Microscopic image optimization method based on biological vision characteristics

Abstract

The application discloses a kind of based on biological visual characteristic micrograph optimization method, it is related to microorganism microscopic imaging technical field, comprising: S1, according to the characteristics of input image, the parameter of retinal model is adaptively adjusted;S2, using retinal model to carry out multilevel central vision channel and peripheral vision channel processing to input image;S3, the output data of central vision channel and peripheral vision channel are fused, and optimization image is generated.The application simulates the working principle of human visual system, especially the space-time filtering characteristics of retina, realizes the efficient optimization processing of microorganism microscopic image, solves the problems of low contrast, noise suppression not thoroughly, overlapping area separation difficulty of existing microorganism microscopic image, realizes the high-fidelity imaging of dense microorganism colony.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of microbial microscopic imaging technology, and particularly relates to a microscopic image optimization method based on biological visual characteristics. BACKGROUND

[0002] Microscopic imaging technology of microorganisms has a wide range of applications in the field of biomedicine. With the deepening of the combination of artificial intelligence and biomedicine, the requirement for the quality of microscopic images is getting higher and higher. High-quality microscopic images of microorganisms can provide more accurate sample features for artificial intelligence deep learning models. However, due to the influence of optical system noise, sample characteristics and other factors in the process of microscopic imaging, the original microscopic images obtained often have problems such as low contrast, much noise and blurred edges, and need to be optimized.

[0003] The traditional microscopic image optimization method is based on histogram equalization and Gaussian filtering, which has obvious shortcomings. Histogram equalization can easily amplify noise while enhancing contrast, linear processing leads to unnatural dynamic range expansion, and strong light areas such as the center of microorganism aggregates are prone to overexposure, and weak light areas such as the edge details of individual microorganisms are lost. Gaussian filtering can blur the image edges while denoising, resulting in loss of image details, which cannot meet the demand for high-quality microscopic images. SUMMARY

[0004] In view of the above problems in the prior art, the microscopic image optimization method based on biological visual characteristics provided by the present application solves the problem that the traditional microscopic image optimization method cannot effectively optimize the microscopic images of microorganisms, and cannot effectively optimize the low contrast, incomplete noise suppression and difficult separation of overlapping areas.

[0005] In order to achieve the above-mentioned purpose, the technical scheme adopted by the present application is as follows:

[0006] The microscopic image optimization method based on biological visual characteristics comprises the following steps:

[0007] S1, adjusting the parameters of the retina model according to the characteristics of the input image;

[0008] S2, using the retina model to perform multi-level central vision channel and peripheral vision channel processing on the input image;

[0009] S3, fusing the output data of the central vision channel and the peripheral vision channel to generate an optimized image.

[0010] Further, the S1 comprises:

[0011] The local adaptation sensitivity of photoreceptors for controlling the local brightness adaptive intensity of the image is adjusted by the following formula:

[0012] ,

[0013] where pLAS is the photoreceptor local adaptation sensitivity, min(,) is a function to find the minimum value, σ L is the standard deviation of the luminance of the input image, μ L is the mean value of the luminance of the input image;

[0014] The horizontal cell gain, which is used to control the intensity of the image halo effect and thus affect the edge enhancement effect, is adjusted by the following formula:

[0015] ,

[0016] where hCG is the horizontal cell gain, max(,) is a function to find the maximum value, C local is the local contrast of the input image;

[0017] The bipolar cell contrast enhancement, which is used to control the image contrast enhancement effect, is adjusted by the following formula:

[0018] ,

[0019] where bCC is the bipolar cell contrast enhancement;

[0020] The ganglion cell central vision channel sensitivity, which is used to control the image detail enhancement, is adjusted by the following formula:

[0021] ,

[0022] where cVGCS is the ganglion cell central vision channel sensitivity, N level is the noise level of the input image calculated using wavelet transform;

[0023] The ganglion cell peripheral vision channel sensitivity, which is used to control the image motion detection, is adjusted by the following formula:

[0024] ,

[0025] where pVGCS is the ganglion cell peripheral vision channel sensitivity, D frame is the time change evaluation value of the input image.

