Image enhancement method and system based on spatial visual neural network model

Abstract

The present invention relates to an image enhancement method for constructing a spatial visual neural network model. The present invention first normalizes a binary noisy two-dimensional image to satisfy the small parameter restriction imposed by the adiabatic approximation condition for activating FHN neurons; secondly, convolves the spatial signal with an FHN neuron template to obtain a two-dimensional image encoding signal of a spatial neuron pulse potential sequence; constructs an anisotropic diffusion function based on improved bidirectional adaptive selection as a visual receptive field model with a directional selection mechanism, convolves the neuron pulse encoding signal with the constructed receptive field model; and finally finds the optimal binary image result. The invention effectively combines the directional selectivity of the biological visual system and the neuron pulse emission mechanism, making it conform to the physiological characteristics of real visual neuron pulse triggering and signal selectivity, thereby achieving a relatively ideal image denoising effect.

Description

Technical Field

[0001] The present invention belongs to the field of image processing, and in particular relates to an image enhancement method and system for a spatial visual neural network model. Background Art

[0002] During image acquisition, interference signals are often mixed in. These interference signals are often caused by factors such as sensor material properties, operating environment, electronic components, and circuit structure. Therefore, image denoising is a crucial component of image processing, and its results are crucial for subsequent image feature extraction, image analysis, and image recognition and classification. Furthermore, visual physiological experiments and model simulations have demonstrated, from a macroscopic perspective, that the visual system exhibits directional selectivity when observing or recognizing objects, and does not respond equally to stimuli in all directions.

[0003] For example, the visual perception system is most sensitive to horizontal or vertical changes in light intensity, but least sensitive to light intensity in oblique directions. Furthermore, from a microscopic perspective, biological visual systems contain clusters of neurons sensitive to different directions. Methods and systems can produce strong responses to stimuli with specific contours or motion directions, but weaker responses in other directions.

[0004] Traditional neurons use their own pulse characteristics to perform denoising, which requires dimensionality reduction, which is not in line with the physiological mechanism of visual space. The image has no spatial structure correlation during the dimensionality reduction process, resulting in the loss of spatial correlation information. Dimensionality reduction also causes pixel drift due to the time lag effect. Summary of the Invention

[0005] The purpose of the present invention is to provide an image enhancement method for a spatial visual neural network model, thereby solving the problem that the image has no spatial structural correlation during the dimensionality reduction process, resulting in the loss of spatial correlation information, and the pixel drift phenomenon caused by the time lag effect caused by dimensionality reduction.

[0006] To solve the above problems, the first aspect of the present invention provides an image enhancement method for a spatial visual neural network model, which includes: normalizing a noisy binary image; constructing a 3*3 spatial FHN neural network convolution kernel template based on the processed binary image; and obtaining a spatial neuron pulse potential signal corresponding to the binary image by passing a noisy signal through the FHN neural network convolution kernel.

[0007] Traversing the spatial neuron pulse potential signal of the binary image, sequentially selecting a current center value point with eight surrounding directions; judging the difference between the center value of the current center value point and the eight surrounding directions through the corresponding local variance function or substitution function, and constructing a visual receptive field diffusion coefficient with a direction selection mechanism;

[0008] Substituting the visual receptive field diffusion coefficient into the diffusion equation; calculating the mean and local variance of the eight directions relative to the center value point; and obtaining the diffusion coefficient by determining the difference between the mean and the center value from the local variance function or the alternative function;

[0009] The spatial neuron pulse potential signal of the binary image is subjected to multiple spatial convolution filtering by using the visual receptive field diffusion coefficient; in each filtering, multiple optimal algorithm iterations are performed by using the quantum particle swarm algorithm to obtain a processed image.

[0010] A second aspect of the present invention provides an image enhancement system for a spatial visual neural network model, comprising:

[0011] The pulse potential signal generating unit is configured to perform normalization processing on the noisy binary image; construct a 3*3 spatial FHN neural network convolution kernel template based on the processed binary image; and obtain a spatial neuron pulse potential signal corresponding to the binary image by passing the noisy signal through the FHN neural network convolution kernel:

[0012] A diffusion coefficient unit is configured to traverse the spatial neuron pulse potential signal of the binary image and sequentially select a current center value point with eight surrounding directions; based on the difference between the center value of the current center value point and the eight surrounding directions, determine the corresponding local variance function or substitution function to construct a visual receptive field diffusion coefficient with a direction selection mechanism;

[0013] A selection unit is configured to substitute the visual receptive field diffusion coefficient into a diffusion equation; calculate the mean and local variance of eight directions relative to the center value point; and obtain the diffusion coefficient by selecting from the local variance function or the alternative function by determining the difference between the mean and the center value;

[0014] A graphics processing unit is configured to perform multiple spatial convolution filtering on the spatial neuron pulse potential signal of the binary image through the visual receptive field diffusion coefficient; in each filtering, multiple optimal algorithm iterations are performed through the quantum particle swarm algorithm to obtain a processed image.

