Image deblurring method, device and computer readable storage medium

Abstract

The embodiment of the present invention provides an image deblurring method, device and computer-readable storage medium, the method comprising: obtaining an image to be deblurred, dividing the image to be deblurred into a plurality of image blocks; analyzing and marking each of the image blocks, marking the original clear image block and the image block to be optimized, and calculating the actual pixel ratio of the blurred area; comparing the actual pixel ratio with a predetermined pixel ratio threshold, marking the first image block to be optimized and the second optimized image block to be optimized; using a conventional image local deblurring method to remove the blurred area in each first image block to be optimized; optimizing the image blur degradation model based on L1 norm regularization to calculate a clear image and a blur kernel, determining the clear image as the second optimized clear image block after the second image block to be optimized is deblurred; splicing and combining to obtain a target clear image after the image to be deblurred is deblurred. This embodiment can effectively improve the efficiency and effect of image deblurring.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of image processing technology, and in particular to an image deblurring method, device and computer-readable storage medium. Background Art

[0002] At present, with the continuous improvement of image technology, when a camera device captures an image, the captured image is usually blurred due to the influence of users or environmental factors. Therefore, an image deblurring method comes into being.

[0003] An existing method for overall image deblurring is usually to use an image blind deblurring algorithm model to deblur the entire image. Specifically, after constructing an image blur degradation model of the image to be deblurred, the latent image and blur kernel in the image blur degradation model are calculated. The final latent image is the clear image after deblurring. However, this method takes a lot of time to calculate the latent image and blur kernel, and the deblurring efficiency is low. In addition, there is also a method for local image deblurring, which usually first determines the blurred area in the image to be deblurred, and then uses the pixel mean of the non-blurred area in the image to be deblurred to replace the blurred pixels in the blurred area, thereby removing the blurred area in the image. However, the image deblurring effect of this method is relatively poor, and the image is still unclear after deblurring. Summary of the invention

[0004] The technical problem to be solved by the embodiments of the present invention is to provide an image deblurring method which can effectively improve the efficiency and effect of image deblurring.

[0005] A further technical problem to be solved by the embodiments of the present invention is to provide an image deblurring device that can effectively improve the efficiency and effect of image deblurring.

[0006] A further technical problem to be solved by an embodiment of the present invention is to provide a computer-readable storage medium for storing a computer program that can effectively improve the efficiency and effect of image deblurring.

[0007] In order to solve the above technical problems, the embodiment of the present invention first provides the following technical solution: an image deblurring method, comprising the following steps:

[0008] Acquire an image to be deblurred, and divide the image to be deblurred into a plurality of image blocks of predetermined sizes;

[0009] Analyze and mark each of the image blocks, wherein the image blocks without blurry areas and the image blocks with blurry areas are marked as original clear image blocks and image blocks to be optimized, respectively, and calculate the actual pixel ratio of the blurry areas in the image blocks to be optimized;

[0010] Comparing the actual pixel ratio with a predetermined pixel ratio threshold, further marking the image block to be optimized whose actual pixel ratio is greater than zero and less than the predetermined pixel ratio threshold as a first image block to be optimized, and marking the image block corresponding to the blurred area whose actual pixel ratio is greater than or equal to the predetermined pixel ratio threshold as a second image block to be optimized;

[0011] Using a conventional local image deblurring method to remove blurry areas in each of the first image blocks to be optimized to obtain a first optimized clear image block;

[0012] Using the maximum image gradient and the minimum image intensity of the second image block to be optimized as a priori conditions, optimizing the pre-stored image blur degradation model based on L1 norm regularization to calculate the clear image and blur kernel in the image blur degradation model, and determining the clear image as the second optimized clear image block after the blur of the second image block to be optimized is removed; and

[0013] The original clear image block, the first optimized clear image block and the second optimized clear image block corresponding to each of the images to be deblurred are spliced ​​together to obtain the target clear image after deblurring corresponding to each of the images to be deblurred.

[0014] Furthermore, the method of using the maximum image gradient and the minimum image intensity of the second image block to be optimized as a priori conditions, optimizing the pre-stored image blur degradation model based on L1 norm regularization to calculate the clear image and blur kernel in the image blur degradation model, and determining the clear image as the second optimized clear image block after the blur of the second image block to be optimized is specifically as follows:

[0015] calculating the maximum image gradient and the minimum image intensity of the second image block to be optimized; and

[0016] The maximum image gradient and the minimum image intensity of the second image block to be optimized are combined as prior conditions, and a clear image in the image blur degradation model is calculated based on a semi-quadratic splitting algorithm model and a fast Fourier transform algorithm model. Then, the blur kernel in the image blur degradation model is calculated based on the clear image in the image blur degradation model in combination with a fast Fourier transform algorithm model and blur kernel constraints, and the clear image is determined as the second optimized clear image block after the blur of the second image block to be optimized is removed.

