Text image defect detection method, computer device and storage medium

Abstract

The application provides a character image defect detection method, a computer device and a storage medium, wherein the method comprises the following steps: acquiring a non-defect image and a to-be-detected image; acquiring a first image and a second image of the non-defect image; obtaining a third image according to the second image and the first image; obtaining a fourth image according to the second image and the to-be-detected image; obtaining a fifth image based on the third image and the second image; obtaining a sixth image based on the third image and the fourth image; obtaining a seventh image according to the fifth image and the sixth image; obtaining a defect value of the fourth image according to the third image and the seventh image; and determining a detection result of the fourth image based on the defect value of the fourth image. The application can assist in character image defect detection and improve the detection accuracy.

Description

Technical Field

[0001] This application relates to the field of text image defect detection, and more particularly to a text image defect detection method, computer device, and storage medium. Background Technology

[0002] Currently, the printing industry mostly uses traditional automated optical inspection methods to inspect printed text. These methods, which employ region-of-interest (ROI) technology to compare regions within an image, lack limitations on the comparison area and are prone to overscanning due to subtle changes in light source. This necessitates significant manpower for re-inspection, wasting human resources and time. Furthermore, manual inspection is susceptible to errors due to limitations in human eyesight and attention, and inconsistent standards among inspectors further reduce accuracy. Summary of the Invention

[0003] In view of the above, it is necessary to provide a method, computer device and storage medium for detecting text image defects, which can assist in the detection of text image defects and improve the accuracy of text image defect detection.

[0004] The text image defect detection method includes: acquiring a flawless image and an image to be detected; performing a first image processing on the flawless image to obtain a first image of the flawless image; performing a second image processing on the flawless image to obtain a second image of each character in the flawless image; obtaining a third image of each character from the first image based on the second image of each character; obtaining a fourth image of each character from the image to be detected based on the second image of each character; establishing a correlation between the second image, third image, and fourth image of each character; performing a third image processing on the second image of any character based on the third image of any character to obtain a fifth image of any character; performing the third image processing on the fourth image of any character based on the third image of any character to obtain a sixth image of any character; obtaining a seventh image of any character based on the fifth and sixth images of any character; obtaining a defect value of the fourth image of any character based on the third and seventh images of any character; and determining the detection result of the fourth image of any character in the image to be detected based on the defect value of the fourth image of any character and a preset threshold.

[0005] Optionally, the method further includes: before performing the first image processing on the flawless image, locating each character in the flawless image to obtain the position information of each character in the flawless image.

[0006] Optionally, the first image processing of the flawless image to obtain the first image of the flawless image includes: obtaining a mask image of the flawless image based on the position information of each character in the flawless image; and using the mask image as the first image of the flawless image.

[0007] Optionally, the second image processing includes: segmenting each character in the flawless image based on the position information of each character in the flawless image.

[0008] Optionally, obtaining a third image of each character from the first image based on the second image of each character; and obtaining a fourth image of each character from the image to be detected based on the second image of each character includes: using a template matching method, taking the second image of each character as a target image, identifying the target image in the first image, and obtaining a third image of each character in the first image that matches the second image of each character in the flawless image; and using the template matching method, taking the second image of each character as a target image, identifying the target image in the image to be detected, and obtaining a fourth image of each character in the image to be detected that matches the second image of each character in the flawless image.

[0009] Optionally, the third image processing includes: using the third image of any character to remove the background outside the character outline in the second image of any character and the background outside the character outline in the fourth image of any character; and / or using the third image of any character to remove the character outline in the second image of any character and the character outline in the fourth image of any character.

[0010] Optionally, obtaining the seventh image of any character based on the fifth and sixth images of any character includes: using a structural similarity algorithm to obtain a difference image between the fifth and sixth images of any character, and using the difference image as the seventh image of any character.

[0011] Optionally, obtaining the defect value of the fourth image of any character based on the third and seventh images of any character; and determining the detection result of the fourth image of any character in the image to be detected based on the defect value of the fourth image of any character and a preset threshold includes: calculating the ratio between the area of ​​a preset pixel value in the seventh image of any character and the area of ​​the preset pixel value in the third image of any character, and using the ratio as the defect value of the fourth image of any character; comparing the defect value of the fourth image of any character with the preset threshold; determining that the fourth image of any character is a defective image when the defect value of the fourth image of any character is greater than or equal to the preset threshold; and determining that the fourth image of any character is a flawless image when the defect value of the fourth image of any character is less than the preset threshold.