[0026] Further, the method for calculating the local contrast of the input image includes the following steps:

[0027] A1. For each pixel in the input image, a local window is defined which surrounds it in the positive center;

[0028] A2, calculating the standard deviation and mean value of all pixels in the local window, and taking the calculation result of the standard deviation divided by the mean value as the contrast of the local window;

[0029] A3, calculating the mean value of the contrast of the local window corresponding to each pixel of the input image, to obtain the local contrast of the input image.

[0030] Further, the retinal model of S1 and S2 includes:

[0031] a photoreceptor layer for simulating the cone cells and rod cells in the retina of the organism, performing local brightness self-adaptation on the input image;

[0032] a horizontal cell layer for simulating the horizontal cells in the retina of the organism, providing a lateral inhibition signal, and performing local contrast enhancement on the output data of the photoreceptor layer;

[0033] a bipolar cell layer for simulating the bipolar cells in the retina of the organism, further integrating and enhancing the contrast of the output data of the horizontal cell layer.

[0034] a ganglion cell layer for simulating the ganglion cells in the retina of the organism, processing the output data of the bipolar cell layer through the central visual channel and the peripheral visual channel.

[0035] Further, the operation process expression of the photoreceptor layer is:

[0036] ,

[0037] wherein, P adapted (x,y,t) is the (x,y) coordinate pixel output value of the photoreceptor layer after local brightness self-adaptation at time t, ε1 is the first constant for preventing division by zero, pLAS is the photoreceptor local adaptation sensitivity, P(x,y,t) is the (x,y) coordinate pixel output value of the photoreceptor layer without local brightness self-adaptation at time t;

[0038] ,

[0039] wherein, G σS (x,y) is the (x,y) coordinate value of the spatial Gaussian kernel, G σt (t) is the value of the time Gaussian kernel at time t, * is the convolution operation, I denoised (x,y,t) is the (x,y) coordinate pixel value of the input image at time t.

[0040] Further, the operation process expression of the horizontal cell layer is:

[0041] ,

[0042] wherein OPL(x, y, t) is the (x, y) coordinate pixel output value of the horizontal cell layer at time t, P adapted (x, y, t) is the (x, y) coordinate pixel output value of the photoreceptor layer after local luminance self-adaptive adjustment at time t, hCG is the horizontal cell gain, and H(x, y, t) is the (x, y) coordinate value of the lateral inhibition signal at time t;

[0043] ,

[0044] wherein G σS (x, y) is the (x, y) coordinate value of the spatial Gaussian kernel, G σt (t) is the value of the temporal Gaussian kernel at time t, and * is the convolution operation.

[0045] Further, the operation expression of the bipolar cell layer is:

[0046] ,

[0047] wherein IPL(x, y, t) is the (x, y) coordinate pixel output value of the horizontal cell layer at time t, B ON_enhanced (x, y, t) is the (x, y) coordinate pixel contrast enhancement value of the ON-type polar cell at time t, B OFF_enhanced (x, y, t) is the (x, y) coordinate pixel contrast enhancement value of the OFF-type polar cell at time t;

[0048] The ON-type polar cell is used for image luminance increase response.

[0049] The OFF-type polar cell is used for image luminance decrease response.

[0050] ,

[0051] ,

[0052] wherein B ON (x, y, t) is the (x, y) coordinate value of the ON-type polar cell at time t, B OFF (x, y, t) is the (x, y) coordinate value of the OFF-type polar cell at time t, and hCG is the horizontal cell gain.

[0053] ,

[0054] ,

[0055] wherein max(, ) is a function for taking the maximum value, and OPL(x, y, t) is the (x, y) coordinate pixel output value of the horizontal cell layer at time t.