[0017] Further, the analyzing and marking each of the image blocks, wherein the image blocks without blurry areas and the image blocks with blurry areas are marked as original clear image blocks and image blocks to be optimized respectively, and the actual pixel ratio of the blurry areas in the image blocks to be optimized is calculated specifically includes:

[0018] Calculate the image mean and variance standard deviation of each image block;

[0019] Determine an adaptive threshold of each of the image blocks according to the image mean and variance standard deviation;

[0020] Comparing the adaptive threshold with a predetermined threshold interval, marking an image block whose adaptive threshold is less than or equal to the predetermined threshold interval as an original clear image block, and marking an image block whose adaptive threshold is greater than the predetermined threshold interval as an image block to be optimized; and

[0021] Calculate the actual pixel ratio of the blurred area in the image block to be optimized.

[0022] Furthermore, the step of removing the blurred areas in each of the first image blocks to be optimized by using a conventional local image deblurring method to obtain the first optimized clear image blocks specifically includes:

[0023] Calculating average pixel values ​​of areas other than the blurred area in the first conventional image block to be optimized; and

[0024] The actual pixel value of each pixel in the blurred area of ​​the first image block to be optimized is modified to the average pixel value to obtain the first optimized clear image block.

[0025] Furthermore, after the image to be deblurred is equally divided into a plurality of image blocks of predetermined sizes and before each image block is analyzed and marked, each image block is preprocessed, and the preprocessing at least includes graying and filtering.

[0026] On the other hand, in order to solve the above-mentioned further technical problems, an embodiment of the present invention further provides the following technical solutions: an image deblurring device, which is respectively connected to a camera device for providing an image to be deblurred and an image display device for displaying a target clear image processed by the image deblurring device, the image deblurring device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the image deblurring method as described in any one of the above.

[0027] On the other hand, in order to solve the above-mentioned further technical problems, an embodiment of the present invention further provides the following technical solution: a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the image deblurring method as described in any one of the above-mentioned items.

[0028] After adopting the above technical scheme, the embodiment of the present invention has at least the following beneficial effects: after the embodiment of the present invention obtains the image to be deblurred again, the image to be deblurred is equally divided into a plurality of image blocks of predetermined sizes, and the original clear image block and the image block to be optimized are respectively marked, and then the actual pixel ratio occupied by the corresponding blurred area is calculated, and the actual pixel ratio is compared with the predetermined pixel ratio threshold value, and the image block to be optimized is further classified and marked as a first image block to be optimized and a second image block to be optimized. Since the actual pixel ratio occupied by the blurred area in the first image block to be optimized is relatively small, a conventional image local deblurring method is used for deblurring, and the deblurring effect is good. However, since the actual pixel ratio occupied by the blurred area in the second image block to be optimized is relatively large, the second image block to be optimized is used. The maximum image gradient and the minimum image intensity of the image block are combined as prior conditions, and the pre-stored image blur degradation model is optimized based on L1 norm regularization to calculate the clear image and blur kernel in the image blur degradation model, so as to realize deblurring of the entire second image block to be optimized. The maximum image gradient and the minimum image intensity are combined as prior conditions to effectively avoid falling into the local optimal solution when solving the clear image, thereby greatly improving the overall deblurring efficiency of the second image block to be optimized. Finally, the original clear image block, the first optimized clear image block and the second optimized clear image block corresponding to each of the images to be deblurred are spliced ​​and combined to obtain the target clear image after deblurring corresponding to the image to be deblurred, which can effectively improve the efficiency and effect of image deblurring. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 The present invention is a flowchart of an optional embodiment of the image deblurring method according to an embodiment of the present invention.

[0030] Figure 2 This is a specific flow chart of step S5 of an optional embodiment of the image deblurring method according to an embodiment of the present invention.

[0031] Figure 3 This is a specific flow chart of step S2 of an optional embodiment of the image deblurring method according to an embodiment of the present invention.

[0032] Figure 4 This is a specific flow chart of step S4 of an optional embodiment of the image deblurring method according to an embodiment of the present invention.

[0033] Figure 5 The figure is a principle block diagram of an optional embodiment of the image deblurring device according to the embodiment of the present invention.