[0012] The computer-readable storage medium stores at least one instruction, which, when executed by a processor, implements the text image defect detection method.

[0013] The computer device includes a memory and at least one processor. The memory stores at least one instruction, which, when executed by the at least one processor, implements the text image defect detection method.

[0014] Compared with existing technologies, the text image defect detection method, computer device and storage medium can reduce the over-detection rate of image preprocessing, distinguish between text outlines and background areas in text images, and determine the defect detection results of the image in the area where the text is located by detecting the text outlines and background areas, thereby improving the efficiency and accuracy of defect detection. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application 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 embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0016] Figure 1 This is a flowchart of the text image defect detection method provided in the embodiments of this application.

[0017] Figure 2 This is an architectural diagram of the computer device provided in the embodiments of this application.

[0018] Figure 3 This is an example diagram illustrating the steps related to background removal provided in the embodiments of this application.

[0019] Figure 4 This is an example diagram illustrating the steps involved in removing text outlines as provided in the embodiments of this application.

[0020] Figure 5 This is an example image of the seventh image obtained by removing the background, as provided in an embodiment of this application.

[0021] Figure 6 This is an example image of the seventh image obtained by removing text outlines, as provided in an embodiment of this application.

[0022] Figure 7 This is a flowchart of step S7 provided in the embodiments of this application.

[0023] Explanation of main component symbols

[0024] Defect detection system 30 memory 31 processor 32

[0025] The following detailed description, in conjunction with the accompanying drawings, will further illustrate this application. Detailed Implementation

[0026] To better understand the above-mentioned objectives, features, and advantages of this application, the application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0027] Numerous specific details are set forth in the following description to provide a thorough understanding of this application. The described embodiments are merely some, not all, of the embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0029] See Figure 1 The diagram shown is a flowchart of a text image defect detection method according to a preferred embodiment of this application.

[0030] In this embodiment, the text image defect detection method can be applied to a computer device (e.g., Figure 2In the computer device 3) shown, for computer devices that need to perform text image defect detection, the function for text image defect detection provided by the method of this application can be directly integrated into the computer device, or it can be run on the computer device in the form of a software development kit (SDK).

[0031] like Figure 1 As shown, the text image defect detection method specifically includes the following steps. Depending on different needs, the order of the steps in this flowchart can be changed, and some steps can be omitted.

[0032] Step S1: The computer device acquires a flawless image and an image to be inspected, performs a first image processing on the flawless image, and obtains a first image of the flawless image.

[0033] In one embodiment, the computer device can acquire a flawless image in response to user input. The flawless image may also be pre-stored in the computer device's memory or in another device communicatively connected to the computer device. In this embodiment, the flawless image may be a standard sample (Golden Sample) image of a printed product produced in a factory, containing text (e.g., Japanese characters, kanji, numbers, English letters, etc.). It should be noted that the position of the standard sample image does not need to be corrected, nor does the orientation of the text. The image to be inspected may be an image captured from the printed product to be inspected. The size of the image to be inspected is the same as the size of the flawless image.

[0034] In one embodiment, before performing the first image processing on the flawless image, the computer device first locates each character in the flawless image to obtain the position information of each character in the flawless image.

[0035] In one embodiment, a computer device can use Optical Character Recognition (OCR) technology to recognize the text in the flawless image, thereby identifying the text area and background area of ​​the flawless image, and determining the position of each character in the text area. The text area refers to the region containing text, which the computer device can delineate using Region of Interest (ROI) technology; the background area refers to the region that does not contain text, i.e., the area outside the text area in the flawless image.

[0036] In one embodiment, performing a first image processing on the flawless image to obtain a first image of the flawless image includes: using ROI technology to obtain a mask image of the flawless image based on the position information of each character in the flawless image; and using the mask image as the first image of the flawless image.

[0037] In one embodiment, the mask image includes: a mask image for masking a background area in the flawless image, the mask image being designated as a first background image; and a mask image for masking the outline of text in the flawless image, the mask image being designated as a first text image.

[0038] In one embodiment, the first background image is a binary image. The pixel value of the background area in the first background image is 0, and the pixel value of the text outline in the first background image is 255.

[0039] In one embodiment, the first text image is a binary image. The pixel value of the background area in the first text image is 255, and the pixel value of the text outline in the first text image is 0.

[0040] In this embodiment, the mask image is used as the first image of the flawless image, and the first image includes the first background image and the first text image.

[0041] It should be noted that in actual operation, only the first background image can be obtained and the first background image can be used for subsequent detection. In that case, the detection result obtained in step S7 will be the detection result of the text outline defects in the fourth image.

