TW202307729A - Image processing method, computer device, and storage medium - Google Patents

Abstract

The present application provides an image processing method, a computer device, and a storage medium. The image processing method includes: determining a text area and a background area of a flawless image to obtain a first image of each text; removing the background area from the first image to obtain a second image; processing the second image to obtain a third image, N fourth images, and N fifth images corresponding to the fourth image one-to-one; calculating a similarity value between each fifth image and the corresponding third image, and determining a defect threshold; determining whether the fourth image corresponding to the fifth image is a defective image; when the fourth image is a flawed image, performing a shading processing on an intercepted background image, and synthesizing the flawed image and the intercepted background image after the shading processing, and obtaining a composite image. This application can assist in generating flawed training samples and reduce labor costs.

Description

Image processing method, computer device and storage medium

The invention relates to the field of image processing, in particular to an image processing method, a computer device and a storage medium.

Due to the high yield rate in the current industrial production process, it is difficult to obtain a large number of defective printing image samples, which are used as training samples to train the defect detection model. The existing method of artificially synthesizing flawed samples requires manually marking the flawed data after generating the simulated data, or training another deep learning model to classify, which consumes a lot of manpower and time, and manual marking Errors and omissions are also prone to occur in the process. How to efficiently solve the problem of insufficient training data on the premise of ensuring accuracy has always been a major issue in the application of deep learning.

In view of the above, it is necessary to provide an image processing method, a computer device and a storage medium, which can automatically generate a large number of defective printed images and reduce the cost of manual synthesis and marking.

The image processing method includes: acquiring a flawless image, determining a character area and a background area of the flawless image, and determining the position of each character in the character area; Segment the text area to obtain the first image of each text; remove the background from the first image of each text to obtain the second image of each text; process according to the preset first image processing method The second image of each character is obtained by obtaining the third image of each character; the second image of each character is processed according to the preset second image processing method to obtain N pieces of the first image of each character Four images and N fifth images, the N fourth images of each character are in one-to-one correspondence with the N fifth images, and N is a positive integer greater than 1; calculate each character The similarity measures between each fifth image in the N fifth images and the third image of each character are obtained, and N similarity measures corresponding to each character are obtained, and each character N pieces of the fifth image are respectively associated with the N similarity measures corresponding to each character, and a flaw threshold is determined according to the N similarity measures corresponding to all characters in the character area; compare the corresponding The size of each similarity measure in the N similarity measures and the defect threshold, wherein, when any similarity measure corresponding to any text is greater than the defect threshold, it is determined to be associated with the arbitrary similarity measure The fourth image corresponding to the fifth image is a flawed image; when any one of the fourth images is determined to be a flawed image, a background image is intercepted from the background area, and the interception The size of the background image is equal to the size of the flawed image; and performing shading processing on the intercepted background image, synthesizing the flawed image and the background image after shading processing to obtain composite image.

Optionally, the first image processing method includes image binarization and contour extraction; the second image processing method includes erasure processing, image binarization, and contour extraction.

Optionally, removing the background from the first image of each character, and obtaining the second image of each character includes Method 1: using the Otsu algorithm to determine the first threshold of the first image, according to The first threshold obtains a mask of the first image, and performs a bitwise AND operation on the mask and the first image to obtain a foreground text image of the first image; and The second image is obtained by performing softening and edge processing on the foreground character image by using a Gaussian blur technique.

Optionally, removing the background from the first image of each character, and obtaining the second image of each character includes method two: using Fourier transform to remove the dots in the first image, and performing binarization on the first image after removing the dots; and performing edge softening processing on the binarized first image by using a Gaussian blur technique to obtain the second image.

Optionally, the first image processing method and the second image processing method perform image binarization according to the first threshold, and use Fourier descriptor algorithm or invariant moment algorithm to perform contour extraction .

Optionally, the second image of each character is processed according to the preset second image processing method to obtain N fourth images and N fifth images of each character, and each The N fourth images of the characters are in one-to-one correspondence with the N fifth images, including: performing N times of random erasing on the second images of each character to obtain N fourth images of each character. image; performing image binarization on the N fourth images of each character to obtain N black and white images; performing contour extraction on the N black and white images to obtain the N fifth images picture.

