Stochastic resonance image enhancement method and device of FHN neuron model

Abstract

The invention provides a stochastic resonance image enhancement method and device for an FHN neuron model, and relates to the technical field of image processing, and the method comprises the steps: obtaining an original image; the method comprises the following steps: segmenting an original image into a plurality of non-overlapped sub-image areas in a sliding window mode, and numbering each sub-image area; pixel points in the sub-image areas are converted into a one-dimensional data sequence according to a clockwise spiral expansion mode; performing normalization processing on the one-dimensional data sequence; inputting the normalized one-dimensional data sequence into a one-dimensional asymmetric FHN neuron model, and determining an optimal one-dimensional data sequence enhancement result of pixel points in each sub-image region by adjusting model parameters and interference noise intensity and by taking an optimal signal-to-noise ratio as a target; recovering each optimal one-dimensional data sequence enhancement result into a sub-image enhancement region according to an inverse process of clockwise spiral expansion; and combining the enhanced sub-image areas into an enhanced image according to the serial number sequence.

Description

Technical Field

[0001] The invention relates to the technical field of image processing, and in particular to a random resonance image enhancement method and device for a FHN neuron model. Background Art

[0002] With the rapid development of computer vision and image processing technology, images have become the main way for people to obtain external information. However, in real life, images are often interfered by various external noises during the process of acquisition, processing, transmission and display, resulting in serious degradation of image quality. This degradation not only affects people's intuitive perception of image information, but also has an adverse effect on subsequent higher-level image processing tasks such as image classification and target detection. Therefore, how to enhance the useful signals in images and improve image quality has become an important research topic in the field of image processing.

[0003] At present, a variety of methods have been proposed for image enhancement research. These methods mainly focus on removing noise information in the image to improve the image quality. Common image enhancement methods include image histogram equalization and various image filtering techniques, such as mean filtering, median filtering, Gaussian filtering, etc. These methods enhance the contrast and clarity of the image by adjusting the brightness distribution of the image or smoothing the noise in the image.

[0004] Existing image enhancement methods often lead to the loss of inherent pixel information of the image while filtering out noise, thus reducing the image quality. At the same time, the non-Gaussian noise in the image cannot be effectively processed, resulting in poor final image enhancement effect. Summary of the invention

[0005] In order to solve the technical problem that the existing image enhancement methods often cause the loss of image inherent pixel information and reduce image quality while filtering out noise, and at the same time, the non-Gaussian noise in the image cannot be effectively processed, resulting in poor final image enhancement effect, the present invention provides a random resonance image enhancement method and device of FHN neuron model.

[0006] The technical solution provided by the embodiment of the present invention is as follows: First aspect: An embodiment of the present invention provides a stochastic resonance image enhancement method for a FHN neuron model, comprising: S1: Get the original image; S2: dividing the original image into a plurality of non-overlapping sub-image regions by means of a sliding window, and numbering each of the sub-image regions; S3: Converting the pixel points in the sub-image area into a one-dimensional data sequence in a clockwise spiral manner; S4: performing normalization processing on the one-dimensional data sequence; S5: input the normalized one-dimensional data sequence into the one-dimensional asymmetric FHN neuron model, and determine the optimal one-dimensional data sequence enhancement result of the pixel points in each sub-image area by adjusting the model parameters and the interference noise intensity with the goal of optimizing the signal-to-noise ratio; S6: according to the inverse process of clockwise spiral expansion, each of the optimal one-dimensional data sequence enhancement results is restored to a sub-image enhancement area; S7: Combining the sub-image enhancement regions into an enhanced image in order of numbering.

[0007] Second aspect: An embodiment of the present invention provides a stochastic resonance image enhancement device for a FHN neuron model, comprising: An acquisition module, used for acquiring the original image; A segmentation module, used for segmenting the original image into a plurality of non-overlapping sub-image regions by means of a sliding window, and numbering each of the sub-image regions; A conversion module, used for converting the pixel points in the sub-image area into a one-dimensional data sequence in a clockwise spiral expansion manner; A normalization module, used for performing normalization processing on the one-dimensional data sequence; A determination module is used to: input the normalized one-dimensional data sequence into the one-dimensional asymmetric FHN neuron model, and determine the optimal one-dimensional data sequence enhancement result of the pixel points in each sub-image area by adjusting the model parameters and the interference noise intensity with the goal of optimizing the signal-to-noise ratio; A restoration module, used for restoring each of the optimal one-dimensional data sequence enhancement results into a sub-image enhancement region according to the inverse process of clockwise spiral expansion; The combining module is used to combine the sub-image enhancement areas into an enhanced image in the order of numbers.

