A fast blind deconvolution method for text images

Abstract

The fast text image blind deconvolution method and device provided in the embodiment of the present invention reads the blurred image y to be processed from the data storage device, initializes the convolution kernel k, the preset parameter β and the preset threshold β0, determines whether the preset parameter β is greater than the preset threshold β0, and outputs a clear image x and the convolution kernel k if it is not, and if so, determines the clear image x according to the preset first method, determines the convolution kernel k according to the preset second method, and adjusts the preset parameter β according to the preset third method until the preset parameter β is less than the preset threshold β0. This solution solves the problem of high computational complexity and slow computational speed of the algorithm for blind deconvolution of text images based on L0 regularization intensity and gradient. The algorithm for blind deconvolution of text images solved by single-loop iteration provides a new way for fast blind deconvolution, and has the beneficial effects of good restoration effect, low algorithm complexity, and fast computational speed.

Description

Technical Field

[0001] The invention relates to the field of image processing, and in particular to a fast text image blind deconvolution method. Background Art

[0002] In recent years, single image deblurring technology has made significant progress, and motion blur removal has been successful in natural images. The prior knowledge used by these algorithms is mostly based on the heavy-tailed gradient statistics of natural images. However, for text images, since their content is mainly two-tone (black and white), they do not follow the heavy-tailed gradient statistics of natural images, so these methods are less effective for text images. At present, the best algorithm for blind deconvolution of text images is based on the zero-norm (L0) regularization algorithm of intensity and gradient. The calculation of its optimization model is based on the pyramid algorithm (first sparsely sample the image, then gradually increase the sampling rate) and the semi-quadratic splitting method (for example, Chinese patent application 201710159744.1). The model is characterized by containing multiple regularization coefficients. The algorithm needs to perform cyclic iterative calculations for each coefficient (other coefficients are temporarily fixed). For each additional coefficient, there is one more layer of loop nesting. Adding one layer of loop of the pyramid algorithm, the total number of loop nesting layers reaches 4 layers. Therefore, the calculation speed of the algorithm is slow. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a fast text image blind deconvolution method, which has the advantages of good restoration effect, low algorithm complexity, and fast calculation speed.

[0004] In a first aspect, the present invention provides a fast text image blind deconvolution method, comprising:

[0005] Read the blurred image y to be processed from the data storage device, initialize the convolution kernel k, the preset parameter β and the preset threshold β0;

[0006] Determine whether the preset parameter β is greater than the preset threshold β0. If not, output the clear image x and the convolution kernel k.

[0007] If so, the clear image x is determined according to a preset first method, the convolution kernel k is determined according to a preset second method, and the preset parameter β is adjusted according to a preset third method until the preset parameter β is less than a preset threshold β0.

[0008] As an optional solution, the initialization of the convolution kernel k includes:

[0009] The size of the convolution kernel k is set to 0.1 to 0.4 times the size of the blurred image y to be processed, the two elements in the central area of ​​the convolution kernel k are 0.5, and the remaining elements of the convolution kernel k are set to 0.

[0010] As an optional solution, the initialization preset parameter β has a value range of 1 to 50, and the preset threshold β0 has a value range of 0.01 to 0.2.

[0011] As an optional solution, determining the clear image x according to a preset first manner includes:

[0012] The clear image x is calculated and processed in the following way,

[0013]

[0014] The convolution kernel k is expanded to the same size as the blurred image y to be processed, F(x), F(k), and F(y) are the Fourier transforms of x, k, and y respectively, and F(k) T is the conjugate transpose of F(k);

[0015] x=F -1 (F(x))

[0016] F -1 (F(x)) denotes the inverse Fourier transform of F(x);

[0017] All elements in the clear image x that are greater than 0.999 are set to 1, and all elements in the clear image x that are less than 0.001 are set to 0.

[0018] As an optional solution, determining the convolution kernel k according to a preset second method includes:

[0019] The convolution kernel k is calculated and processed as follows,

[0020]

[0021] F(x) T is the conjugate transpose of F(x);

[0022] k=F -1 (F(k))

[0023] Among them, F -1 (F(k)) denotes the inverse Fourier transform of F(k);

[0024] Reduce the size of the convolution kernel k to be the same as the initialization convolution kernel size; set all elements less than 0 in the convolution kernel k to 0, normalize the convolution kernel k, determine the sum of all elements in the convolution kernel k, denoted as ktot, and divide all elements in the convolution kernel k by ktot, k=k / ktot.