Optionally, the similarity measure refers to the Euclidean distance between each fifth image of each character and the third image of each character; wherein, according to the character region Determining a blemish threshold for N similarity measures corresponding to all the characters respectively includes: according to the number of images of the fifth image corresponding to each value of the similarity measure, making the similarity measure and the a line relationship diagram of the number of images; and using the first local minimum value of the similarity measure in the line relationship diagram as the blemish threshold.

Optionally, performing shading processing on the intercepted background image, synthesizing the flawed image and the background image after shading processing, and obtaining a composite image includes: performing the shading processing on the intercepted background image Adjusting the brightness and darkness of the image multiple times to obtain multiple adjusted images, and synthesizing the multiple adjusted images with the defective image respectively to obtain multiple composite images.

The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the image processing method is realized.

The computer device includes a memory and at least one processor, the memory stores at least one instruction, and the at least one instruction implements the image processing method when executed by the at least one processor.

Compared with the conventional technology, the image processing method, computer device and storage medium can automatically generate a large number of defective printed images, and can automatically mark the training samples without training an additional deep learning model, reducing the The cost of artificial synthesis and labelling.

In order to more clearly understand the above objects, features and advantages of the present application, the present application will be described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

A lot of specific details are set forth in the following description to facilitate a full understanding of the application, and the described embodiments are only a part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs. The terms used herein in the specification of the application are only for the purpose of describing specific embodiments, and are not intended to limit the application.

Referring to FIG. 1 , it is a flowchart of an image processing method in a preferred embodiment of the present application.

In this embodiment, the image processing method can be applied to a computer device (such as the computer device 3 shown in FIG. 2 ). For a computer device that needs to perform image processing, the computer device can directly integrate the method described in this application. The functions provided for image processing, or run on a computer device in the form of a software development kit (Software Development Kit, SDK).

As shown in FIG. 1 , the image processing method specifically includes the following steps. According to different requirements, the order of the steps in the flow chart can be changed, and some steps can be omitted.

Step S1, the computer device acquires a flawless image, determines the text area and the background area of the flawless image, and determines the position of each character in the text area.

In one embodiment, the computerized device may capture a flawless image in response to user input. The flawless image can also be pre-stored in the storage of the computer device, or in other devices connected in communication with the computer device. In this embodiment, the defect-free image may be a standard sample (Golden Sample) image of a printed matter produced by a factory, and the defect-free image includes text (for example, Chinese characters, numbers, English letters, etc.). It should be noted that the position of the standard sample image does not need to be corrected, and the arrangement direction of the characters also does not need to be corrected.

In one embodiment, the computer device can use Optical Character Recognition (Optical Character Recognition, OCR) technology to recognize the text of the flawless image, and then confirm the text area and the background area of the flawless image, and determine the Describe the position of each text in the text area. The text area refers to the area containing the text, and the computer device can use the region of interest (Region Of Interest, ROI) technology to outline the text area, such as shown in Figure 3, along the direction of the text arrangement with the surrounding large rectangles The frame (solid line) encloses all the text in it, and frames the text area. It should be noted that the dotted frame around the large rectangular frame in Fig. 3 is only used to indicate the large rectangular frame; the background area is Refers to the area that does not contain text, that is, the area outside the text area in the flawless image, such as the shaded area shown in FIG. 3 .

Step S2, the computer device divides the character area according to the position of each character, and obtains the first image of each character.

In one embodiment, the computer device can use the character cutting function of the OCR software to segment the text area, segment the area where each text is located, and obtain the first image of each text, and the text of each text. The first image contains an image of the full text outline of the text. For example, the large rectangular frame (solid line) in Figure 3 can be segmented, and the rectangular image of the area where the text "0" is located can be segmented according to the small rectangular frame (solid line) in Figure 3, as shown in Figure 4 In the first image 3B1 of the text "0" shown in , it should be noted that the dotted frame around the small rectangular frame in FIG. 3 is only used to indicate the small rectangular frame.

In step S3, the computer device removes the background from the first image of each character to obtain a second image of each character.