[0056] Further, the operation process expression of the central vision channel of the ganglion cell layer is:

[0057] ,

[0058] Wherein, CV (x, y, t) is the (x, y) coordinate pixel output value of the central vision channel of the ganglion cell layer at t moment, OPL (x, y, t) is the (x, y) coordinate pixel output value of the horizontal cell layer at t moment, cVGCS is the sensitivity of the central vision channel of the ganglion cell, and ε2 is the second constant for preventing division by 0;

[0059] The operation process expression of the peripheral vision channel of the ganglion cell layer is:

[0060] ,

[0061] Wherein, PV (x, y, t) is the (x, y) coordinate pixel output value of the peripheral vision channel of the ganglion cell layer at t moment, ε3 is the third constant for preventing division by 0, and pVGCS is the sensitivity of the peripheral vision channel of the ganglion cell, is the operation of partial derivation with respect to time.

[0062] Further, the S3 comprises the following steps:

[0063] S31, converting the output data of the central vision channel from the BGR color space to the YCrCb color space;

[0064] S32, linearly mapping the output data of the peripheral vision channel of the ganglion cell layer to the 0-255 value range by the following formula, so as to align with the Y component value range of the YCrCb color space:

[0065] ,

[0066] Wherein, P norm is the image data after linear mapping, P is the image data before linear mapping, max () is the function of taking the maximum value, and min () is the function of taking the minimum value;

[0067] S33, reserving the Cr component and the Cb component of the output data of the central vision channel of the ganglion cell layer after conversion to the YCrCb color space, and taking the output data of the peripheral vision channel of the ganglion cell layer after linear mapping as a new Y component, so as to fuse to obtain the optimized image in the YCrCb space;

[0068] S34, converting the optimized image in the YCrCb space back to the BGR space to obtain the final optimized image.

[0069] The beneficial effects of the present application are:

[0070] (1) The application simulates the working principle of the human visual system, especially the space-time filtering characteristics of the retina, realizes efficient and optimized processing of the microscopic image of microorganisms, solves the problems of low contrast, incomplete noise suppression and difficult separation of overlapping areas in the existing microscopic image of microorganisms, and realizes high-fidelity imaging of dense microorganism groups.

[0071] (2) The application adjusts the parameters of the retinal model through the features of the input image, ensures the enhancement of local adaptability in images with large brightness changes, the enhancement of edges in images with low contrast, the enhancement of the sensitivity of the central visual channel in images with large noise, and the enhancement of the sensitivity of the peripheral visual channel in sequences with obvious motion.

[0072] (3) The photoreceptor layer of the retinal model of the application realizes adaptive brightness adjustment of different regions of the image by simulating the local adaptation mechanism of the cone cells and rod cells in the retina of living organisms, so that the microorganism features in the over-bright and over-dark regions are clearly visible at the same time.

[0073] (4) The photoreceptor layer and horizontal cell layer of the retinal model of the application simulate the spectral whitening principle of the outer plexiform layer of the retina of living organisms, reduce the low-frequency brightness energy, i.e. the average brightness, through space-time filtering, enhance the medium-frequency brightness, i.e. the details, effectively enhance the detail information in the microscopic image of microorganisms, and at the same time retain the morphological features of microorganisms.

[0074] (5) The photoreceptor layer and horizontal cell layer of the retinal model of the application are also based on the non-separable space-time filtering characteristics of the retina, effectively remove high-frequency spatial and temporal noise while retaining the edge information of microorganisms.

[0075] (6) The bipolar cell layer of the retinal model of the application improves the edge sharpness of the overlapping area by simulating the contrast enhancement mechanism of the retina, which is convenient for subsequent application of the microscopic image of microorganisms such as microorganism segmentation and counting.

[0076] (7) The ganglion cell layer of the retinal model of the application is responsible for detailed color vision and texture recognition through the central visual channel, corresponding to the small cell pathway of the biological retina; through the peripheral visual channel, it is responsible for sensitive transient signal detection of edge structure recognition such as motion and events, corresponding to the large cell pathway of the biological retina.