[0008] The third aspect: An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the stochastic resonance image enhancement method of the FHN neuron model as described in the first aspect is implemented.

[0009] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: (1) In the present invention, the normalized one-dimensional data sequence is input into the one-dimensional asymmetric FHN neuron model. By adjusting the model parameters and the interference noise intensity, the optimal one-dimensional data sequence enhancement result of the pixel points in each sub-image area is determined with the goal of optimizing the signal-to-noise ratio. While filtering out the noise, important pixel information is retained, thereby improving the image quality.

[0010] (2) In the present invention, the normalized one-dimensional data sequence is input into the one-dimensional asymmetric FHN neuron model, and the optimal one-dimensional data sequence enhancement result of the pixel points in each sub-image area is determined by adjusting the model parameters and the interference noise intensity, with the goal of optimizing the signal-to-noise ratio. The one-dimensional asymmetric FHN neuron model is used to effectively process the non-Gaussian noise in the image, thereby improving the image enhancement effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic flow chart of a stochastic resonance image enhancement method for a FHN neuron model provided by an embodiment of the present invention; Figure 2 A schematic structural diagram of a stochastic resonance image enhancement device for a FHN neuron model provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0013] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0014] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0015] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0016] In the embodiments of the present invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are consistent.

[0017] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0018] Reference Manual Attached Figure 1 , shows a flow chart of a random resonance image enhancement method for a FHN neuron model provided by an embodiment of the present invention.

[0019] The embodiment of the present invention provides a random resonance image enhancement method of a FHN neuron model, which can be implemented by a random resonance image enhancement device of a FHN neuron model, and the random resonance image enhancement device of the FHN neuron model can be a terminal or a server. The processing flow of the random resonance image enhancement method of the FHN neuron model can include the following steps: S1: Get the original image.

[0020] S2: Divide the original image into multiple non-overlapping sub-image regions by means of a sliding window, and number each sub-image region.

[0021] Among them, sliding window is a commonly used image processing and computing method, especially widely used in computer vision, signal processing, data analysis and other fields. The basic idea of ​​sliding window is to use a fixed-size window to slide on the image, signal or data sequence to process it.

[0022] In a possible implementation manner, the sub-image area is specifically:

[0023] in, SubI i Indicates i sub-image area, p jk The sub-image area j Line k The pixel value of the column, , , M Represents the length of the original image, N Indicates the width of the original image. m Indicates the length of the sub-image area, n Indicates the width of the sub-image area.

[0024] In a possible implementation manner, the sub-image area numbers are specifically:

[0025] in, SubI i Indicates i sub-image area, M Represents the length of the original image, N Indicates the width of the original image. m Indicates the length of the sub-image area, n Indicates the width of the sub-image area.

[0026] In the present invention, the original image is divided into a plurality of non-overlapping sub-image regions by a sliding window method and numbered, which can improve the efficiency and accuracy of image processing, reduce memory usage, and enhance the flexibility and adaptability of processing.

[0027] S3: Convert the pixel points in the sub-image area into a one-dimensional data sequence in a clockwise spiral manner.

[0028] Among them, clockwise spiral unfolding is a technique that flattens a matrix or two-dimensional data into a one-dimensional sequence in a spiral clockwise direction. This unfolding method is widely used in image processing, data visualization and other fields, especially when processing local features of an image or sorting data.

[0029] In a possible implementation, the one-dimensional data sequence is specifically:

[0030] in, SeqI i Indicates i The pixel value sequence corresponding to the sub-image area is p jk The sub-image area j Line k The pixel value of the column, , .

[0031] In the present invention, the clockwise spiral expansion can arrange the features of the local area in a specific order, so that the structure and pattern in the image can be more easily captured when performing feature extraction. At the same time, flattening the two-dimensional matrix into a one-dimensional sequence can simplify the data structure, making the storage and transmission of data more efficient. When processing a large amount of image data, a one-dimensional sequence may be easier to manage than a two-dimensional matrix.

[0032] S4: Normalize the one-dimensional data sequence.

[0033] Among them, normalization is a data preprocessing technology that aims to adjust data to a standard range or scale.

[0034] S5: The normalized one-dimensional data sequence is input into the one-dimensional asymmetric FHN neuron model, and the optimal one-dimensional data sequence enhancement result of the pixel points in each sub-image area is determined by adjusting the model parameters and the interference noise intensity with the goal of optimizing the signal-to-noise ratio.