[0025] As an optional solution, adjusting the preset parameter β according to a preset third mode includes:

[0026] The preset parameter β=rβ is adjusted, where the value range of r is 0.9 to 0.98.

[0027] In a second aspect, the present invention provides a fast text image blind deconvolution device, comprising:

[0028] A reading unit, used for reading the blurred image to be processed from the data storage device, initializing the convolution kernel k, the preset parameter β and the preset threshold β0;

[0029] A judgment unit, used to judge whether a preset parameter β is greater than a preset threshold β0, and if not, output a clear image x and a convolution kernel k;

[0030] A determination unit is used to determine the clear image x according to a preset first method when the preset parameter β is greater than a preset threshold β0, determine the convolution kernel k according to a preset second method, and adjust the preset parameter β according to a preset third method until the preset parameter β is less than the preset threshold β0.

[0031] In a third aspect, the present invention provides a computer device, comprising:

[0032] at least one processor; and

[0033] a memory communicatively connected to the at least one processor; wherein,

[0034] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the above-mentioned fast text image blind deconvolution method.

[0035] In a fourth aspect, the present invention provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the above-mentioned fast text image blind deconvolution method.

[0036] The fast text image blind deconvolution method and device provided in the embodiment of the present invention reads the blurred image y to be processed from the data storage device, initializes the convolution kernel k, the preset parameter β and the preset threshold β0, determines whether the preset parameter β is greater than the preset threshold β0, and outputs a clear image x and the convolution kernel k if it is not, and if so, determines the clear image x according to the preset first method, determines the convolution kernel k according to the preset second method, and adjusts the preset parameter β according to the preset third method until the preset parameter β is less than the preset threshold β0. This solution solves the problem of high computational complexity and slow computational speed of the algorithm for blind deconvolution of text images based on L0 regularization intensity and gradient. The algorithm for blind deconvolution of text images solved by single-loop iteration provides a new way for fast blind deconvolution, and has the beneficial effects of good restoration effect, low algorithm complexity, and fast computational speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A flowchart of a fast text image blind deconvolution method is provided in an embodiment of the present invention;

[0038] Figure 2 A schematic flow chart of another fast text image blind deconvolution method is provided in an embodiment of the present invention;

[0039] Figure 3 A schematic diagram of a flow chart of a fast text image blind deconvolution method is provided in an embodiment of the present invention;

[0040] Figure 4 A schematic diagram of an original image in a fast text image blind deconvolution method is provided in an embodiment of the present invention;

[0041] Figure 5 A schematic diagram of the effect after processing in a fast text image blind deconvolution method is provided in an embodiment of the present invention;

[0042] Figure 6 A schematic diagram of the effect of a blur convolution kernel in a fast text image blind deconvolution method is provided in an embodiment of the present invention;

[0043] Figure 7 A structural block diagram of a computer device is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0045] The terms "first", "second", "third", "fourth", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0046] Combination Figure 1 As shown, an embodiment of the present invention provides a fast text image blind deconvolution method, including:

[0047] S101, reading a blurred image y to be processed from a data storage device, initializing a convolution kernel k, a preset parameter β, and a preset threshold β0;

[0048] S102, determining whether the preset parameter β is greater than a preset threshold β0, if not, outputting a clear image x and a convolution kernel k;

[0049] S103, if yes, determine the clear image x according to a preset first method, determine the convolution kernel k according to a preset second method, and adjust the preset parameter β according to a preset third method until the preset parameter β is less than a preset threshold β0.

[0050] In the embodiment of the present invention, the initialization of the convolution kernel k includes:

[0051] The size of the convolution kernel k is set to 0.1 to 0.4 times the size of the blurred image y to be processed, the two elements in the central area of ​​the convolution kernel k are 0.5, and the remaining elements of the convolution kernel k are set to 0, the initialization preset parameter β ranges from 1 to 50, and the preset threshold β0 ranges from 0.01 to 0.2.