[0015] The third aspect of the present invention provides an electronic device, which includes a processor; and a memory, which stores computer instructions of an image enhancement method of a spatial visual neural network model. When the computer instructions are executed by the processor, the electronic device executes the image enhancement method of the spatial visual neural network model in the present invention.

[0016] The fourth aspect of the present invention provides a computer-readable storage medium, a computer-readable storage medium containing program instructions for an image enhancement method of a spatial visual neural network model. When the program instructions are executed by a processor, the method of implementing the image enhancement method of the spatial visual neural network model according to the present invention is implemented.

[0017] The above technical solution of the present invention has the following beneficial technical effects:

[0018] By constructing a bidirectional adaptive filter as an anisotropic diffusion equation filter as a visual receptive field selection mechanism, it is possible to select the difference direction, thereby satisfying the directional selectivity of the visual perception system and effectively improving the previous disadvantage that it is difficult to filter out mutation noise signals with large differences.

[0019] Based on the FHN neuron model, a 3x3 neural network convolution kernel template is constructed. This method directly encodes spatial potential spikes without dimensionality reduction, preserving the adjacent correlation of spatial information and avoiding offsets and time lags. The neural spatial filter kernel conforms to the two-dimensional spatial characteristics of vision and generates corresponding spike potentials in response to the input signal. The neural network preserves the key characteristics of neuronal spike discharge and maintains neighborhood spatial correlation, making the image potential encoding more consistent with the true physiological characteristics of vision.

[0020] The quantum particle swarm optimization iterative algorithm is used to efficiently and conveniently obtain the optimal parameters and output results. The optimal fitness function is selected as the quantitative evaluation indicator during each iteration, and different diffusion functions are adaptively selected based on the characteristics of the center value. This is beneficial to preserving the spatial structure characteristics of the image in a specific direction and the correlation of pixel values ​​in that direction, as well as the reliability of noise removal.

[0021] By constructing the FHN neuron spatial network convolution kernel, highlighting information features, re-encoding potentials, and selecting the diffusion function with 8 direction selection differences at the center point, a bidirectional selection adaptive visual receptive field model is constructed to effectively retain the real signal, selectively remove the noise signal, and effectively output high-quality images. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] FIG1 is a schematic flow chart for illustrating an image enhancement method of a spatial visual neural network model in one embodiment of the present invention;

[0023] FIG2 is a schematic diagram illustrating the composition of an image enhancement system of a spatial visual neural network model in one embodiment of the present invention;

[0024] FIG3 is a schematic diagram illustrating the composition of an image enhancement method of a spatial visual neural network model in another embodiment of the present invention;

[0025] FIG4 is a schematic diagram illustrating a bidirectional adaptive selection model process of a visual receptive field neural network in one embodiment of the present invention;

[0026] FIG5 is a graph illustrating an optimization curve of QPSO image processing in one embodiment of the present invention;

[0027] FIG6 is a diagram for illustrating a comparison between the present invention and other methods in one embodiment of the present invention;

[0028] FIG7 is a schematic structural diagram of an electronic device provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0029] To make the objectives, technical solutions, and advantages of the present invention more clearly understood, the present invention will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present invention.

[0030] The present invention takes the following factors into consideration: First, the traditional neuron model needs to reduce the two-dimensional signal to a one-dimensional signal for denoising. In the process of dimensionality reduction, the correlation of the spatial structure is lost. In addition, the pixel drift phenomenon is caused by the time lag effect caused by the time dependency of the single direction in the dimensionality reduction and denoising process.

[0031] Secondly, traditional image denoising methods lack a selective mechanism for noise signals. Traditional partial differential equation image denoising methods can remove image noise while preserving image details such as edges and textures. However, they produce a staircase effect in smooth image regions. While they consider the difference between surrounding and central elements, they are less effective for granular or intense noise. They also fail to consider the directional selectivity of the human visual system and the visual physiological characteristics of neuronal action potential pulse emission. Consequently, their image denoising results often struggle to meet the requirements of consistency with human subjective evaluation. Therefore, combining the directional selectivity of the visual system with the neuronal pulse emission mechanism, we construct an improved anisotropic diffusion function for the visual receptive field and propose an image enhancement method based on a spatial visual neural network model, which conforms to the working mechanism of binary image denoising based on visual physiological characteristics.