[0077] (8) The application fuses the output data of the central visual channel and the peripheral visual channel, retains the Cr component and the Cb component of the output data of the central visual channel of the ganglion cell layer after conversion to the YCrCb color space, that is, retains the chrominance information of the central visual channel; and takes the output data of the ganglion cell layer of the peripheral visual channel after linear mapping as a new Y component, that is, injects the motion and edge features of the peripheral visual channel, and fully utilizes the biological mechanism that the large cell pathway of the retina dominates motion perception and the small cell pathway is responsible for color identification. BRIEF DESCRIPTION OF DRAWINGS

[0078] Figure 1 A flowchart of a microimage optimization method based on biological visual characteristics provided for an embodiment of the application is shown in the figure;

[0079] Figure 2 A schematic diagram of the biological retina structure for reference when setting the retina model for an embodiment of the application is shown in the figure;

[0080] Figure 3 A structure diagram of the retina model for an embodiment of the application is shown in the figure;

[0081] Figure 4 An input image for an embodiment of the application is shown in the figure;

[0082] Figure 5 An image output by the central visual channel for an embodiment of the application is shown in the figure;

[0083] Figure 6 An image output by the peripheral visual channel for an embodiment of the application is shown in the figure;

[0084] Figure 7 The final optimized image for an embodiment of the application is shown in the figure. DETAILED DESCRIPTION

[0085] The specific embodiments of the application are described below to facilitate the understanding of the application by those skilled in the art, but it should be clear that the application is not limited to the scope of the specific embodiments, and for those skilled in the art, any changes that are obvious within the spirit and scope of the application as defined and determined by the appended claims are obvious, and all applications utilizing the concept of the application are within the scope of protection.

[0086] As Figure 1 shown, in an embodiment of the application, the microimage optimization method based on biological visual characteristics comprises the following steps:

[0087] S1, according to the characteristics of the input image, adaptively adjusting the parameters of the retina model, including:

[0088] The photoreceptor local adaptation sensitivity for controlling the local brightness adaptive intensity of the image is adjusted by the following formula:

[0089] ,

[0090] wherein pLAS is the photoreceptor local adaptation sensitivity, min(,) is a function to find the minimum value, σ L is the standard deviation of the luminance of the input image, μ L is the mean value of the luminance of the input image;

[0091] The horizontal cell gain, which is used to control the intensity of the image halo effect and further affect the edge enhancement effect, is adjusted by the following formula:

[0092] ,

[0093] wherein hCG is the horizontal cell gain, max(,) is a function to find the maximum value; C local is the local contrast of the input image C local The calculation method of the local contrast C

[0094] The bipolar cell contrast enhancement, which is used to control the contrast enhancement effect of the image, is adjusted by the following formula:

[0095] ,

[0096] wherein bCC is the bipolar cell contrast enhancement;

[0097] The ganglion cell central vision channel sensitivity, which is used to control the image detail enhancement, is adjusted by the following formula:

[0098] ,

[0099] wherein cVGCS is the ganglion cell central vision channel sensitivity, N level is the noise level of the input image calculated using wavelet transform;

[0100] The ganglion cell peripheral vision channel sensitivity, which is used to control the image motion detection, is adjusted by the following formula:

[0101] ,

[0102] wherein pVGCS is the ganglion cell peripheral vision channel sensitivity, D frame is the time variation evaluation value of the input image;

[0103] If the input image is a dynamic video sequence, D is obtained by calculating the inter-frame difference frame If the input image is a static picture, D frame is 0.

[0104] The application adjusts the parameters of the retina model according to the characteristics of the input image, ensuring that the local adaptability is enhanced in images with large brightness changes, the edges are enhanced in images with low contrast, the sensitivity of the central vision channel is increased in images with large noise, and the sensitivity of the peripheral vision channel is increased in sequences with obvious motion.

[0105] S2, using the retina model to perform multi-level central vision channel and peripheral vision channel processing on the input image.

[0106] The human retina is an important part of the visual system, responsible for converting light signals into neural signals and performing preliminary processing.

[0107] As shown in Figure 2 , the biological retina contains multiple layers of cells, mainly including photoreceptors (cone cells and rod cells), horizontal cells, bipolar cells, amacrine cells and ganglion cells. These cells form a complex neural network and perform a series of signal processing functions.