[0052] In this embodiment, determining the clear image x according to the preset first method includes the following steps:

[0053] The clear image x is calculated and processed in the following way,

[0054]

[0055] The convolution kernel k is expanded to the same size as the blurred image y to be processed, F(x), F(k), and F(y) are the Fourier transforms of x, k, and y respectively, and F(k) T is the conjugate transpose of F(k);

[0056] x=F -1 (F(x))

[0057] F -1 (F(x)) denotes the inverse Fourier transform of F(x);

[0058] All elements in the clear image x that are greater than 0.999 are set to 1, and all elements in the clear image x that are less than 0.001 are set to 0.

[0059] In this embodiment, the convolution kernel k is determined according to the preset second method, including the following steps:

[0060] The convolution kernel k is calculated and processed as follows,

[0061]

[0062] F(x) T is the conjugate transpose of F(x);

[0063] k=F -1 (F(k))

[0064] Among them, F -1 (F(k)) denotes the inverse Fourier transform of F(k);

[0065] Reduce the size of the convolution kernel k to be the same as the initialization convolution kernel size; set all elements less than 0 in the convolution kernel k to 0, normalize the convolution kernel k, determine the sum of all elements in the convolution kernel k, denoted as ktot, and divide all elements in the convolution kernel k by ktot, k=k / ktot.

[0066] In some embodiments, adjusting the preset parameter β according to a preset third method includes:

[0067] The preset parameter β=rβ is adjusted, wherein the value range of r is 0.9 to 0.98. In this embodiment, r is 0.92. It should be noted that the value can be flexibly selected according to needs and is not limited thereto.

[0068] Combination Figure 2 As shown, an embodiment of the present invention also provides a fast text image blind deconvolution method, comprising the following steps:

[0069] S201, input grayscale blurred image y, the width and height of grayscale blurred image y corresponding to pixels are 596*288;

[0070] S202, initialize the convolution kernel k, the size is 131*131, set the two elements of the 66th row, 66th column and 67th column to 0.5, and the rest of the elements to 0. The coefficient β is 5, and the threshold β0 is 0.1;

[0071] S203, judging whether the coefficient β is greater than the threshold β0, if not, outputting the clear image x, the convolution kernel k, and the algorithm ends; if yes, proceeding to step S204;

[0072] S204, calculating a clear image x, and processing the clear image x;

[0073] S205, calculating the convolution kernel k, and processing the convolution kernel k;

[0074] S206, adjust coefficient β and proceed to step S203.

[0075] In S202, the convolution kernel k is initialized in the following manner, the size of the convolution kernel k is set to be approximately 0.3 to 0.4 times the size of the input image y, the two central elements (rows or columns) are 0.5, and the remaining elements are set to 0;

[0076] In S202 , the coefficient β and the threshold β0 are initialized in the following manner, where the coefficient β ranges from 1 to 50; the threshold β0 ranges from 0.01 to 0.2.

[0077] In S204, x is calculated and processed as follows:

[0078]

[0079] Expand the convolution kernel k to the same size as the input image y. F(x), F(k), and F(y) are the Fourier transforms of x, k, and y, respectively. F(k) T is the conjugate transpose of F(k);

[0080] x=F -1 (F(x))

[0081] F -1 (F(x)) denotes the inverse Fourier transform of F(x);

[0082] Process x as follows: set all elements in x greater than 0.999 to 1, and set all elements in x less than 0.001 to 0.

[0083] In S205, k is calculated and processed as follows:

[0084]

[0085] F(x) T is the conjugate transpose of F(x);

[0086] k=F -1 (F(k));

[0087] F -1 (F(k)) denotes the inverse Fourier transform of F(k);

[0088] Process k as follows: reduce the size of the convolution kernel k to the same size as the initial convolution kernel; set all elements in k that are less than 0 to 0; normalize k, calculate the sum of all elements in k, denoted as ktot, and divide all elements in k by ktot, k=k / ktot;

[0089] In S206, the coefficient β=rβ is adjusted in the following manner, wherein the value range of r is 0.9 to 0.98. In this embodiment, the value of r is 0.92.