[0042] In practice, it is also possible to acquire only the first text image and use the first text image for subsequent detection. In this case, the detection result obtained in step S7 is the detection result of the background area defects in the fourth image.

[0043] In practice, the first background image and the first text image can be acquired simultaneously for subsequent detection. In this case, the detection results obtained in step S7 include the detection results of text outline defects in the fourth image and the detection results of background defects in the fourth image. This will not be elaborated further hereafter.

[0044] Step S2: The computer device performs a second image processing on the flawless image to obtain a second image of each character in the flawless image.

[0045] In one embodiment, the second image processing includes: segmenting each character in the flawless image based on the positional information of each character in the flawless image. A computer device can use the character segmentation function of OCR software to segment the text area, separating the region containing each character to obtain a first image of each character, wherein the first image of each character contains an image of the complete character outline. For example, each character in the flawless image can be segmented in the form of a rectangular bounding box to obtain a second image of a single character, such as... Figure 3 The second image G1 shown Figure 4 The second image G2 is shown.

[0046] In step S3, the computer device obtains a third image of each character from the first image based on the second image of each character; and obtains a fourth image of each character from the image to be detected based on the second image of each character, and establishes an association between the second image, the third image and the fourth image of each character.

[0047] In one embodiment, the computer device uses a feature matching method to identify the target image in the first image, using the second image of each character as the target image, and extracts the identified target image from the image to be detected, thereby obtaining a third image of each character in the first image that matches the second image of each character in the flawless image.

[0048] It should be noted that, since in this embodiment, the first image is the mask image used to mask the background area in the flawless image (i.e., the first background image) and / or the mask image used to mask the text outlines in the flawless image (i.e., the first text image), the third image for each text also includes the mask image used to mask the background area in the flawless image (hereinafter referred to as the third background image for clarity) and / or the mask image used to mask the text outlines in the flawless image (hereinafter referred to as the third text image). That is, the third image obtained from the first background image is denoted as the third background image for each text; and the third image obtained from the first text image is denoted as the third text image for each text. Similarly, the third background image is a binary image, with the pixel value of the background area in the third background image being 0, and the pixel value of the text outlines in the third background image being 255. The third text image is a binary image, wherein the pixel value of the background area in the third text image is 255, and the pixel value of the text outlines in the third text image is 0.

[0049] Using the template matching method, the second image of each character is taken as the target image, the target image is identified in the image to be detected, and the identified target image is extracted from the image to be detected, thereby obtaining the fourth image of each character in the image to be detected that matches the second image of each character in the flawless image.

[0050] For example Figure 3 As shown, the third background image M1 and the fourth image T1 are obtained based on the second image G1; for example... Figure 4 As shown, the third text image M2 and the fourth image T2 are obtained based on the second image G2; for example... Figure 5 As shown, the obtained third background image M3.

[0051] It should be noted that since each character has a unique second image in step S2, a one-to-one correspondence is established between the second image and the third image of each character, and the second and third images of each character are the same size. Similarly, a one-to-one correspondence is established between the second image and the fourth image of each character, and the second and fourth images of each character are the same size. Therefore, using the second image of each character as the relationship node, a one-to-one correspondence is also established between the third and fourth images of each character, and the third and fourth images of each character are the same size. In summary, a one-to-one correspondence is established between any two of the second, third, and fourth images of each character, and all three images are the same size.

[0052] In step S4, the computer device performs third image processing on the second image of any character based on the third image of any character to obtain a fifth image of any character; and performs the third image processing on the fourth image of any character based on the third image of any character to obtain a sixth image of any character.

[0053] In one embodiment, the third image processing includes: using a third background image in a third image of any character to remove the background outside the character outline in a second image of any character and the background outside the character outline in a fourth image of any character, the removal including masking; and / or using a third character image in a third image of any character to remove the character outline in a second image of any character and the character outline in a fourth image of any character, the removal including masking.

[0054] For example, for instance Figure 3As shown, the fifth image GM1 is obtained by masking the second image G1 with the third background image M1, and the sixth image TM1 is obtained by masking the fourth image T1 with the third background image M1. For example... Figure 4 As shown, the fifth image GM2 is obtained by masking the second image G2 with the third text image M2, and the sixth image TM2 is obtained by masking the fourth image T2 with the third text image M2; for example... Figure 5 As shown, the fifth image GM3 and the sixth image TM3 are obtained using the third background image M3.

[0055] Step S5: The computer device obtains a seventh image of any character based on the fifth and sixth images of the character.