[0034] Figure 6 This is a functional module diagram of an optional embodiment of the image deblurring device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The present application is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the following illustrative embodiments and descriptions are only used to explain the present invention and are not intended to limit the present invention. In addition, the embodiments and features in the embodiments of the present application may be combined with each other without conflict.

[0036] like Figure 1 As shown, an optional embodiment of the present invention provides an image deblurring method, comprising the following steps:

[0037] S1: Acquire an image to be deblurred, and divide the image to be deblurred into a plurality of image blocks of predetermined sizes;

[0038] S2: Analyze and mark each of the image blocks, wherein the image blocks without blurry areas and the image blocks with blurry areas are marked as original clear image blocks and image blocks to be optimized, respectively, and calculate the actual pixel ratio of the blurry areas in the image blocks to be optimized;

[0039] S3: comparing the actual pixel ratio with a predetermined pixel ratio threshold, further marking the image block to be optimized whose actual pixel ratio is greater than zero and less than the predetermined pixel ratio threshold as a first image block to be optimized, and marking the image block corresponding to the blurred area whose actual pixel ratio is greater than or equal to the predetermined pixel ratio threshold as a second image block to be optimized;

[0040] S4: using a conventional local image deblurring method to remove blurry areas in each of the first image blocks to be optimized to obtain a first optimized clear image block;

[0041] S5: using the maximum image gradient and the minimum image intensity of the second image block to be optimized as a priori conditions, optimizing the pre-stored image blur degradation model based on L1 norm regularization to calculate the clear image and blur kernel in the image blur degradation model, and determining the clear image as the second optimized clear image block after the blur of the second image block to be optimized is removed; and

[0042] S6: splicing and combining the original clear image block, the first optimized clear image block and the second optimized clear image block corresponding to each of the images to be deblurred to obtain the target clear image after deblurring corresponding to each of the images to be deblurred.

[0043] In the embodiment of the present invention, after obtaining the image to be deblurred, the image to be deblurred is equally divided into a plurality of image blocks of predetermined sizes, and the original clear image blocks and the image blocks to be optimized are respectively marked, and then the actual pixel ratio occupied by the corresponding blurred area is calculated, and the actual pixel ratio is compared with the predetermined pixel ratio threshold, and the image blocks to be optimized are further classified and marked as the first image block to be optimized and the second image block to be optimized. Since the actual pixel ratio occupied by the blurred area in the first image block to be optimized is relatively small, a conventional image local deblurring method is used for deblurring, and the deblurring effect is good. However, since the actual pixel ratio occupied by the blurred area in the second image block to be optimized is relatively large, the image gradient maximum and image intensity of the second image block to be optimized are used. The minimum degree is combined as a priori condition, and the pre-stored image blur degradation model is optimized based on L1 norm regularization to calculate the clear image and blur kernel in the image blur degradation model, so as to realize deblurring of the entire second image block to be optimized. The maximum image gradient and the minimum image intensity are combined as priori conditions, which can effectively avoid falling into the local optimal solution when solving the clear image, thereby greatly improving the overall deblurring efficiency of the second image block to be optimized. Finally, the original clear image block, the first optimized clear image block and the second optimized clear image block corresponding to each of the images to be deblurred are spliced ​​and combined to obtain the target clear image after deblurring corresponding to the image to be deblurred, which can effectively improve the efficiency and effect of image deblurring.

[0044] In a specific implementation, the predetermined pixel ratio threshold is usually set to 0.05±0.01.

[0045] In an optional embodiment of the present invention, Figure 2 As shown, the step S5 specifically includes:

[0046] S51: Calculating the maximum image gradient and the minimum image intensity of the second image block to be optimized; and

[0047] S52: Using the maximum image gradient and the minimum image intensity of the second image block to be optimized as a priori conditions, a clear image in the image blur degradation model is calculated based on a semi-quadratic splitting algorithm model and a fast Fourier transform algorithm model, and then a blur kernel in the image blur degradation model is calculated based on the clear image in the image blur degradation model in combination with a fast Fourier transform algorithm model and blur kernel constraint conditions, and the clear image is determined as the second optimized clear image block after the blur of the second image block to be optimized is removed.

[0048] In this embodiment, the maximum image gradient and the minimum image intensity of the second image block to be optimized are first calculated, and then the semi-quadratic splitting algorithm model is used to replace the clear image in the iterative process of the image blur degradation model, and then the fast Fourier transform algorithm model is used to calculate the clear image in the iterative process of the image blur degradation model, and then the cycle is repeated in sequence to finally calculate the most accurate clear image; in the iterative process, each time a clear image is solved, the blur kernel in the image blur degradation model is calculated in combination with the fast Fourier transform algorithm model, and then the most accurate blur kernel is obtained in the iterative process according to the blur kernel constraint condition.