[0090] Combination Figure 3, 4 5, in order to facilitate understanding of the implementation effect of the present invention, Figure 3 is the input blurred image, Figure 4 is the result obtained after blind deblurring of the present invention, from Figure 4 It can be seen that the recovery effect is obvious. Figure 5 is the corresponding blur convolution kernel.

[0091] The fast text image blind deconvolution method provided in the embodiment of the present invention reads the blurred image y to be processed from the data storage device, initializes the convolution kernel k, the preset parameter β and the preset threshold β0, determines whether the preset parameter β is greater than the preset threshold β0, and outputs a clear image x and the convolution kernel k if it is not, and if so, determines the clear image x according to the preset first method, determines the convolution kernel k according to the preset second method, and adjusts the preset parameter β according to the preset third method until the preset parameter β is less than the preset threshold β0. This solution solves the problem of high computational complexity and slow computational speed of the algorithm for blind deconvolution of text images based on L0 regularization intensity and gradient. The algorithm for blind deconvolution of text images solved by single-loop iteration provides a new way for fast blind deconvolution, and has the beneficial effects of good restoration effect, low algorithm complexity, and fast computational speed.

[0092] Combination Figure 6 As shown, accordingly, an embodiment of the present invention further provides a fast text image blind deconvolution device, including:

[0093] A reading unit 601 is used to read the blurred image to be processed from the data storage device, and initialize the convolution kernel k, the preset parameter β and the preset threshold β0;

[0094] A judging unit 602 is used to judge whether a preset parameter β is greater than a preset threshold β0, and if not, output a clear image x and a convolution kernel k;

[0095] The determination unit 603 is used to determine the clear image x according to a preset first method when the preset parameter β is greater than a preset threshold β0, determine the convolution kernel k according to a preset second method, and adjust the preset parameter β according to a preset third method until the preset parameter β is less than the preset threshold β0.

[0096] The embodiment of the present invention provides a fast text image blind deconvolution device, which solves the problems of high computational complexity and slow computational speed of the text image blind deconvolution algorithm based on L0 regularization strength and gradient. The text image blind deconvolution algorithm solved by single-loop iteration provides a new approach for fast blind deconvolution, and has the beneficial effects of good restoration effect, low algorithm complexity, fast computational speed, etc.

[0097] Accordingly, according to an embodiment of the present invention, the present invention also provides a computer device, a readable storage medium and a computer program product.

[0098] Figure 7 FIG. 1 is a schematic diagram of the structure of a computer device 12 provided in an embodiment of the present invention. Figure 7 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 7 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0099] like Figure 7 As shown, computer device 12 is in the form of a general-purpose computing device. Computer device 12 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0100] Components of computer device 12 may include, but are not limited to, one or more processors or processing units 16 , a system memory 28 , and a bus 18 that connects various system components including system memory 28 and processing unit 16 .

[0101] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0102] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0103] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 7 not shown, usually called a "hard drive"). Although Figure 7 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the embodiments of the present invention.

[0104] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0105] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the computer device 12, and / or may communicate with any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the computer device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the computer device 12, including, but not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0106] The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28, such as implementing the fast text image blind deconvolution method provided by the embodiment of the present invention.

[0107] An embodiment of the present invention also provides a non-transitory computer-readable storage medium storing computer instructions, on which a computer program is stored, wherein when the program is executed by a processor, the fast text image blind deconvolution method provided in all the inventive embodiments of the present application is implemented.

[0108] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, an apparatus, or a device.

[0109] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0110] The program code included in the computer-readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages ​​such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer by any type of network including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect to the Internet).

[0111] An embodiment of the present invention further provides a computer program product, including a computer program, which implements the above-mentioned fast text image blind deconvolution method when executed by a processor.

[0112] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the disclosure of the present invention can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present invention can be achieved, and this document does not limit this.