In one embodiment, removing the background from the first image of each character, and obtaining the second image of each character includes Method 1: a computer device uses Otsu algorithm (OTSU Thresholding) to determine the first The first threshold of the image, obtaining the mask (mask) of the first image according to the first threshold, and performing a bitwise AND (Bitwise AND) operation on the mask and the first image , obtaining a foreground text image of the first image; and performing Soft Edge processing on the foreground text image by using a Gaussian Blur technique (Gaussian Blur), to obtain the second image.

In one embodiment, the first method is applicable to the first image with a relatively low background complexity, for example, the first image is a silk screen process printing (Silk Screen Process Printing) image. The Otsu algorithm may determine the first threshold of the first image, the first threshold comprising an image binarization (Thresholding) optimal segmentation threshold (eg, 30) of the first image and performing binarization on the first image according to the first threshold to obtain the mask of the first image. For example, in FIG. 4 , the mask image 3B2 of the first image 3B1 is obtained by using the Otsu algorithm.

In one embodiment, the bitwise AND operation can separate the foreground text outline image in the first image from the background that does not contain the text outline, so as to obtain the foreground text image and the background of the first image image, the background of the foreground text image is transparent. For example, in FIG. 4 , the foreground text image 3B3 and the background image 3B4 of the image 3B1 are obtained according to the image 3B2 .

In one embodiment, as shown in the foreground text image 3B3 in FIG. 4, since the foreground text image may contain jagged edges, Gaussian blur technology can be used to soften the edges, and the obtained first The second image is shown as the second image 3B5 in FIG. 4 .

In one embodiment, removing the background from the first image of each character, and obtaining the second image of each character includes Method 2: the computer device uses Fourier Transform to remove the first image. A network point in an image, performing binarization on the first image after removing the network point; and using Gaussian blur technology to soften the edge of the binarized first image to obtain the first image Two images.

In one embodiment, the second method is suitable for the first image with a relatively complex background containing screen dots (for example, square screen dots, circular screen dots, etc.), for example, the first image is process printing image. The Fourier transform can change the frequency (Frequency) of the first image, so as to achieve the effect of removing dots; the binarization of the first image after removing dots can be the method The Otsu algorithm in method one; the Gaussian blur technique is the same as that used in method one.

Step S4, the computer device processes the second image of each character according to a preset first image processing method to obtain a third image of each character.

In one embodiment, the first image processing method includes image binarization and contour extraction. The computer device performs image binarization on the second image according to the first threshold, for example, when the pixel value at any position in the second image is greater than or equal to the first Threshold, binarize the primitive at any position to 255; when the primitive value at any position in the second image is less than the first threshold, turn the image at any position Element binarized to 0. For example, as shown in FIG. 5 , an image 4A1 is obtained after image binarization is performed on the second image 3B5 .

In one embodiment, the computer device uses the Fourier Descriptors algorithm or the Invariant Moments algorithm to outline the text in the second image after image binarization Extraction; the Fourier descriptor algorithm can identify the closed edge of the character contour in the second image after image binarization, and reconstruct it, thereby extracting the character contour; the invariant The moment algorithm uses properties such as translation invariance, scale invariance, and rotation invariance to describe the overall characteristics of the second image after image binarization, thereby extracting the second image after image binarization The outline of the text in the image. For example, as shown in FIG. 5 , the third image 4A2 of the character “0” is obtained after contour extraction is performed on the image 4A1 . It should be noted that each character in the flawless image has a third image corresponding to one of them, and when the flawless image contains M characters, a total of M pieces of the third image are obtained. image, where M represents a positive integer greater than 0.

Step S5, the computer device processes the second image of each character according to the preset second image processing method, and obtains N fourth images and N fifth images of each character, and each character N pieces of fourth images correspond to N pieces of fifth images one by one, and N is a positive integer greater than 1.

In one embodiment, the computer device can use an image erasing tool (for example, an eraser tool in Photoshop) to perform N times of random erasing on the second image of each character to obtain N frames of each character For the fourth image, as shown in Figure 5, for example, after the second image 3B5 of the word "0" is randomly erased twice, two fourth images of the word "0" are obtained: the fourth image 4B1 and the second image 4B1. Four images 4C1.