[0032] In one aspect of the embodiment of the present invention, Figure 1 As shown, an image enhancement method of a spatial visual neural network model is provided, which includes the following steps:

[0033] Step S101 involves normalizing the noisy binary image. Based on the processed binary image, a 3x3 spatial FHN neural network convolution kernel template is constructed. The noisy signal passes through the FHN neural network convolution kernel to obtain a spatial neuronal spike potential signal corresponding to the binary image.

[0034] The noisy binary image is normalized, and a 3*3 spatial FHN neural network convolution kernel template is constructed. The noisy signal is pulse-coded by the neural network convolution kernel to obtain a two-dimensional image coding signal of the spatial neuron pulse potential sequence.

[0035] Step S102 involves traversing the spatial neuronal spike potential signals of the binary image and sequentially selecting a current center point with eight surrounding directions. Based on the difference between the center value of the current center point and the surrounding eight directions, the corresponding local variance function or substitution function is used to construct a visual receptive field diffusion coefficient with a direction-selective mechanism.

[0036] A visual receptive field diffusion coefficient with a direction-selective mechanism is constructed, and the local variance and substitution function are automatically selected based on the difference between the current center value and the surrounding eight directions. The local variance is selected for the center value with small differences, while the substitution function selects the diffusion coefficient for the center point with large differences. Noise is often abrupt, and the substitution function can effectively remove isolated noise points.

[0037] Step S103: Substituting the visual receptive field diffusion coefficient into the diffusion equation. Calculating the mean and local variance in eight directions relative to the center value. Determining the difference between the mean and the center value, the diffusion coefficient is obtained from either the local variance function or the surrogate function.

[0038] The constructed improved bidirectional adaptive anisotropic diffusion function is introduced into the diffusion equation, and the mean and local variance in eight directions relative to the center point are calculated. The local variance or alternative function is selected as the diffusion coefficient by judging the difference between the mean and the center value, and spatial convolution filtering is performed on the pulse sequence two-dimensional image coding signal.

[0039] Step S104 includes performing multiple spatial convolution filters on the spatial neuron spike potential signal of the binary image using the visual receptive field diffusion coefficient. In each filtering, multiple optimal algorithm iterations are performed using the quantum particle swarm algorithm to obtain a processed image.

[0040] Initialize the quantum particle swarm population and the optimal fitness function. The fitness function uses the peak signal-to-noise ratio (PSNR). Calculate the PSNR of the two-dimensional image obtained by the anisotropic diffusion equation during the iteration. Update the optimal fitness function to determine whether the optimal PSNR has been achieved, and then determine the number of iterations. Use the quantum particle swarm algorithm to perform multiple optimal algorithm iterations on the results of each processing to obtain the optimal PSNR and the processed image.

[0041] In one embodiment of the image enhancement method of the spatial visual neural network model of the present invention, obtaining the spatial neuron pulse potential signal corresponding to the binary image in step S101 includes: pulse encoding the noisy signal through the neural network convolution kernel to obtain the spatial neuron pulse potential signal corresponding to the binary image.

[0042] In another embodiment of the image enhancement method of the spatial visual neural network model of the present invention, step S102 comprises determining, based on the difference between the center value of the current center value point and the surrounding eight directions, the corresponding local variance function or substitution function to construct a visual receptive field diffusion coefficient with a direction selection mechanism, including:

[0043] Obtain the difference between the center value of the current center point and the surrounding eight directions, and determine whether the difference is less than the set threshold. If so, construct the visual receptive field diffusion coefficient with a direction-selective mechanism through the local variance function. If not, construct the visual receptive field diffusion coefficient with a direction-selective mechanism through the substitution function.

[0044] In another embodiment of the image enhancement method of the spatial visual neural network model of the present invention, in step S104, multiple optimal algorithm iterations are performed using the quantum particle swarm algorithm in each filtering.

[0045] Initialize the quantum particle swarm population, initialize the optimal fitness function, use the peak signal-to-noise ratio as the fitness function, calculate the peak signal-to-noise ratio of the two-dimensional image obtained by the anisotropic diffusion equation in each filtering, update the optimal fitness function, and determine whether the optimal peak signal-to-noise ratio is obtained, and then decide the number of iterations.