[0049] In a specific implementation, the image blur degradation model can be expressed as the following formula:

[0050]

[0051] Among them, B is the blurred image, I is the clear image, K is the blur kernel, ε is the noise. In addition, according to the principle of image blur, the blur kernel constraint condition is K i >0 and Σ i K i =1, where i represents the number of iterations. In addition, after obtaining the blur kernel, it is necessary to set the unfavorable elements in K to 0 to adjust K to obtain the final accurate blur kernel.

[0052] In an optional embodiment of the present invention, Figure 3 As shown, the step S2 specifically includes:

[0053] S21: Calculate the image mean and variance standard deviation of each image block;

[0054] S22: determining an adaptive threshold of each image block according to the image mean and variance standard deviation;

[0055] S23: comparing the adaptive threshold with a predetermined threshold interval, marking an image block whose adaptive threshold is less than or equal to the predetermined threshold interval as an original clear image block, and marking an image block whose adaptive threshold is greater than the predetermined threshold interval as an image block to be optimized; and

[0056] S24: Calculate the actual pixel ratio of the blurred area in the image block where the blurred area exists.

[0057] In this embodiment, by calculating the image mean and variance standard deviation of each of the image blocks, and further determining the adaptive threshold of the image block, and by comparing the adaptive threshold with the predetermined threshold interval, it is determined whether the image block has a blurred area. The judgment method is relatively simple and can effectively improve the detection efficiency of the blurred area. In specific implementation, since the pixels in the blurred area are relatively smaller than the pixels in the clear area, the size of the blurred area in the image block can be determined by reading the pixels in the image block, and then the actual pixel ratio of the blurred area to the image block can be obtained by a simple ratio calculation.

[0058] In an optional embodiment of the present invention, Figure 4 As shown, the step S4 specifically includes:

[0059] S41: Calculate the average pixel value of other areas except the blurred area in the first image block to be optimized; and

[0060] S42: Modify the actual pixel value of each pixel in the blurred area of ​​the first image block to be optimized to the average pixel value to obtain the first optimized clear image block.

[0061] In this embodiment, the pixel value of each pixel point in the blurred area is modified by replacing the average pixel value of other areas except the blurred area in the first image block to be optimized, so as to remove the blurred area in the first image block to be optimized. The process is relatively simple and the deblurring effect is good for image blocks with smaller blurred areas.

[0062] In an optional embodiment of the present invention, after the image to be deblurred is equally divided into a plurality of image blocks of predetermined sizes and before each of the image blocks is analyzed and marked, each image block is also preprocessed, and the preprocessing includes at least graying and filtering. In this embodiment, by graying and filtering the image blocks, subsequent image processing and detection are facilitated, which is conducive to improving the deblurring effect and achieving image optimization.

[0063] On the other hand, Figure 5 As shown, an embodiment of the present invention further provides an image deblurring device 1, which is respectively connected to a camera device 3 for providing an image to be deblurred and an image display device 5 for displaying a target clear image processed by the image deblurring device 1. The image deblurring device 1 includes a processor 10, a memory 12, and a computer program stored in the memory and configured to be executed by the processor. When the processor 10 executes the computer program, it implements the image deblurring method as described in any one of the above items.

[0064] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the image deblurring device. For example, the computer program may be divided into Figure 6 The functional modules in the image deblurring device 1, wherein the image acquisition and equal division module 21, the preliminary marking and ratio calculation module 22, the secondary marking module 23, the conventional deblurring module 24, the optimized deblurring module 25 and the image combination module 26 respectively execute the above steps S1 to S6.

[0065] The image deblurring device 1 may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The image deblurring device 1 may include, but is not limited to, a processor 10 and a memory 12. Those skilled in the art may understand that the schematic diagram is only an example of the image deblurring device 1 and does not constitute a limitation on the image deblurring device 1. The image deblurring device 1 may include more or fewer components than shown in the figure, or may combine certain components, or different components. For example, the image deblurring device 1 may also include input and output devices, network access devices, buses, etc.

[0066] The processor 10 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 10 is the control center of the image deblurring device 1, and various parts of the entire image deblurring device 1 are connected by various interfaces and lines.