In one embodiment, the computer device performs image binarization on the N fourth images of each character to obtain N black and white images, and the image binarization is the same as the method used in step S4 Similarly, for example, as shown in FIG. 5 , an image 4B2 is obtained after image binarization is performed on the fourth image 4B1 , and an image 4C2 is obtained after image binarization is performed on the fourth image 4C1 .

In one embodiment, the computer device performs contour extraction on the N black-and-white images to obtain the N fifth images, the contour extraction is the same as the method used in step S4, as shown in Figure 5, for example, The fifth image 4B3 of the character "0" is obtained after the contour extraction of the image 4B2; the fifth image 4C3 of the character "0" is obtained after the contour extraction of the image 4C2.

It should be noted that when the flawless image contains M characters, after obtaining N fourth images of each character, a total of M*N fourth images of all characters are obtained, and the M*N fifth images.

Step S6, the computer device calculates the similarity measurement (Similarity Measurement) between each of the N fifth images of each character and the third image of each character, and obtains N similarity measures corresponding to each character, and the N fifth images of each character are respectively associated with the N similarity measures corresponding to each character, according to the corresponding values of all characters in the character area N similarity measures determine a blemish threshold.

In one embodiment, the similarity measure refers to a Euclidean distance (Euclidean Distance) between each fifth image of each character and the third image of each character. The computer device calculates the Euclidean distance between each fifth image of each character and the third image of each character, thereby obtaining each fifth image of each character The value of the corresponding similarity measure. For example, as shown in FIG. 5, for the character "0" having two fifth images, the Euclidean distance between the fifth image 4B3 of the character "0" and the third image 4A2 is 0.76, The Euclidean distance between the fifth image 4C3 of the text "0" and the third image 4A2 is 0.23. It should be noted that when the flawless image contains M characters, after obtaining N fourth images of each character, a total of M*N fourth images of all characters are obtained, and the M*N fifth images, and then obtain M*N similarity measure values.

In one embodiment, the determining a blemish threshold according to the N similarity measures corresponding to all the characters in the text area includes: according to the image of the fifth image corresponding to each value of the similarity measure As for the number of images, a broken-line relationship graph of the similarity measure and the number of images is made.

Specifically, when the flawless image contains M characters, after the computer device obtains the values of M*N similarity measures, it will count the number of fifth images corresponding to the value of each similarity measure. number, and taking the similarity measure as the horizontal axis, and the number of the fifth image as the vertical axis, to make the broken line relationship diagram. For example, the number of the fifth image corresponding to the value of the similarity measure 0.01 is 36, the number of the fifth image corresponding to the value of the similarity measure 0.35 is 0, and the value of the similarity measure is 0.82 The number of corresponding fifth images is 52, etc., and the obtained broken-line relationship diagram is shown in FIG. 6 .

In one embodiment, the computer device uses the first local minimum value (Local Minimum) of the similarity measure in the broken line graph as the flaw threshold. For example, as shown in FIG. 6, the first local minimum value of the similarity measure in the broken-line relationship diagram is 0.35, then the defect threshold is 0.35. It should be noted that the dotted line in FIG. 6 is only For example the first local minimum is 0.35.

Step S7, the computer device compares each of the N similarity measures corresponding to each character with the defect threshold, and when any similarity measure corresponding to any character is less than or equal to the defect threshold, Step S8 is executed, and when any similarity measure corresponding to any character is greater than the blemish threshold, step S9 is executed.

In step S8, the computer device determines that the fourth image corresponding to the fifth image associated with the arbitrary similarity measure is a flawless image.

For example, the Euclidean distance between the fifth image 4C3 of the word "0" and the third image 4A2 is 0.23, which is smaller than the blemish threshold 0.35, and the computer device can mark the fourth image 4C1 as a blemish-free image .

Step S9, the computer device determines that the fourth image corresponding to the fifth image associated with any one of the similarity measures is a flawed image; when any one of the fourth images is determined to be flawed When drawing an image, intercept a background image from the background area, the size of the intercepted background image is equal to the size of the defective image; and perform shading processing on the intercepted background image, and synthesize The flawed image and the background image after shading processing are used to obtain a composite image.