[0056] In one embodiment, a computer device uses a Structural Similarity (SSIM) algorithm to obtain a difference image between a fifth and a sixth image of any given character, and uses this difference image as a seventh image of the given character. The seventh image of the given character is a binary image, wherein the pixel value of the background area in the seventh image of the given character is 0, and the pixel value of the character outline in the seventh image of the given character is 255. For example, the computer device can obtain the seventh image of the given character using the SSIM algorithm by installing software such as Python, OpenCV, scikit-image, and imutils.

[0057] For example, for instance Figure 5 As shown, the seventh image D1 is obtained based on the fifth image GM3 and the sixth image TM3; for example... Figure 6 As shown, the seventh image D2 is obtained based on the fifth image GM2 and the sixth image TM2.

[0058] Step S6: The computer device obtains the defect value of the fourth image of any character based on the third and seventh images of any character.

[0059] In one embodiment, the computer device calculates the ratio between the area of ​​a preset pixel value (e.g., 255) in a seventh image of any character and the area of ​​the preset pixel value in a third image of any character, and uses this ratio as a defect value for a fourth image of any character. The computer device first calculates the proportion 'a' of the area of ​​white pixels with a pixel value of 255 in the seventh image of any character, then calculates the proportion 'b' of the area of ​​white pixels with a pixel value of 255 in the third image of any character, and finally calculates the ratio 'c' of proportion 'a' and proportion 'b', using this ratio 'c' as the defect value for the fourth image of any character.

[0060] For example Figure 5 In the image, the defect value obtained from the seventh image D1 and the third background image M3 is 0.17; for example... Figure 6 In the image, the defect value obtained from the seventh image D2 and the third text image M2 is 0.078.

[0061] Step S7: The computer device determines the detection result of the fourth image of any character in the image to be detected based on the defect value of the fourth image of any character and a preset threshold.

[0062] In one embodiment, the preset threshold can be 0.02, and the specific flowchart of step S7 is as follows: Figure 7 As shown, the details are as follows.

[0063] In step S70, the computer device compares the defect value of the fourth image of any character with the preset threshold; when the defect value of the fourth image of any character is greater than or equal to the preset threshold, step S71 is executed; and when the defect value of the fourth image of any character is less than the preset threshold, step S72 is executed.

[0064] In step S71, the computer device determines that the fourth image of any of the characters is a flawed image.

[0065] For example Figure 6 In the analysis, the defect value obtained from the seventh image D2 and the third text image M2 is 0.078, which is greater than the preset threshold of 0.02, thus confirming that... Figure 4 The fourth image T2 in the image to be detected is a flawed image.

[0066] In step S72, the computer device determines that the fourth image of any one of the characters is a flawless image.

[0067] The above Figure 1 This application details the text and image defect detection method, which is described below in conjunction with... Figure 2 The hardware architecture for implementing the text image defect detection method is described below.

[0068] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0069] See Figure 2 The diagram shown is a structural schematic of a computer device provided in a preferred embodiment of this application. In this preferred embodiment, the computer device 3 includes a memory 31 and at least one processor 32. Those skilled in the art should understand that... Figure 2The structure of the computer device shown does not constitute a limitation of the embodiments of this application. It can be a bus structure or a star structure. The computer device 3 may also include more or fewer other hardware or software than shown, or different component arrangements.

[0070] In some embodiments, the computer device 3 includes a terminal capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, the hardware of which includes, but is not limited to, microprocessors, application-specific integrated circuits, programmable gate arrays, digital processors, and embedded devices.

[0071] It should be noted that the computer device 3 described is merely an example. Other existing or future electronic products that are suitable for this application should also be included within the scope of protection of this application and are incorporated herein by reference.

[0072] In some embodiments, the memory 31 is used to store program code and various data. For example, the memory 31 can be used to store flawless images, and can also store a defect detection system 30 installed in the computer device 3, enabling high-speed and automatic access to programs or data during the operation of the computer device 3. The memory 31 includes read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable storage medium capable of carrying or storing data.

[0073] In some embodiments, the at least one processor 32 may be composed of integrated circuits, such as a single-packaged integrated circuit or multiple integrated circuits packaged with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The at least one processor 32 is the control unit of the computer device 3, connecting various components of the computer device 3 via various interfaces and lines. It executes programs or modules stored in the memory 31 and calls data stored in the memory 31 to perform various functions of the computer device 3 and process data, such as performing text and image defect detection.