[0035] Among them, the one-dimensional asymmetric FHN (FitzHugh-Nagumo) neuron model is a mathematical model used to simulate the electrical activity of neurons. This model is an extension or variant of the classic FitzHugh-Nagumo model, and is mainly used to describe the dynamic behavior and pulse emission of neurons.

[0036] Among them, the signal-to-noise ratio (SNR) is an important indicator for measuring signal quality and is widely used in signal processing, communication, image processing, audio processing and other fields. It is used to quantify the relationship between useful information and noise in the signal.

[0037] In a possible implementation, the one-dimensional asymmetric FHN neuron model is specifically:

[0038] in, v represents the membrane potential of the neuron, a and b represents the dimensionless equation constant, represents the interference noise intensity, t Indicates time, SeqI i Indicates i The pixel value sequence corresponding to the sub-image area.

[0039] In a possible implementation manner, the signal-to-noise ratio is specifically:

[0040] in, SNRrepresents the signal-to-noise ratio, represents the signal frequency, Indicates the amplitude of signal frequency change, Represents the power spectral density of the input one-dimensional data sequence, Indicates the intensity of interference noise near the signal frequency.

[0041] In the present invention, by adjusting the parameters of the FHN model and the noise intensity, the characteristics of the signal can be effectively enhanced to make it more prominent under noise interference. At the same time, by optimizing the signal-to-noise ratio, the interference of noise on the signal can be reduced and the clarity of the signal can be enhanced.

[0042] Furthermore, the pixel data of the sub-image area is input into the FHN model and the signal-to-noise ratio is optimized, so that the image quality can be improved.

[0043] S6: According to the inverse process of clockwise spiral expansion, each optimal one-dimensional data sequence enhancement result is restored to a sub-image enhancement area.

[0044] In the present invention, the restoration process can reorganize the optimized enhancement results into sub-image regions, so that each sub-region in the image undergoes consistent enhancement processing, which helps to improve the overall quality of the image and makes each sub-image region appear clearer and more delicate in the restored image.

[0045] S7: Combining the sub-image enhancement regions into an enhanced image in order of numbering.

[0046] In the present invention, by combining the sub-image regions in sequence, it is possible to ensure that the processing results of each sub-region can be presented consistently in the overall image. The numbering sequence helps to ensure that the arrangement and splicing of the sub-image regions are orderly, thereby avoiding the problem of inconsistency or misalignment during the combination process. At the same time, splicing the sub-image regions into a complete image in sequence reduces the complexity and error rate of the image processing process, making the image enhancement and splicing process more efficient and controllable.

[0047] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: (1) In the present invention, the normalized one-dimensional data sequence is input into the one-dimensional asymmetric FHN neuron model. By adjusting the model parameters and the interference noise intensity, the optimal one-dimensional data sequence enhancement result of the pixel points in each sub-image area is determined with the goal of optimizing the signal-to-noise ratio. While filtering out the noise, important pixel information is retained, thereby improving the image quality.

[0048] (2) In the present invention, the normalized one-dimensional data sequence is input into the one-dimensional asymmetric FHN neuron model, and the optimal one-dimensional data sequence enhancement result of the pixel points in each sub-image area is determined by adjusting the model parameters and the interference noise intensity, with the goal of optimizing the signal-to-noise ratio. The one-dimensional asymmetric FHN neuron model is used to effectively process the non-Gaussian noise in the image, thereby improving the image enhancement effect.

[0049] Reference Manual Attached Figure 2 , showing a schematic structural diagram of a random resonance image enhancement device for a FHN neuron model provided by the present invention.

[0050] The present invention also provides a stochastic resonance image enhancement device 20 for a FHN neuron model, comprising: An acquisition module 201 is used to acquire an original image; A segmentation module 202, configured to segment the original image into a plurality of non-overlapping sub-image regions by means of a sliding window, and number each of the sub-image regions; A conversion module 203, configured to convert the pixel points in the sub-image area into a one-dimensional data sequence in a clockwise spiral expansion manner; A normalization module 204, configured to perform normalization processing on the one-dimensional data sequence; The determination module 205 is used to: input the normalized one-dimensional data sequence into the one-dimensional asymmetric FHN neuron model, and determine the optimal one-dimensional data sequence enhancement result of the pixel points in each sub-image area by adjusting the model parameters and the interference noise intensity with the goal of optimizing the signal-to-noise ratio; A restoration module 206, configured to restore each of the optimal one-dimensional data sequence enhancement results into a sub-image enhancement region according to the inverse process of clockwise spiral expansion; The combining module 207 is used to combine the sub-image enhancement regions into an enhanced image according to the sequence of numbers.