[0046] In one embodiment of the image enhancement method of the spatial visual neural network model of the present invention, the mathematical expression of the FHN neuron is shown in Formula 1:

[0047] Formula 1

[0048] Where, u is the fast-changing membrane voltage of the neuron. v is the neuron’s slow-varying recovery voltage. ε(0<ε=1) is the time constant that determines the neuron’s firing rate.a is the threshold value for transition from single potential well to double potential well, a and b are all constants, which together determine the shape of the double potential well.

[0049] In one embodiment of the image enhancement method of the spatial visual neural network model of the present invention, the receptive field model of the diffusion equation is shown in the following formula 2:

[0050] Formula 2

[0051] In the formula u 0 ( x , y ) is the initial image, div is the divergence operator, t is the scale factor, |▽ u | is the modulus of the image gradient, c 1 represents the local variance diffusion coefficient function, c 2 represents the alternative diffusion coefficient function, u 1 and u 2 represents the choice of diffusion coefficient function coefficient, which takes the value of 0 or 1, and the sum is 1. The threshold of the difference between the center point value and the mean of the eight directions is 0.2. If it is less than 0.2, the local variance is selected, otherwise the alternative function is selected as the coefficient function.

[0052] The second aspect of the present invention, as shown in FIG2 , provides an image enhancement system for a spatial visual neural network model, comprising:

[0053] The pulse potential signal generating unit 101 is configured to perform normalization processing on the noisy binary image. Based on the processed binary image, a 3*3 spatial FHN neural network convolution kernel template is constructed. The noisy signal passes through the FHN neural network convolution kernel to obtain a signal that is relatively close to the binary image.

[0054] Corresponding spatial neuron pulse potential signal:

[0055] Diffusion coefficient unit 201 is configured to traverse the spatial neuron spike potential signals of the binary image and sequentially select a current center value point with eight surrounding directions. Based on the difference between the center value of the current center value point and the eight surrounding directions, it determines the corresponding local variance function or substitution function to construct a visual receptive field diffusion coefficient with a direction selection mechanism.

[0056] Selection unit 301 is configured to substitute the visual receptive field diffusion coefficient into the diffusion equation. Means and local variances in eight directions relative to the center value are calculated. The diffusion coefficient is obtained by determining the difference between the mean and the center value and selecting from a local variance function or a surrogate function.

[0057] The graphics processing unit 401 is configured to perform multiple spatial convolution filtering on the spatial neuron pulse potential signal of the binary image using the visual receptive field diffusion coefficient. In each filtering, multiple optimal algorithm iterations are performed using the quantum particle swarm algorithm to obtain a processed image.

[0058] In another embodiment of the image enhancement system of the spatial visual neural network model of the present invention, the pulse potential signal generating unit 101 is further configured to: pulse encode the noisy signal through the neural network convolution kernel to obtain a spatial neuron pulse potential signal corresponding to the binary image.

[0059] In another embodiment of the image enhancement method of the spatial visual neural network model of the present invention, as shown in FIG3 , the corresponding steps include:

[0060] Step (1) for the image in the field of view I ( i , j ) ( i = 1,2,… M ; j = 1,2,… N ,variable i and j The same below) is normalized, I ( i , j ) = S ( t )+ξ( t ), S ( t ) is the input signal, ξ ( t ) is Gaussian white noise. Its expression is shown in formula (1):

[0061] (1)

[0062] in, f is the normalized image; I ( i, j ) is the original noisy image; max( I ( i , j )) express I ( i , j ) maximum value; M is the number of rows of the image; N is the number of columns of the image.

[0063] Step (2) constructs a 3*3 size FHN neural network convolution kernel template, and pulse codes the noisy signal through the neural network convolution kernel to obtain a two-dimensional image coding signal of the spatial neuron pulse potential sequence.

[0064] The FHN neuron model retains the characteristics of the regenerative excitation mechanism of excitable nerve cells and is used to describe the existence of the excitation threshold of nerve and optic nerve electrical impulses and the generation of pulse chains under the action of external current. The mathematical expression of the FHN neuron is shown in Equation (2):

[0065] (2)

[0066] Where, u is the fast-changing membrane voltage of the neuron; v is the neuron’s slow-varying recovery voltage; ε (0 < ε = 1) is the time constant that determines the neuron’s firing rate; a is the threshold value for transition from single potential well to double potential well, a and b are all constants that together determine the shape of the double potential well. The stochastic resonance mechanism of the neuron itself works synergistically with external periodic signals and noise to achieve signal enhancement, detection, denoising, and encoding.