[0113] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A fast text image blind deconvolution method, characterized in that: include: Read the blurred image y to be processed from the data storage device, initialize the convolution kernel k, the preset parameter β and the preset threshold β0; The initializing convolution kernel k includes: setting the size of the convolution kernel k to 0.1 to 0.4 times the size of the blurred image y to be processed, the two elements in the central area of ​​the convolution kernel k to 0.5, and the remaining elements of the convolution kernel k to 0; initializing the preset parameter β to a value range of 1 to 50, and the preset threshold β0 to a value range of 0.01 to 0.2; Determine whether the preset parameter β is greater than the preset threshold β0. If not, output the clear image x and the convolution kernel k. If yes, the clear image x is determined according to the preset first method, the convolution kernel k is determined according to the preset second method, and the preset parameter β is adjusted according to the preset third method until the preset parameter β is less than the preset threshold β0; The determining the clear image x according to the preset first mode includes: The clear image x is calculated and processed in the following way, The convolution kernel k is expanded to the same size as the blurred image y to be processed, F(x), F(k), and F(y) are the Fourier transforms of x, k, and y respectively, and F(k) T is the conjugate transpose of F(k); F -1 (F(x)) denotes the inverse Fourier transform of F(x); Set all elements in the clear image x that are greater than 0.999 to 1, and set all elements in the clear image x that are less than 0.001 to 0; The determining the convolution kernel k according to the preset second method includes: The convolution kernel k is calculated and processed as follows, ； F(x) T is the conjugate transpose of F(x); ； Among them, F -1 (F(k)) denotes the inverse Fourier transform of F(k); Reduce the size of the convolution kernel k to be the same as the initialization convolution kernel size; set all elements less than 0 in the convolution kernel k to 0, normalize the convolution kernel k, determine the sum of all elements in the convolution kernel k, denoted as ktot, and divide all elements in the convolution kernel k by ktot, k=k / ktot; The adjusting the preset parameter β according to the preset third mode includes: adjusting the preset parameter β = rβ ,in r The value range is 0.9 to 0.

98.

2. A fast text image blind deconvolution device, characterized in that: include: A reading unit, used for reading the blurred image to be processed from the data storage device, initializing the convolution kernel k, the preset parameter β and the preset threshold β0; The initializing convolution kernel k includes: setting the size of the convolution kernel k to 0.1 to 0.4 times the size of the blurred image y to be processed, the two elements in the central area of ​​the convolution kernel k to 0.5, and the remaining elements of the convolution kernel k to 0; initializing the preset parameter β to a value range of 1 to 50, and the preset threshold β0 to a value range of 0.01 to 0.2; A judgment unit, used to judge whether a preset parameter β is greater than a preset threshold β0, and if not, output a clear image x and a convolution kernel k; A determination unit, configured to determine the clear image x according to a preset first method when the preset parameter β is greater than a preset threshold β0, determine the convolution kernel k according to a preset second method, and adjust the preset parameter β according to a preset third method until the preset parameter β is less than the preset threshold β0; The determining the clear image x according to the preset first mode includes: The clear image x is calculated and processed in the following way, ； The convolution kernel k is expanded to the same size as the blurred image y to be processed, F(x), F(k), and F(y) are the Fourier transforms of x, k, and y respectively, and F(k) T is the conjugate transpose of F(k); ； F -1 (F(x)) denotes the inverse Fourier transform of F(x); Set all elements in the clear image x that are greater than 0.999 to 1, and set all elements in the clear image x that are less than 0.001 to 0; The determining the convolution kernel k according to the preset second method includes: The convolution kernel k is calculated and processed as follows, ； F(x) T is the conjugate transpose of F(x); ； Among them, F -1 (F(k)) denotes the inverse Fourier transform of F(k); Reduce the size of the convolution kernel k to be the same as the initialization convolution kernel size; set all elements less than 0 in the convolution kernel k to 0, normalize the convolution kernel k, determine the sum of all elements in the convolution kernel k, denoted as ktot, and divide all elements in the convolution kernel k by ktot, k=k / ktot; The adjusting the preset parameter β according to the preset third mode includes: adjusting the preset parameter β = rβ ,in r The value range is 0.9 to 0.

98.

3. A computer device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the fast text image blind deconvolution method described in claim 1.

4. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable the computer to execute the fast text image blind deconvolution method according to claim 1.

Images