[0067] The memory 12 can be used to store the computer program and / or module. The processor 10 realizes various functions of the mask repair control device 1 by running or executing the computer program and / or module stored in the memory 12 and calling the data stored in the memory 12. The memory 12 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a graphic recognition function, a graphic overlay function, etc.), etc.; the data storage area can store data (such as graphic data, etc.) created according to the use of the image deblurring device 1, etc. In addition, the memory 12 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0068] If the functions described in the embodiments of the present invention are implemented in the form of software function modules or units and sold or used as independent products, they can be stored in a storage medium readable by a computing device. Based on this understanding, the embodiments of the present invention implement all or part of the processes in the above-mentioned embodiments, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor 10, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0069] On the other hand, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the image deblurring methods described above.

[0070] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0071] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, which all belong to the protection scope of the present invention.

Claims

1. An image deblurring method, characterized in that: The method comprises the following steps: Acquire an image to be deblurred, and divide the image to be deblurred into a plurality of image blocks of predetermined sizes; Analyze and mark each of the image blocks, wherein the image blocks without blurry areas and the image blocks with blurry areas are marked as original clear image blocks and image blocks to be optimized, respectively, and calculate the actual pixel ratio of the blurry areas in the image blocks to be optimized; Comparing the actual pixel ratio with a predetermined pixel ratio threshold, further marking the image block to be optimized whose actual pixel ratio is greater than zero and less than the predetermined pixel ratio threshold as a first image block to be optimized, and marking the image block corresponding to the blurred area whose actual pixel ratio is greater than or equal to the predetermined pixel ratio threshold as a second image block to be optimized; Using a conventional local image deblurring method to remove blurry areas in each of the first image blocks to be optimized to obtain a first optimized clear image block; Using the maximum image gradient and the minimum image intensity of the second image block to be optimized as a priori conditions, optimizing the pre-stored image blur degradation model based on L1 norm regularization to calculate the clear image and blur kernel in the image blur degradation model, and determining the clear image as the second optimized clear image block after the blur of the second image block to be optimized is removed; and The original clear image block, the first optimized clear image block and the second optimized clear image block corresponding to each of the images to be deblurred are spliced ​​together to obtain the target clear image after deblurring corresponding to each of the images to be deblurred.

2. The image deblurring method according to claim 1, wherein: The method of using the maximum image gradient and the minimum image intensity of the second image block to be optimized as a priori conditions, optimizing the pre-stored image blur degradation model based on L1 norm regularization to calculate the clear image and blur kernel in the image blur degradation model, and determining the clear image as the second optimized clear image block after the blur of the second image block to be optimized is specifically as follows: calculating the maximum image gradient and the minimum image intensity of the second image block to be optimized; and The maximum image gradient and the minimum image intensity of the second image block to be optimized are combined as prior conditions, and a clear image in the image blur degradation model is calculated based on a semi-quadratic splitting algorithm model and a fast Fourier transform algorithm model. Then, the blur kernel in the image blur degradation model is calculated based on the clear image in the image blur degradation model in combination with a fast Fourier transform algorithm model and blur kernel constraints, and the clear image is determined as the second optimized clear image block after the blur of the second image block to be optimized is removed.

3. The image deblurring method according to claim 1, wherein: The analyzing and marking each of the image blocks, wherein the image blocks without blurry areas and the image blocks with blurry areas are marked as original clear image blocks and image blocks to be optimized respectively, and the actual pixel ratio of the blurry areas in the image blocks to be optimized is calculated specifically includes: Calculate the image mean and variance standard deviation of each image block; Determine an adaptive threshold of each of the image blocks according to the image mean and variance standard deviation; Comparing the adaptive threshold with a predetermined threshold interval, marking an image block whose adaptive threshold is less than or equal to the predetermined threshold interval as an original clear image block, and marking an image block whose adaptive threshold is greater than the predetermined threshold interval as an image block to be optimized; and Calculate the actual pixel ratio of the blurred area in the image block to be optimized.

4. The image deblurring method according to claim 1, wherein: The method of removing the blurry area in each of the first image blocks to be optimized by using a conventional local image deblurring method to obtain the first optimized clear image block specifically includes: Calculating the average pixel value of other areas except the blurred area in the first image block to be optimized; and The actual pixel value of each pixel in the blurred area of ​​the first image block to be optimized is modified to the average pixel value to obtain the first optimized clear image block.

5. The image deblurring method according to any one of claims 1 to 4, characterized in that: After the image to be deblurred is equally divided into a plurality of image blocks of predetermined sizes and before each of the image blocks is analyzed and marked, each image block is preprocessed, and the preprocessing at least includes graying and filtering.

6. An image deblurring device, connected to a camera device for providing an image to be deblurred and an image display device for displaying a target clear image processed by the image deblurring device, characterized in that: The image deblurring device comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the image deblurring method according to any one of claims 1 to 5 when executing the computer program.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the image deblurring method according to any one of claims 1 to 5.

Images