[0067] The coding characteristics of neurons are determined by their own threshold characteristics. If the membrane potential is lower than the threshold, no pulses will be emitted. Only when it is higher than the threshold will pulses be emitted. The mathematical expression of pulse emission is shown in formula (3):

[0068] (3)

[0069] in, th is the threshold; f ( i , j ) is the normalized external noisy signal of formula (2). After encoding, the image can be converted from the external electrical pulse sequence to the symbol sequence.

[0070] Step (3) Perona and Malik The anisotropic diffusion equation PM is proposed as formula (4):

[0071] (4)

[0072] in: u 0 (x, y) is the initial image, div is the divergence operator, t is the scale factor, |▽ u | is the modulus of the image gradient, c (|▽ u|) is the diffusion coefficient function, also known as the gradient modulus function, which satisfies: c (|▽ u |) is about |▽ u | non-negative monotonic function, |▽ u |→0 , c (|▽ u |)=0 ;|▽ u |→∞ , c (|▽ u |) = 1. Usually c ( x ) = k 2 / ( x 2 + k 2 )or c ( x ) =exp(-( x 2 / k 2 )) . In the formula, k is the decrease rate constant. c (|▽ u |) Diffusion coefficients of different scales are generated according to the different local gradients.

[0073] The diffusion coefficient function is improved by using the normalized local mean and gradient method. f ( i , j ) is the normalized image, f ( i , j ) The local grayscale mean in a 3×3 square area with any point as the center is:

[0074] (5)

[0075] The local variance is as follows (6):

[0076] (6)

[0077] When the image is not contaminated by noise, the average value of each pixel in the smooth area is δ 2 ( i , j ) is very close to the pixel gray value, so the local variance is small; while the gray value of isolated noise pixels or edge points varies greatly, and the gray value of some pixels is greatly different from the average value within the region, so the local variance δ 2 ( i ,j ) is very big.

[0078] If there is noise, there will be pixels in the smooth area and edge area, and the local variance δ 2 ( i , j ) are all increased, so in this case the local variance δ 2 ( i , j ) can no longer effectively measure the spatial details, so the diffusion coefficient function is reconstructed using the alternative function ω( i , j ) Replace the central value based on the maximum statistical value replacement algorithm.

[0079] Set the absolute value of the direction difference between the 8 directions and the center point as formula (7):

[0080] (7)

[0081] Substitution function ω( i , j ) as shown in formula (8):

[0082] (8)

[0083] The diffusion coefficient function of the local variance is as follows (9):

[0084] (9)

[0085] The alternative diffusion coefficient function is as shown in formula (10):

[0086] (10)

[0087] The schematic diagram of the bidirectional adaptive selection model processing of the visual receptive field neural network is shown in Figure 4. In combination, the two diffusion coefficient functions construct the anisotropic diffusion equation receptive field model of the bidirectional selection adaptive filter as shown in formula (11):

[0088] (11)

[0089] In the formula u 0( x, y ) is the initial image, div is the divergence operator, t is the scale factor, |▽ u | is the modulus of the image gradient, c 1 represents the local variance diffusion coefficient function, c 2 represents the alternative diffusion coefficient function, u 1 and u2 represents the choice of diffusion coefficient function coefficient, which takes values ​​of 0 or 1, and the sum is 1. The threshold of the difference between the central 11 point values ​​and the mean of the 8 directions is 0.2. If it is less than 0.2, the local variance is selected. Otherwise, an alternative function is selected as the coefficient function.

[0090] The discretization numerical iteration form is as follows, considering the eight neighborhoods around the pixel point, as shown in formula (12):

[0091] (12)

[0092] in G m It is a symbol representing 8 directions and has the characteristics of direction selection. c Represents the diffusion coefficient function, which has two scales and is judged based on the mean. m The value range is 1-8. G 1 to G 4 represents N, W, E, S four vertical and horizontal directions, G 5 to G 8 represents WN, EN, WS, and ES, four oblique directions. To ensure the stability of the iteration, 0≤λ≤0.25.

[0093] Step (4) In order to select the optimal result after multiple iterations, the quantum particle swarm algorithm is used to optimize each result after the receptive field filtering process in step (3), and the peak signal-to-noise ratio of the image quality evaluation index is used as the optimal fitness function. Initialize the population and set the maximum number of iterations of the quantum particle swarm. T max , number of outer wheels R , population size M and dimensions D dim And the optimization range of each dimension, the particle position vector within the set range X i = ( X i1 , X i2 ,..., X iDdim )( i = 1,2,..., M ) to randomly assign initial values.