For example, as shown in FIG. 5 , the Euclidean distance between the fifth image 4B3 of the word "0" and the third image 4A2 is 0.76, which is greater than the blemish threshold of 0.35, and the computer device can convert the fourth image 4B1 Labeled as flawed image 4B1.

In one embodiment, since the shading of the text area and the background area may be slightly different, multiple (for example, 4) shading adjustments may be performed on the background image to increase the sensitivity of the ambient light source. fault tolerance, and obtain a plurality of images after adjusting the shading (in order to clearly illustrate the present invention, the image after adjusting the shading is referred to as an "adjusted image" here); the multiple adjusted images are respectively compared with The defective images are synthesized to obtain multiple synthesized images. For example, as shown in FIG. 7 , the computer device intercepts a background image 6A that is the same size as the defective image 4B1 from the background area, adjusts the brightness of the background image 6A four times, and converts the defective image to The image 4B1 is synthesized with the background image 6A after each shading processing to obtain a synthesized image 6B, a synthesized image 6C, a synthesized image 6D, and a synthesized image 6E.

In one embodiment, the synthetic image can be used as a flawed sample to train a neural network to obtain a flaw detection model; after obtaining a synthetic image of any character, steps S5 to S9 can be repeated to obtain the arbitrary character A larger number (eg, 80) of flawed samples.

In one embodiment, when the defect-free image contains M characters, after the computer device obtains N fourth images of each character, a total of M*N fourth images are obtained; the computer device determines M * K fourth images in the N fourth images are flawed images, and K background images corresponding to each of the flawed images are intercepted from the background area; computer device Perform L times of shading adjustment on each image, and then synthesize each shading-adjusted background image and the corresponding defective image to obtain K*L synthetic images, where K is less than A positive integer of M*N, L is a positive integer greater than one.

In step S10, the computer device determines the size relationship between the number of composite images and a preset second threshold, and when the number of composite images is smaller than the preset second threshold, step S1 is executed; When the number of synthesized images is greater than or equal to the preset second threshold, step S11 is executed.

In an embodiment, the preset second threshold may be 100,000.

In step S11, the computer device uses the synthesized image to train a neural network to obtain a defect detection model.

The above-mentioned FIG. 1 introduces the image processing method of the present application in detail. The hardware device architecture for implementing the image processing method will be introduced below in conjunction with FIG. 2 .

It should be understood that the embodiments are only for illustration, and are not limited by the structure in terms of the scope of the patent application.

Referring to FIG. 2 , it is a schematic structural diagram of a computer device provided by a preferred embodiment of the present application. In a preferred embodiment of the present application, the computer device 3 includes a storage 31 and at least one processor 32 . Those skilled in the art should understand that the structure of the computer device shown in Figure 2 does not constitute a limitation of the embodiment of the present application, it can be a bus-type structure or a star structure, and the computer device 3 can also include a ratio More or less other hardware or software, or different arrangements of components are illustrated.

In some embodiments, the computer device 3 includes a terminal capable of automatically performing numerical calculations and/or information processing according to preset or stored instructions, and its hardware includes but not limited to microprocessors, dedicated integrated circuits, Programmable gate arrays, digital signal processors and embedded devices, etc.

It should be noted that the computer device 3 is only an example, and other existing or future electronic products that can be adapted to this application should also be included in the scope of protection of this application and included here by reference.

In some embodiments, the storage 31 is used to store program codes and various data. For example, the storage 31 can be used to store flawless images, and can also store the image processing system 30 installed in the computer device 3, and realize high-speed, automatic completion of programs or access to data. The storage 31 includes a read-only memory (Read-Only Memory, ROM), a programmable read-only memory (Programmable Read-Only Memory, PROM), an erasable programmable read-only memory (Erasable Programmable Read -Only Memory, EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically-Erasable Programmable Read-Only Memory (EEPROM) , CD-ROM (Compact Disc Read-Only Memory, CD-ROM) or other optical disk storage, disk storage, tape storage, or any other computer-readable storage medium that can be used to carry or store data.