[0108] Photoreceptors form synapses with horizontal cells and bipolar cells in the first synaptic layer, the outer plexiform layer (OPL), which helps to enhance contrast and color texture. In the second synaptic layer, the inner plexiform layer (IPL), bipolar cells and amacrine cells form synapses with ganglion cells, and the IPL amacrine cells can respond to moving objects.

[0109] The information processing of the biological retina is mainly carried out through two pathways: the central vision pathway, which is responsible for detailed color vision and texture recognition, corresponding to the small cell pathway; and the peripheral vision pathway, which is responsible for sensitive transient signal detection (such as motion and events) and edge structure recognition, corresponding to the large cell pathway.

[0110] The main processing characteristics of the biological retina include: 1) local logarithmic brightness compression: realized at the photoreceptor and ganglion cell level, so that very bright and very dark areas can present clear details in the same picture; 2) spectral whitening in the outer plexiform layer: achieved through spatiotemporal filtering of photoreceptors and horizontal cells, reducing low-frequency brightness energy (average brightness) and enhancing medium-frequency brightness (details); 3) high-frequency noise filtering: through non-separable spatiotemporal filtering, effectively reducing high-frequency spatial and temporal noise.

[0111] Based on this, asFigure 3 The retina model of the present application comprises:

[0112] a photoreceptor layer for simulating the cone cells and rod cells in the retina of the living being, performing local luminance self-adaptation on the input image;

[0113] a horizontal cell layer for simulating the horizontal cells in the retina of the living being, providing a lateral inhibition signal, and performing local contrast enhancement on the output data of the photoreceptor layer;

[0114] a bipolar cell layer for simulating the bipolar cells in the retina of the living being, further integrating and enhancing the contrast of the output data of the horizontal cell layer.

[0115] a ganglion cell layer for simulating the ganglion cells in the retina of the living being, processing the output data of the bipolar cell layer through the central visual channel and the peripheral visual channel.

[0116] The operation process expression of the photoreceptor layer is:

[0117] ,

[0118] wherein, P adapted (x,y,t) is the (x,y) coordinate pixel output value of the photoreceptor layer after local luminance self-adaptation at time t, ε1 is the first constant for preventing division by zero, pLAS is the photoreceptor local adaptation sensitivity, P(x,y,t) is the (x,y) coordinate pixel output value of the photoreceptor layer without local luminance self-adaptation at time t;

[0119] ,

[0120] wherein, G σS (x,y) is the (x,y) coordinate value of the spatial Gaussian kernel, G σt (t) is the value of the time Gaussian kernel at time t, * is the convolution operation, I denoised (x,y,t) is the (x,y) coordinate pixel value of the input image at time t.

[0121] The photoreceptor layer of the retina model of the present application realizes adaptive luminance adjustment of different regions of the image by simulating the local adaptation mechanism of the cone cells and rod cells in the retina of the living being, so that the microbial features of the over-bright and over-dark regions are both clearly visible.

[0122] The operation process expression of the horizontal cell layer is:

[0123] ,

[0124] wherein, OPL(x,y,t) is the (x,y) coordinate pixel output value of the horizontal cell layer at time t, Padapted (x,y,t) is the (x,y) coordinate pixel output value of the photoreceptor layer after local brightness self-adaptive adjustment at t moment, hCG is the horizontal cell gain, and H(x,y,t) is the (x,y) coordinate value of the lateral inhibition signal at t moment;

[0125] ,

[0126] Wherein, G σS (x,y) is the (x,y) coordinate value of the spatial Gaussian kernel, G σt (t) is the t moment value of the time Gaussian kernel, and * is the convolution operation.

[0127] The photoreceptor layer and the horizontal cell layer of the retina model of the application effectively enhance the detail information in the microorganism microscopic image by simulating the spectral whitening principle of the outer plexiform layer of the biological retina, reducing the low-frequency brightness energy, i.e. the average brightness, and enhancing the medium-frequency brightness, i.e. the details, while retaining the morphological characteristics of the microorganism.

