defect detection system in this embodiment corresponds one-to-one to each step in the linear defect detection method in the aforementioned embodiment. Therefore, the specific implementation method and technical effects achieved by this embodiment can refer to the implementation method of the aforementioned linear defect detection method, which will not be repeated here.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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).

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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 linear defect detection method, characterized in that: The method comprises the following steps: The original image is denoised in a direction by using guided filtering to obtain a linear defect filtered image. The linear defect filter image is enhanced by using a local enhancement method to obtain a linear defect enhanced image; The edge detection method is used to extract the features of the linear defect enhanced image to obtain the linear defect feature image; The defect directionality verification method is used to perform feature connectivity verification on the linear defect feature image to obtain the linear defect detection result.

2. A linear defect detection method according to claim 1, characterized in that: The process of using guided filtering to perform direction denoising on the original image to obtain a linear defect filtered image is as follows: A guide image is constructed based on the original image, and the guide image and the original image are simultaneously input into a local linear model to obtain a linear relationship between the guide image and the original image; Based on the linear relationship between the guide image and the original image, the original image is directionally denoised to obtain a linear defect filtered image.

3. A linear defect detection method according to claim 2, characterized in that: The process of constructing a guided image based on the original image is as follows: The original image is subjected to binarization processing, edge contour extraction processing and pixel value expansion processing to obtain an edge contour image; The edge contour image and the original image are superimposed to obtain a guiding image.

4. A linear defect detection method according to claim 2 or 3, characterized in that: The local linear model is expressed as: q i =a k I i +b k Among them, a k and b k represents the local window w of the local linear model k The linear coefficient, q i Represents the pixels of the original image, I i Represents the pixels of the guidance image.

5. A linear defect detection method according to claim 1, characterized in that: The process of enhancing the linear defect filtered image by local enhancement to obtain the linear defect enhanced image is as follows: Performing image segmentation on the linear defect filter image to obtain a plurality of linear defect filter sub-images; Dynamically adjust the brightness or contrast of each pixel in the area based on the mean and variance information in the linear defect filtering sub-image area to obtain a number of linear defect enhanced sub-images; The image merging process is performed on several linear defect enhanced sub-images to obtain a final linear defect enhanced image.

6. A linear defect detection method according to claim 1, characterized in that: The process of extracting features from the linear defect enhanced image by edge detection to obtain the linear defect feature image is as follows: Binarizing the linear defect enhanced image to obtain a binary image of the linear defect enhanced image; The edge contour extraction process is performed on the binary image of the linear defect enhanced image to obtain a linear defect feature image.

7. A linear defect detection method according to claim 1, characterized in that: The defect directionality check method is used to check the feature connectivity of the linear defect feature image to obtain the linear defect detection result. The process is as follows: Acquire a plurality of defect sub-images from the linear defect feature image, and perform comprehensive verification on the distance and directionality of the defect based on the plurality of defect sub-images to obtain a comprehensive verification result between the defects; Different defects are combined based on the comprehensive verification results between defects to obtain linear defect detection results.

8. A linear defect detection system, characterized in that: The system comprises: A guided filtering unit, wherein the guided filtering unit performs direction denoising on the original image by using a guided filtering method to obtain a linear defect filtered image; A local enhancement unit, wherein the local enhancement unit performs image enhancement on the linear defect filtered image in a local enhancement manner to obtain a linear defect enhanced image; An edge detection unit, wherein the edge detection unit extracts features from the linear defect enhanced image by edge detection to obtain a linear defect feature image; A directionality verification unit is used to perform feature connectivity verification on the linear defect feature image in a defect directionality verification manner to obtain a linear defect detection result.

9. 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 linear defect detection method as described in any one of claims 1 to 7 is implemented.

10. 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 linear defect detection method described in any one of claims 1 to 7 is implemented.