[0074] In some embodiments, the defect detection system 30 operates in a computer device 3. The defect detection system 30 may include multiple functional modules composed of program code segments. The program code of each program segment in the defect detection system 30 may be stored in the memory 31 of the computer device 3 and executed by at least one processor 32 to achieve... Figure 1 The text image defect detection function shown.

[0075] In this embodiment, the defect detection system 30 can be divided into multiple functional modules according to the functions it performs. A module, as referred to in this application, is a series of computer program segments that can be executed by at least one processor and perform a fixed function, and is stored in memory.

[0076] Although not shown, the computer device 3 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 32 via a power management device, thereby enabling functions such as charging, discharging, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The computer device 3 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0077] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0078] The integrated unit implemented as a software functional module described above can be stored in a computer-readable storage medium. This software functional module, stored in a storage medium, includes several instructions to cause a computer device (which may be a server, personal computer, etc.) or processor to execute portions of the methods described in the various embodiments of this application.

[0079] In a further embodiment, combined with Figure 2 The at least one processor 32 can execute the operating system of the computer device 3 and various installed applications (such as the defect detection system 30), program code, etc., for example, the various modules mentioned above.

[0080] The memory 31 stores program code, and the at least one processor 32 can call the program code stored in the memory 31 to execute related functions. The program code stored in the memory 31 can be executed by the at least one processor 32 to realize the functions of each module to achieve the purpose of text and image defect detection.

[0081] In one embodiment of this application, the memory 31 stores one or more instructions (i.e., at least one instruction), which are executed by the at least one processor 32 to implement... Figure 1 The purpose of the text image defect detection shown is to detect defects.

[0082] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0083] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0084] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0085] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within this application. No reference numerals in the claims should be construed as limiting the scope of the claims. Furthermore, it is clear that the word "comprising" does not exclude other elements or, and the singular does not exclude the plural. Multiple elements or devices recited in the apparatus claims may also be implemented by a single element or device in software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any particular order.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to the above preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.

Claims

1. A method for detecting defects in text images, characterized in that, The method includes: Acquire a flawless image and an image to be detected, locate each character in the flawless image, and obtain the position information of each character in the flawless image; Based on the position information of each character in the flawless image, a mask image of the flawless image is obtained; the mask image is used as the first image of the flawless image. Based on the position information of each character in the flawless image, each character in the flawless image is segmented to obtain a second image of each character in the flawless image; Using a template matching method, the second image of each character is taken as the target image, and the target image is identified in the first image to obtain a third image of each character in the first image that matches the second image of each character in the flawless image; and Using the template matching method, the second image of each character is taken as the target image, and the target image is identified in the image to be detected to obtain the fourth image of each character in the image to be detected that matches the second image of each character in the flawless image. Establish a connection between the second, third, and fourth images of each character; Based on the third image of any character, remove the background outside the character outline in the second image of that character to obtain a fifth image of that character; and Based on the third image of any one of the characters, remove the background outside the character outline in the fourth image of any one of the characters to obtain the sixth image of any one of the characters; Using a structural similarity algorithm, the difference image between the fifth and sixth images of any given character is obtained, and the difference image is used as the seventh image of any given character. Calculate the ratio between the area of ​​a preset pixel value in the seventh image of any character and the area of ​​the preset pixel value in the third image of any character, and use the ratio as the defect value of the fourth image of any character; and Based on the defect value of the fourth image of any character and a preset threshold, the detection result of the fourth image of any character in the image to be detected is determined.

2. The text image defect detection method according to claim 1, characterized in that, The method for obtaining the fifth image further includes: using the third image of any character, removing the character outline from the second image of any character to obtain the fifth image of any character; The method for obtaining the sixth image further includes: using the third image of any character, removing the character outline from the fourth image of any character to obtain the sixth image of any character.

3. The text image defect detection method according to claim 1, characterized in that, The determination of the detection result of the fourth image of any character in the image to be detected, based on the defect value of the fourth image of any character and a preset threshold, includes: Compare the defect value of the fourth image of any given character with the preset threshold; When the defect value of the fourth image of any character is greater than or equal to the preset threshold, the fourth image of any character is determined to be a defective image; and When the defect value of the fourth image of any character is less than the preset threshold, the fourth image of any character is determined to be a defect-free image.

4. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, which, when executed by a processor, implements the text image defect detection method as described in any one of claims 1 to 3.

5. A computer device, characterized in that, The computer device includes a memory and at least one processor, wherein the memory stores at least one instruction, which, when executed by the at least one processor, implements the text image defect detection method as described in any one of claims 1 to 3.

Images