[0094] Initialize the optimal fitness function and calculate the fitness function value of each particle fitness ( X ), the non-global optimal fitness value is replaced by the best fitness value of each generation fitness ( X ) is substituted and recorded as pbest( i )( i = 1,2,..., M ), set the global optimal fitness function, recorded as gbest By the local optimum of each particle pbest ( i ). As shown in Figure 5, after about 12 iterations of QPSO optimization, the convergence value of fitness is around 19.1 dB. The optimal output image can be found through rapid iteration, and the signal-to-noise ratio tends to stabilize at a maximum value of 19.1 dB.

[0095] in, fitness ( X ) is the peak signal-to-noise ratio, which is an objective standard for evaluating images. The principle of this method is to calculate the mean square error between the original image and the processed image, relative to (2 n -1) 2 The logarithmic value of is shown in (13):

[0096] (13)

[0097] MSE is the mean square error between the original image and the processed image, as shown in formula (14):

[0098] (14)

[0099] In the formula f * ( i , j ) and f ( i , j ) represent the filtered image and the ideal image respectively. The better the denoising effect, the smaller the MSE.

[0100] Step (5) Output of the best results and parameters, according to the best global gbest The value is used as the basis for obtaining the best parameters and outputting the optimal image.

[0101] Figure 6 Comparison of the present invention and other methods. As can be seen from Figure (c), most of the noise can be filtered out after wavelet denoising, but there is still granular noise. Catte While filtering out noise, the binary image will also produce a fogging effect. This is because Catte The algorithm introduces the blurring phenomenon caused by Gaussian filtering.

[0102] Figure (e) shows a signal that undergoes traditional dimensionality reduction before entering the FHN model. When processing the reduced 2D signal, some structural correlation and detail are lost. Figure (e) shows the resulting pixel shift in structure. Figure (f) shows the result of our algorithm flow. From a subjective perspective, it closely matches visual characteristics and nearly preserves the characteristics of the original binary image.

[0103] The third aspect of the present invention provides an electronic device comprising: a processor and a memory, computer instructions for an image enhancement method of a spatial visual neural network model and / or computer instructions for processing state data of an intelligent agent using an action strategy model. When the computer instructions are executed by the processor, the electronic device executes the image enhancement method according to the spatial visual neural network model and / or an image enhancement method of a spatial visual neural network model in the present invention.

[0104] The fourth aspect of the present invention provides a computer-readable storage medium, which contains program instructions of an action strategy model and / or program instructions for processing state data of an intelligent agent using an action strategy model. When the program instructions are executed by a processor, an image enhancement method based on a spatial visual neural network model and / or an image enhancement method based on a spatial visual neural network model in the present invention is implemented.

[0105] As a non-volatile computer-readable storage medium, it can be used to store non-volatile software programs, non-volatile computer executable programs, and modules, such as the program instructions / modules corresponding to the image enhancement method of the spatial visual neural network model in the embodiments of the present invention. One or more program instructions stored in the non-volatile computer-readable storage medium, when executed by a processor, perform the image enhancement method of the spatial visual neural network model and the method of controlling an intelligent agent using an action strategy model in any of the above-mentioned method embodiments.

[0106] The non-volatile computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store an image enhancement method based on a spatial visual neural network model, and data created by the use of a method processing device for controlling an intelligent agent using an action strategy model, etc.

[0107] In addition, the non-volatile computer-readable storage medium may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0108] In some embodiments, the non-volatile computer-readable storage medium may optionally include a memory remotely located from the processor, and the remote memory may be connected to the image enhancement method using a spatial visual neural network model and the method for language recognition using an action strategy model via a network. Examples of such a network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0109] An embodiment of the present invention also provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes any one of the above-mentioned image enhancement methods of the spatial visual neural network model.

[0110] FIG7 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention, Figure 7 As shown, the device includes one or more processors 710 and a memory 720. FIG7 uses one processor 710 as an example. The device for the image enhancement method using a spatial visual neural network model may also include an input device 730 and an output device 740. The processor 710, memory 720, input device 730, and output device 740 may be connected via a bus or other means.

[0111] Figure 7 uses a bus connection as an example. Memory 720 is the aforementioned non-volatile computer-readable storage medium. Processor 710 executes the non-volatile software programs, instructions, and modules stored in memory 720 to execute various server functional applications and data processing, thereby implementing the aforementioned method. Input device 730 can receive input of numeric or character information and generate key signal input related to user settings and function control of the information delivery device. Output device 740 may include a display device such as a display screen.