[0128] The photoreceptor layer and the horizontal cell layer are also based on the non-separable space-time filtering characteristics of the retina, effectively remove the high-frequency spatial and temporal noise while retaining the edge information of the microorganism.

[0129] The operation expression of the bipolar cell layer is:

[0130] ,

[0131] Wherein, IPL(x,y,t) is the (x,y) coordinate pixel output value of the horizontal cell layer at t moment, B ON_enhanced (x,y,t) is the (x,y) coordinate pixel contrast enhancement value of the ON type bipolar cell at t moment, B OFF_enhanced (x,y,t) is the (x,y) coordinate pixel contrast enhancement value of the OFF type bipolar cell at t moment;

[0132] The ON type bipolar cell is used for image brightness increase response;

[0133] The OFF type bipolar cell is used for image brightness decrease response;

[0134] ,

[0135] ,

[0136] Wherein, B ON (x,y,t) is the (x,y) coordinate value of the ON type bipolar cell at t moment, B OFF (x,y,t) is the (x,y) coordinate value of the OFF type bipolar cell at t moment, and hCG is the horizontal cell gain.

[0137] ,

[0138] ,

[0139] wherein max(, ) is a function of taking maximum value, and OPL(x,y,t) is the pixel output value of (x,y) coordinate of horizontal cell layer at t moment.

[0140] The bipolar cell layer of the retina model improves the edge definition of the overlapping area by simulating the contrast enhancement mechanism of the retina, and facilitates the subsequent application of the microbial microscopic image such as microbial segmentation and counting.

[0141] The operation process expression of the central visual channel of the ganglion cell layer is as follows:

[0142] ,

[0143] wherein CV(x,y,t) is the pixel output value of (x,y) coordinate of the central visual channel of the ganglion cell layer at t moment, OPL(x,y,t) is the pixel output value of (x,y) coordinate of the horizontal cell layer at t moment, cVGCS is the sensitivity of the central visual channel of the ganglion cell, and ε2 is the second constant for preventing division by 0;

[0144] The operation process expression of the peripheral visual channel of the ganglion cell layer is as follows:

[0145] ,

[0146] wherein PV(x,y,t) is the pixel output value of (x,y) coordinate of the peripheral visual channel of the ganglion cell layer at t moment, ε3 is the third constant for preventing division by 0, and pVGCS is the sensitivity of the peripheral visual channel of the ganglion cell, is the operation of partial derivative with respect to time.

[0147] The ganglion cell layer of the retina model is responsible for detailed color vision and texture recognition through the central visual channel, corresponding to the small cell pathway of the biological retina, and is responsible for sensitive transient signal detection of edge structure recognition such as motion and event through the peripheral visual channel, corresponding to the large cell pathway of the biological retina.

[0148] S3, the output data of the central visual channel and the peripheral visual channel are fused to generate an optimized image, including the following steps:

[0149] S31, the output data of the central visual channel is converted from BGR color space to YCrCb color space;

[0150] S32, linearly map the output data of the peripheral visual channel of the ganglion cell layer to the range of 0 to 255 values by the following formula, so as to align with the range of Y component values of the YCrCb color space:

[0151] ,

[0152] wherein, P norm is the image data after linear mapping, P is the image data before linear mapping, max() is a function of taking maximum value, and min() is a function of taking minimum value;

[0153] S33, retain the Cr component and the Cb component of the output data of the central visual channel of the ganglion cell layer after conversion to the YCrCb color space, and meanwhile take the output data of the peripheral visual channel of the ganglion cell layer after linear mapping as a new Y component, so as to fuse to obtain an optimized image in the YCrCb space;

[0154] S34, convert the optimized image in the YCrCb space back to the BGR space to obtain a final optimized image.