In some embodiments, the at least one processor 32 may be composed of an integrated circuit, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits with the same function or different functions. , including one or more central processing units (Central Processing unit, CPU), microprocessors, digital signal processing chips, graphics processors and combinations of various control chips. The at least one processor 32 is the control core (Control Unit) of the computer device 3, which connects various components of the entire computer device 3 through various interfaces and lines, and runs or executes programs stored in the memory 31 or module, and call the data stored in the memory 31 to execute various functions of the computer device 3 and process data, such as the function of image processing.

In some embodiments, the image processing system 30 runs on the computer device 3 . The image processing system 30 may include a plurality of functional modules composed of program code segments. The program codes of each program segment in the image processing system 30 can be stored in the memory 31 of the computer device 3 and executed by at least one processor 32 to realize the image processing functions shown in FIG. 1 .

In this embodiment, the image processing system 30 can be divided into multiple functional modules according to the functions it performs. The module referred to in this application refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, and are stored in a memory.

Although not shown, the computer device 3 may also include a power supply (such as a battery) for supplying power to each component. Preferably, the power supply may be logically connected to the at least one processor 32 through a power management device, thereby realizing Manage functions such as charging, discharging, and power management. The power supply may also include one or more DC or AC power sources, recharging devices, power failure 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 repeated here.

It should be understood that the embodiments are only for illustration, and are not limited by the structure in terms of the scope of the patent application.

The above-mentioned integrated units implemented in the form of software function modules can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, and includes several instructions for enabling a computer device (which may be a server, a personal computer, etc.) or a processor (processor) to execute part of the method described in each embodiment of the present application.

In a further embodiment, referring to FIG. 2, the at least one processor 32 can execute the operating system of the computer device 3 and various installed applications (such as the image processing system 30), program codes, etc., For example, the various modules mentioned above.

Program codes are stored in the storage 31 , and the at least one processor 32 can call the program codes stored in the storage 31 to execute related functions. The program codes stored in the memory 31 can be executed by the at least one processor 32 to implement the functions of the various modules to achieve the purpose of image processing.

In one embodiment of the present application, the storage 31 stores one or more instructions (that is, at least one instruction), and the at least one instruction is executed by the at least one processor 32 to realize the image shown in FIG. 1 Purpose of processing.

In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or may also be distributed to multiple networks on the unit. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional module in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented not only in the form of hardware, but also in the form of hardware plus software function modules.

It will be apparent to those skilled in the art that the present application is not limited to the details of the exemplary embodiments described above, but that the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application. Therefore, no matter from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the application is defined by the appended claims rather than the above description, so it is intended to All changes within the meaning and range of equivalents of the elements are embraced in this application. Any reference sign in a claim should not be construed as limiting the claim to which it relates. Furthermore, it is clear that the word "comprising" does not exclude other elements or the singular does not exclude the plural. A plurality of units or devices stated in the device claim may also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to denote names and do not imply any particular order.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application without limitation. Although the present application has been described in detail with reference to the above preferred embodiments, those of ordinary skill in the art should understand that the present application can be The technical solution shall be modified or equivalently replaced without departing from the spirit and scope of the technical solution of the present application.

3: Computer device 30: Image processing system 31: Storage 32: Processor S1~S11: Steps

In order to more clearly illustrate the technical solutions in the embodiments of the present application or in the prior art, the accompanying drawings that need to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings in the following description are only It is an embodiment of the present application, and those skilled in the art can also obtain other drawings according to the provided drawings without creative work.

FIG. 1 is a flowchart of an image processing method provided by an embodiment of the present application.

FIG. 2 is a structural diagram of a computer device provided by an embodiment of the present application.

Fig. 3 is an example diagram of step S1 and step S2 provided by the embodiment of the present application.

Fig. 4 is an example diagram of a process of obtaining a second image provided by an embodiment of the present application.

Fig. 5 is an example diagram of the process of obtaining a defective image provided by the embodiment of the present application.

FIG. 6 is an example diagram of a line relationship diagram provided by an embodiment of the present application.