[0112] The above-mentioned product can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0113] As an embodiment, the electronic device described above can be applied to an encryption and decryption platform, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the image enhancement method processor of at least one spatial visual neural network model to:

[0114] The method includes: normalizing a noisy binary image; constructing a 3*3 spatial FHN neural network convolution kernel template based on the processed binary image; and obtaining a spatial neuron pulse potential signal corresponding to the binary image by passing a noisy signal through the FHN neural network convolution kernel.

[0115] Traversing the spatial neuron pulse potential signal of the binary image, sequentially selecting a current center value point with eight surrounding directions; judging the difference between the center value of the current center value point and the eight surrounding directions through the corresponding local variance function or substitution function, and constructing a visual receptive field diffusion coefficient with a direction selection mechanism;

[0116] Substituting the visual receptive field diffusion coefficient into the diffusion equation; calculating the mean and local variance of the eight directions relative to the center value point; and obtaining the diffusion coefficient by determining the difference between the mean and the center value from the local variance function or the alternative function;

[0117] The spatial neuron pulse potential signal of the binary image is subjected to multiple spatial convolution filtering by using the visual receptive field diffusion coefficient; in each filtering, multiple optimal algorithm iterations are performed by using the quantum particle swarm algorithm to obtain a processed image.

[0118] The electronic devices according to the embodiments of the present invention may be in various forms, including but not limited to:

[0119] (1) Mobile communication devices: These devices are characterized by their mobile communication capabilities and their primary purpose is to provide voice and data communications. These terminals include smartphones, multimedia phones, feature phones, etc.

[0120] (2) Ultra-mobile personal computer devices: These devices fall under the category of personal computers, have computing and processing capabilities, and generally also have mobile Internet access features. These terminals include: PDAs, MIDs, and UMPC devices;

[0121] (3) Portable entertainment devices: These devices can display and play multimedia content. These devices include audio and video players, handheld game consoles, e-books, smart toys, and portable car navigation devices.

[0122] (4) Server: A device that provides computing services. The server consists of a processor, hard disk, memory, system bus, etc. The server is similar to a general computer architecture, but because it needs to provide highly reliable services, it has higher requirements in terms of processing power, stability, reliability, security, scalability, and manageability.

[0123] (5) Other electronic devices with data interaction functions.

[0124] The device embodiments described above are merely illustrative. Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of these modules may be selected based on actual needs to achieve the objectives of this embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0125] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods of each embodiment or certain portions of the embodiments.

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An image enhancement method for a spatial visual neural network model, characterized in that: It includes: Normalize the noisy binary image; Based on the processed binary image, a 3*3 spatial FHN neural network convolution kernel template is constructed; Obtaining a spatial neuron pulse potential signal corresponding to the binary image by passing the noisy signal through the FHN neural network convolution kernel; Traversing the spatial neuron pulse potential signal of the binary image, sequentially selecting a current center value point with eight surrounding directions; judging the difference between the center value of the current center value point and the eight surrounding directions through the corresponding local variance function or substitution function, and constructing a visual receptive field diffusion coefficient with a direction selection mechanism; Substituting the visual receptive field diffusion coefficient into the diffusion equation; Calculate the mean and local variance of the eight directions relative to the central value point; by determining the difference between the mean and the central value, select the diffusion coefficient from the local variance function or the alternative function, where: The diffusion coefficient function of the local variance is as follows: Formula 9 The local variance function is shown in Formula 6: Formula 6 Where f (i, j) is the normalized image, and the local grayscale mean in a 3×3 square area centered at any point f (i, j) is As shown in Formula 5: Formula 5 The alternative diffusion coefficient function is shown in Equation 10: Formula 10 Among them, the replacement function As shown in formula 8: Formula 8 In the formula δ represents the statistical difference, Θ represents the pixel value corresponding to the maximum frequency statistic replacing the central value function; where To set the absolute value of the direction difference between the 8 directions and the center point, use Formula 7: Formula 7 The spatial neuron pulse potential signal of the binary image is subjected to multiple spatial convolution filtering by using the visual receptive field diffusion coefficient; in each filtering, multiple optimal algorithm iterations are performed by using the quantum particle swarm algorithm to obtain a processed image.

2. The image enhancement method of the spatial visual neural network model according to claim 1, characterized in that The obtaining of the spatial neuron pulse potential signal corresponding to the binary image comprises: The noisy signal is pulse-coded by a neural network convolution kernel to obtain a spatial neuron pulse potential signal corresponding to the binary image.