[0051] In a possible implementation manner, the sub-image area is specifically:

[0052] in, SubI i Indicates i sub-image area, p jk The sub-image area j Line k The pixel value of the column, , , M Represents the length of the original image, N Indicates the width of the original image.m Indicates the length of the sub-image area, n Indicates the width of the sub-image area.

[0053] In a possible implementation manner, the sub-image area numbers are specifically:

[0054] in, SubI i Indicates i sub-image area, M Represents the length of the original image, N Indicates the width of the original image. m Indicates the length of the sub-image area, n Indicates the width of the sub-image area.

[0055] In a possible implementation, the one-dimensional data sequence is specifically:

[0056] in, SeqI i Indicates i The pixel value sequence corresponding to the sub-image area is p jk The sub-image area j Line k The pixel value of the column, , .

[0057] In a possible implementation, the one-dimensional asymmetric FHN neuron model is specifically:

[0058] in, v represents the membrane potential of the neuron, a and b represents the dimensionless equation constant, represents the interference noise intensity, t Indicates time, SeqI i Indicates i The pixel value sequence corresponding to the sub-image area.

[0059] In a possible implementation manner, the signal-to-noise ratio is specifically:

[0060] in, SNR represents the signal-to-noise ratio, represents the signal frequency, Indicates the amplitude of signal frequency change, Represents the power spectral density of the input one-dimensional data sequence, Indicates the intensity of interference noise near the signal frequency.

[0061] The stochastic resonance image enhancement device 20 of the FHN neuron model provided by the present invention can execute the above-mentioned stochastic resonance image enhancement method of the FHN neuron model and achieve the same or similar technical effects. To avoid repetition, the present invention will not be described in detail.

[0062] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: (1) In the present invention, the normalized one-dimensional data sequence is input into the one-dimensional asymmetric FHN neuron model. By adjusting the model parameters and the interference noise intensity, the optimal one-dimensional data sequence enhancement result of the pixel points in each sub-image area is determined with the goal of optimizing the signal-to-noise ratio. While filtering out the noise, important pixel information is retained, thereby improving the image quality.

[0063] (2) In the present invention, the normalized one-dimensional data sequence is input into the one-dimensional asymmetric FHN neuron model, and the optimal one-dimensional data sequence enhancement result of the pixel points in each sub-image area is determined by adjusting the model parameters and the interference noise intensity, with the goal of optimizing the signal-to-noise ratio. The one-dimensional asymmetric FHN neuron model is used to effectively process the non-Gaussian noise in the image, thereby improving the image enhancement effect.

[0064] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be 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 the processor may also be any conventional processor, etc.

[0065] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0066] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0067] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0068] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0069] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0070] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0071] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0072] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0073] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0074] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0075] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0076] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the stochastic resonance image enhancement method of the FHN neuron model as described in the method embodiment is implemented.

[0077] A computer-readable storage medium provided by the present invention can implement the steps and effects of the stochastic resonance image enhancement method of the FHN neuron model of the above method embodiment. To avoid repetition, the present invention will not go into details.

[0078] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: (1) In the present invention, the normalized one-dimensional data sequence is input into the one-dimensional asymmetric FHN neuron model. By adjusting the model parameters and the interference noise intensity, the optimal one-dimensional data sequence enhancement result of the pixel points in each sub-image area is determined with the goal of optimizing the signal-to-noise ratio. While filtering out the noise, important pixel information is retained, thereby improving the image quality.

[0079] (2) In the present invention, the normalized one-dimensional data sequence is input into the one-dimensional asymmetric FHN neuron model, and the optimal one-dimensional data sequence enhancement result of the pixel points in each sub-image area is determined by adjusting the model parameters and the interference noise intensity, with the goal of optimizing the signal-to-noise ratio. The one-dimensional asymmetric FHN neuron model is used to effectively process the non-Gaussian noise in the image, thereby improving the image enhancement effect.

[0080] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0081] There are a few points to note: (1) The drawings of the embodiments of the present invention only involve structures related to the embodiments of the present invention. Other structures may refer to conventional designs.