[0155] The application fuses the output data of the central visual channel and the peripheral visual channel, retains the Cr component and the Cb component of the output data of the central visual channel of the ganglion cell layer after conversion to the YCrCb color space, that is, retains the chroma information of the central visual channel, and meanwhile takes the output data of the peripheral visual channel of the ganglion cell layer after linear mapping as a new Y component, that is, injects the motion and edge features of the peripheral visual channel, and fully utilizes the biological mechanism that the large cell pathway of the retina dominates motion perception and the small cell pathway is responsible for color identification.

[0156] In the embodiment, the input image to be processed is as shown in Figure 4 , the image output by the central visual channel is as shown in Figure 5 , the image output by the peripheral visual channel is as shown in Figure 6 , and the final optimized image is as shown in Figure 7 .

[0157] In summary, the application simulates the working principle of the human visual system, especially the space-time filtering characteristics of the retina, realizes efficient and optimized processing of the microscopic images of microorganisms, and solves the problems of low contrast, incomplete noise suppression and difficult separation of overlapping areas of the existing microscopic images of microorganisms, and realizes high-fidelity imaging of dense microorganism groups.

[0158] The above is only the preferred embodiment of the application, and is not used to limit the application. For those skilled in the art, the application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the application shall be included in the protection scope of the application.

Claims

1. A microscopic image optimization method based on biological visual characteristics, characterized in that: The following steps are involved: S1. Adaptively adjust the parameters of the retinal model according to the characteristics of the input image; S2, using the retinal model to process the input image in multiple levels of central and peripheral visual channels; S3, fusing the output data of the central visual channel and the peripheral visual channel to generate an optimized image; Said S1 comprises: The local adaptation sensitivity of the photoreceptors used to control the strength of the local brightness adaptation of the image is adjusted by the following formula: Where pLAS is the local adaptation sensitivity of the photoreceptor, min(,) is the function to find the minimum value, σ L is the brightness standard deviation of the input image, μ L is the mean brightness of the input image; The horizontal cell gain, which is used to control the intensity of the image halo effect and thus affect the edge enhancement effect, is adjusted by the following formula: , Among them, hCG is the horizontal cell gain, max(,) is the function to find the maximum value, C local is the local contrast of the input image; The bipolar cell contrast enhancement degree used to control the image contrast enhancement effect is adjusted by the following formula: , Among them, bCC is the bipolar cell contrast enhancement; The sensitivity of the central visual channel of ganglion cells used to control image detail enhancement is adjusted by the following formula: , Among them, cVGCS is the sensitivity of the central visual channel of ganglion cells, N level is the noise level of the input image calculated using wavelet transform; The sensitivity of the peripheral visual channel of ganglion cells used to control image motion detection is adjusted by the following formula: , Among them, pVGCS is the sensitivity of the peripheral visual channel of ganglion cells, D frame Evaluate the temporal variation of the input image; The method for calculating the local contrast of the input image comprises the following steps: A1. For each pixel in the input image, a local window is defined that surrounds the pixel at its center. A2. Calculate the standard deviation and mean of all pixels in the local window, and divide the standard deviation by the mean as the contrast of the local window; A3. averaging the contrasts of the local windows corresponding to all pixels of the input image to obtain the local contrast of the input image.

2. The microscopic image optimization method based on biological visual characteristics according to claim 1, characterized in that: The S1 and S2 retinal models include: The photoreceptor layer is used to simulate the cones and rods in the biological retina and perform local brightness adaptation on the input image; The horizontal cell layer is used to simulate the horizontal cells in the biological retina, providing lateral inhibition signals and performing local contrast enhancement on the output data of the photoreceptor layer; The bipolar cell layer is used to simulate the bipolar cells in the biological retina and further integrate the output data of the horizontal cell layer and enhance the contrast; The ganglion cell layer, used to simulate the ganglion cells in the biological retina, processes the output data of the bipolar cell layer through the central visual channel and the peripheral visual channel.