3. The image enhancement method of the spatial visual neural network model according to claim 1, characterized in that According to the difference between the center value of the current center value point and the surrounding eight directions, the corresponding local variance function or substitution function is used to construct the visual receptive field diffusion coefficient with a direction selection mechanism, including: Obtain the difference between the center value of the current center value point and the surrounding eight directions, and determine whether the difference value is less than the set threshold. If so, construct a visual receptive field diffusion coefficient with a direction selection mechanism through the local variance function; if not, construct a visual receptive field diffusion coefficient with a direction selection mechanism through the substitution function.

4. The image enhancement method of the spatial visual neural network model according to claim 1, characterized in that In each filtering, multiple optimal algorithm iterations are performed through the quantum particle swarm algorithm; Initialize the quantum particle swarm population, initialize the optimal fitness function, use the peak signal-to-noise ratio as the fitness function, calculate the peak signal-to-noise ratio of the two-dimensional image obtained by the anisotropic diffusion equation in each filtering, update the optimal fitness function, and determine whether the optimal peak signal-to-noise ratio is obtained, and then decide the number of iterations.

5. The image enhancement method of the spatial visual neural network model according to claim 1, characterized in that: The mathematical expression of the FHN neuron is shown in Formula 1: Formula 1 Where, u is the fast-changing membrane voltage of the neuron; v is the neuron’s slow-varying recovery voltage; ε (0<ε=1) is the time constant that determines the neuron’s firing rate; a is the threshold value for transition from single potential well to double potential well, a and b are all constants, which together determine the shape of the double potential well.

6. The image enhancement method of the spatial visual neural network model according to claim 1, characterized in that The receptive field model of the diffusion equation is shown in the following formula 2: Formula 2 In the formula u 0 ( x , y ) is the initial image, div is the divergence operator, t is the scale factor, |▽ u | is the modulus of the image gradient, c 1 represents the local variance diffusion coefficient function, c 2 represents the alternative diffusion coefficient function, u 1 and u 2 represents the choice of diffusion coefficient function coefficient, which takes the value of 0 or 1, and the sum is 1. The threshold of the difference between the center point value and the mean of the eight directions is 0.

2. If it is less than 0.2, the local variance is selected, otherwise the alternative function is selected as the coefficient function.

7. An image enhancement system based on a spatial visual neural network model, characterized in that: It includes: a pulse potential signal generating unit configured to perform normalization processing on a noisy binary image; Based on the processed binary image, a 3*3 spatial FHN neural network convolution kernel template is constructed; the spatial neuron pulse potential signal corresponding to the binary image is obtained by passing the noisy signal through the FHN neural network convolution kernel: A diffusion coefficient unit is configured to traverse the spatial neuron pulse potential signal of the binary image and sequentially select a current center value point with eight surrounding directions; based on the difference between the center value of the current center value point and the eight surrounding directions, determine the corresponding local variance function or substitution function to construct a visual receptive field diffusion coefficient with a direction selection mechanism; The selection unit is configured to substitute the visual receptive field diffusion coefficient into the diffusion equation; calculate the mean and local variance of the eight directions relative to the center value point; and obtain the diffusion coefficient from the local variance function or the substitution function by determining the difference between the mean and the center value, wherein, The diffusion coefficient function of the local variance is as follows: Formula 9 The local variance function is shown in Formula 6: Formula 6 Where f(i, j) is the normalized image, and the local grayscale mean in a 3×3 square area centered at any point f(i, j) is: As shown in Formula 5: Formula 5 The alternative diffusion coefficient function is shown in Equation 10: Formula 10 Among them, the replacement function As shown in formula 8: Formula 8 In the formula δ represents the statistical difference, Θ represents the pixel value corresponding to the maximum frequency statistic replacing the central value function; where To set the absolute value of the direction difference between the 8 directions and the center point, use Formula 7: Formula 7 A graphics processing unit is configured to perform multiple spatial convolution filtering on the spatial neuron pulse potential signal of the binary image through the visual receptive field diffusion coefficient; in each filtering, multiple optimal algorithm iterations are performed through the quantum particle swarm algorithm to obtain a processed image.

8. The image enhancement system of the spatial visual neural network model according to claim 7, characterized in that: The pulse potential signal generating unit is further configured as: The noisy signal is pulse-coded by a neural network convolution kernel to obtain a spatial neuron pulse potential signal corresponding to the binary image.

9. An electronic device, characterized in that: include: processor; as well as A memory storing computer instructions of an image enhancement method of a spatial visual neural network model, wherein when the computer instructions are executed by the processor, the electronic device executes the method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that A program instruction for an image enhancement method comprising a spatial visual neural network model, wherein when the program instruction is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images