[0082] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0083] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0084] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A stochastic resonance image enhancement method for FHN neuron model, It is characterized in that include: S1: Get the original image; S2: dividing the original image into a plurality of non-overlapping sub-image regions by means of a sliding window, and numbering each of the sub-image regions; S3: Converting the pixel points in the sub-image area into a one-dimensional data sequence in a clockwise spiral manner; S4: performing normalization processing on the one-dimensional data sequence; S5: input the normalized one-dimensional data sequence into the one-dimensional asymmetric FHN neuron model, and determine the optimal one-dimensional data sequence enhancement result of the pixel points in each sub-image area by adjusting the model parameters and the interference noise intensity with the goal of optimizing the signal-to-noise ratio; S6: according to the inverse process of clockwise spiral expansion, each of the optimal one-dimensional data sequence enhancement results is restored to a sub-image enhancement area; S7: Combining the sub-image enhancement regions into an enhanced image in order of numbering.

2. The stochastic resonance image enhancement method of the FHN neuron model according to claim 1, It is characterized in that The sub-image area is specifically: in, SubI i Indicates i sub-image area, p jk The sub-image area j Line k The pixel value of the column, , , M Represents the length of the original image, N Indicates the width of the original image. m Indicates the length of the sub-image area, n Indicates the width of the sub-image area.

3. The stochastic resonance image enhancement method of the FHN neuron model according to claim 1, It is characterized in that The sub-image area numbers are specifically: in, SubI i Indicates i sub-image area, M Represents the length of the original image, N Indicates the width of the original image. m Indicates the length of the sub-image area, n Indicates the width of the sub-image area.

4. The stochastic resonance image enhancement method of the FHN neuron model according to claim 1, It is characterized in that The one-dimensional data sequence is specifically: in, SeqI i Indicates i The pixel value sequence corresponding to the sub-image area is p jk The sub-image area j Line k The pixel value of the column, , .

5. The stochastic resonance image enhancement method of the FHN neuron model according to claim 1, It is characterized in that The one-dimensional asymmetric FHN neuron model is specifically: in, v represents the membrane potential of the neuron, a and b represents the dimensionless equation constant, represents the interference noise intensity, t Indicates time, SeqI i Indicates i The pixel value sequence corresponding to the sub-image area.

6. The stochastic resonance image enhancement method of the FHN neuron model according to claim 1, It is characterized in that The signal-to-noise ratio is specifically: in, SNR represents the signal-to-noise ratio, represents the signal frequency, Indicates the amplitude of signal frequency change, Represents the power spectral density of the input one-dimensional data sequence, Indicates the intensity of interference noise near the signal frequency.

7. A stochastic resonance image enhancement device for FHN neuron model, It is characterized in that include: An acquisition module, used for acquiring the original image; A segmentation module, used for segmenting the original image into a plurality of non-overlapping sub-image regions by means of a sliding window, and numbering each of the sub-image regions; A conversion module, used for converting the pixel points in the sub-image area into a one-dimensional data sequence in a clockwise spiral expansion manner; A normalization module, used for performing normalization processing on the one-dimensional data sequence; A determination module is used to: input the normalized one-dimensional data sequence into the one-dimensional asymmetric FHN neuron model, and determine the optimal one-dimensional data sequence enhancement result of the pixel points in each sub-image area by adjusting the model parameters and the interference noise intensity with the goal of optimizing the signal-to-noise ratio; A restoration module, used for restoring each of the optimal one-dimensional data sequence enhancement results into a sub-image enhancement region according to the inverse process of clockwise spiral expansion; The combining module is used to combine the sub-image enhancement areas into an enhanced image in the order of numbers.

8. The stochastic resonance image enhancement device of the FHN neuron model according to claim 7, It is characterized in that The sub-image area is specifically: in, SubI i Indicates i sub-image area, p jk The sub-image area j Line k The pixel value of the column, , , M Represents the length of the original image, N Indicates the width of the original image. m Indicates the length of the sub-image area, n Indicates the width of the sub-image area.

9. The stochastic resonance image enhancement device of the FHN neuron model according to claim 7, It is characterized in that The sub-image area numbers are specifically: in, SubI i Indicates i sub-image area, M Represents the length of the original image, N Indicates the width of the original image. m Indicates the length of the sub-image area, n Indicates the width of the sub-image area.

10. The stochastic resonance image enhancement device of the FHN neuron model according to claim 7, It is characterized in that The one-dimensional data sequence is specifically: in, SeqI i Indicates i The pixel value sequence corresponding to the sub-image area is p jk The sub-image area j Line k The pixel value of the column, , .

Images