FIG. 7 is an example diagram of a process of obtaining a composite image provided by an embodiment of the present application.

S1~S11: Steps

Claims (10)

An image processing method, wherein the method includes: Acquiring a flawless image, determining a text area and a background area of the flawless image, and determining the position of each character in the text area; Segmenting the character area according to the position of each character to obtain a first image of each character; removing the background from the first image of each character to obtain a second image of each character; processing the second image of each character according to a preset first image processing method to obtain a third image of each character; According to the preset second image processing method, the second image of each character is processed to obtain N fourth images and N fifth images of each character, and the N fourth images of each character The image is in one-to-one correspondence with N fifth images, and N is a positive integer greater than 1; Calculate the similarity measure between each fifth image in the N fifth images of each character and the third image of each character, and obtain N similarity measures corresponding to each character , and the N fifth images of each character are respectively associated with the N similarity measures corresponding to each character, and one is determined according to the N similarity measures corresponding to all characters in the character area blemish threshold; Comparing the size of each similarity measure in the N similarity measures corresponding to each character with the defect threshold, wherein, when any similarity measure corresponding to any character is greater than the defect threshold, it is determined that it is different from the defect threshold. The fourth image corresponding to the fifth image associated with a similarity measure is a flawed image; When any one of the fourth images is determined to be a defective image, intercepting a background image from the background area, the size of the intercepted background image is equal to the size of the defective image; and Performing shading processing on the intercepted background image, synthesizing the flawed image and the background image after shading processing to obtain a composite image. The image processing method according to claim 1, wherein the first image processing method includes image binarization and contour extraction; the second image processing method includes erasure processing, image binarization, and contour extraction . The image processing method according to claim 2, wherein removing the background from the first image of each character and obtaining the second image of each character includes Method 1: Using the Otsu algorithm to determine a first threshold of the first image, obtain a mask of the first image according to the first threshold, and perform a bit-by-bit comparison of the mask and the first image AND operation to obtain the foreground text image of the first image; and The second image is obtained by performing softening and edge processing on the foreground character image by using a Gaussian blur technique. The image processing method according to claim 2, wherein removing the background from the first image of each character and obtaining the second image of each character includes method two: Using Fourier transform to remove the dots in the first image, and binarize the first image after the dots are removed; and The second image is obtained by performing edge softening processing on the binarized first image by using a Gaussian blur technique. The image processing method according to claim 3, wherein the first image processing method and the second image processing method perform image binarization according to the first threshold, and use the Fourier descriptor algorithm Or invariant moment algorithm for contour extraction. The image processing method according to claim 2, wherein, according to the preset second image processing method, the second image of each character is processed to obtain N fourth images and N fourth images of each character The fifth image, the N fourth images of each character correspond one-to-one to the N fifth images, including: Perform N times of random erasing on the second image of each character to obtain N fourth images of each character; Perform image binarization on the N fourth images of each character to obtain N black and white images; Contour extraction is performed on the N pieces of black and white images to obtain the N pieces of fifth images. The image processing method according to claim 1, wherein the similarity measure refers to the Euclidean distance between each fifth image of each character and the third image of each character ; Wherein, said determining a defect threshold according to the N similarity measures corresponding to all the characters in the text area includes: According to the number of images of the fifth image corresponding to each value of the similarity measure, make a broken-line relationship diagram between the similarity measure and the number of images; and The first local minimum value of the similarity measure in the broken-line relationship graph is used as the flaw threshold. The image processing method according to claim 1, wherein the intercepted background image is subjected to shading processing, and the flawed image and the background image after shading processing are synthesized to obtain a composite image Like include: Perform multiple lightness adjustments on the intercepted background image to obtain multiple adjusted images, and perform composite processing on the multiple adjusted images and the defective image respectively to obtain multiple composite images. A computer-readable storage medium, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the image processing method according to any one of claims 1 to 8 is realized. A computer device, wherein, the computer device includes a storage and at least one processor, at least one instruction is stored in the storage, and when the at least one instruction is executed by the at least one processor, the requirements of items 1 to 1 are implemented. The image processing method described in any one of 8.

Images