3. The microscopic image optimization method based on biological visual characteristics according to claim 2, characterized in that: The calculation process expression of the photoreceptor layer is: , Among them, P adapted (x, y, t) is the pixel output value at the (x, y) coordinate of the photoreceptor layer at time t after local brightness adaptive adjustment, ε1 is the first constant used to prevent division by zero, pLAS is the local adaptation sensitivity of the photoreceptor, and P(x, y, t) is the pixel output value at the (x, y) coordinate of the photoreceptor layer at time t without local brightness adaptive adjustment; ， Among them, G σS (x,y) is the (x,y) coordinate value of the spatial Gaussian kernel, G σt (t) is the time value of the Gaussian kernel at time t, * is the convolution operation, I denoised (x,y,t) is the pixel value at the (x,y) coordinate of the input image at time t.

4. The microscopic image optimization method based on biological visual characteristics according to claim 2, characterized in that: The operation expression of the horizontal cell layer is: , Among them, OPL (x, y, t) is the (x, y) coordinate pixel output value of the horizontal cell layer at time t, P adapted (x, y, t) is the (x, y) coordinate pixel output value of the photoreceptor layer after local brightness adaptive adjustment at time t, hCG is the horizontal cell gain, and H(x, y, t) is the (x, y) coordinate value of the lateral inhibition signal at time t; , Among them, G σS (x,y) is the (x,y) coordinate value of the spatial Gaussian kernel, G σt (t) is the time value of the Gaussian kernel at time t, and * is the convolution operation.

5. The microscopic image optimization method based on biological visual characteristics according to claim 2, characterized in that: The operational expression of the bipolar cell layer is: Among them, IPL (x, y, t) is the (x, y) coordinate pixel output value of the horizontal cell layer at time t, B ON_enhanced (x, y, t) is the pixel contrast enhancement value of the (x, y) coordinate of the ON polar cell at time t, B OFF_enhanced (x, y, t) is the (x, y) coordinate pixel contrast enhancement value of the OFF polarity cell at time t; The ON-type polarity cells are used to respond to increased image brightness; The OFF-type polarity cells are used to respond to image brightness reduction; , , Among them, B ON (x, y, t) is the (x, y) coordinate value of ON polar cell at time t, B OFF (x, y, t) is the (x, y) coordinate value of the OFF polar cell at time t, and hCG is the horizontal cell gain; ， ， Where max(,) is the function for finding the maximum value, and OPL(x,y,t) is the pixel output value of the (x,y) coordinate of the horizontal cell layer at time t.

6. The microscopic image optimization method based on biological visual characteristics according to claim 2, characterized in that: The operation process expression of the central visual channel of the ganglion cell layer is: , Where CV (x, y, t) is the (x, y) coordinate pixel output value of the central visual channel of the ganglion cell layer at time t, OPL (x, y, t) is the (x, y) coordinate pixel output value of the horizontal cell layer at time t, cVGCS is the sensitivity of the central visual channel of the ganglion cell, and ε2 is a second constant used to prevent division by zero; The computational expression of the peripheral visual channel of the ganglion cell layer is: , Where PV (x, y, t) is the (x, y) coordinate pixel output value of the peripheral visual channel of the ganglion cell layer at time t, ε3 is the third constant used to prevent division by zero, and pVGCS is the sensitivity of the ganglion cell peripheral visual channel. is the operation of finding the partial derivative with respect to time.

7. The microscopic image optimization method based on biological visual characteristics according to claim 1, characterized in that: The S3 includes the following sub-steps: S31, converting the output data of the central visual channel from the BGR color space to the YCrCb color space; S32. Linearly map the output data of the peripheral visual channel of the ganglion cell layer to a value range of 0 to 255 using the following formula, so that it is aligned with the value range of the Y component of the YCrCb color space: , Among them, P norm is the image data after linear mapping, P is the image data before linear mapping, max() is the function for finding the maximum value, and min() is the function for finding the minimum value; S33, retaining the Cr component and Cb component of the output data of the central visual channel of the ganglion cell layer after conversion to the YCrCb color space, and using the output data of the peripheral visual channel of the ganglion cell layer after linear mapping as a new Y component, and fusing them to obtain an optimized image in the YCrCb space; S34: Convert the optimized image in the YCrCb space back to the BGR space to obtain the final optimized image.

Images