Image processing method and device, computer equipment, readable storage medium and program product

By extracting and fusing cluster point images in the image, determining contrast based on pixel statistics, and selecting appropriate sharpening operator processing, the problems of low image processing efficiency and error recognition in traditional methods are solved, and more efficient image recognition is achieved.

CN119027343APending Publication Date: 2024-11-26ZHUHAI GENDOW BIOTECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410963011.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The traditional cluster point extraction method is inefficient in image processing, especially when the two cluster points are close, it is easy to have the risk of identification errors, and the interference correction method based on the distance of adjacent cluster points is not efficient.

Method used

By acquiring the image to be processed, extracting sub-images of multiple cluster points, fusing them into cluster point fusion images, and determining pixel contrast based on the pixel statistics of the fused image, selecting an appropriate sharpening operator for sharpening processing, reducing adjacent clusters Point of interference.

Benefits of technology

The efficiency and accuracy of image processing are improved, the risk of identification errors is reduced, and the effect of image recognition is enhanced through adaptive selection of sharpening operators.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119027343A_ABST
    Figure CN119027343A_ABST
Patent Text Reader

Abstract

The invention relates to an image processing method and device, computer equipment, a readable storage medium and a program product. The method comprises the following steps: acquiring a to-be-processed image; extracting sub-images corresponding to the plurality of cluster points in the to-be-processed image, and fusing the plurality of sub-images to obtain a cluster point fused image corresponding to the to-be-processed image; based on the pixel statistical information of the first direction and the pixel statistical information of the second direction in the cluster point fusion image, determining a pixel contrast corresponding to the cluster point fusion image; and based on the target sharpening operator corresponding to the contrast level to which the pixel contrast belongs, sharpening the to-be-processed image to obtain a target image. By adopting the method, the image processing efficiency can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an image processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] With the development of image recognition technology, the technology of extracting cluster points from images has emerged. For example, in the field of gene sequencing, gene sequences are detected by extracting cluster points from fluorescent images. However, when the distance between two cluster points is relatively close, the two cluster points will interfere with each other, increasing the risk of recognition errors.

[0003] Traditional cluster point extraction methods usually calculate the distance between two adjacent cluster points, find the corresponding interference coefficient according to the distance between the cluster points, and correct the two adjacent cluster points based on the interference coefficient, which has the problem of low image processing efficiency. Summary of the invention

[0004] Based on this, it is necessary to provide an image processing method, apparatus, computer device, computer-readable storage medium and computer program product that can improve image processing efficiency in response to the above technical problems.

[0005] In a first aspect, the present application provides an image processing method, comprising:

[0006] Get the image to be processed;

[0007] Extracting sub-images corresponding to a plurality of cluster points in the image to be processed, and fusing the plurality of sub-images to obtain a cluster point fused image corresponding to the image to be processed;

[0008] Determine a pixel contrast corresponding to the cluster point fusion image based on pixel statistical information in a first direction and pixel statistical information in a second direction in the cluster point fusion image;

[0009] Based on the target sharpening operator corresponding to the contrast level to which the pixel contrast belongs, the image to be processed is sharpened to obtain a target image.

[0010] In a second aspect, the present application further provides an image processing device, comprising:

[0011] An image acquisition module, used for acquiring an image to be processed;

[0012] A cluster point extraction module is used to extract sub-images corresponding to multiple cluster points in the image to be processed, and fuse the multiple sub-images to obtain a cluster point fused image corresponding to the image to be processed;

[0013] A contrast determination module, used to determine a pixel contrast corresponding to the cluster point fusion image based on pixel statistics information in a first direction and pixel statistics information in a second direction in the cluster point fusion image;

[0014] The image sharpening module is used to perform sharpening processing on the image to be processed based on the target sharpening operator corresponding to the contrast level to which the pixel contrast belongs, so as to obtain the target image.

[0015] In one embodiment, the image processing apparatus further includes:

[0016] The operator determination module is used to obtain a sample image; perform different degrees of smoothing on the sample image, perform different degrees of sharpening on the sample image, and obtain reference images corresponding to multiple contrast levels; for any contrast level, perform sharpening on the reference image corresponding to the contrast level according to each candidate sharpening operator, perform target object recognition on the sharpened reference image, determine a sharpening effect score according to the target object recognition result, and determine a target sharpening operator corresponding to the contrast level according to the sharpening effect scores corresponding to each candidate sharpening operator.

[0017] In one embodiment, the cluster point extraction module is further used for:

[0018] Based on the brightness threshold of the pixel points, multiple target pixel points are determined from the image to be processed to form a cluster point area corresponding to the image to be processed; the cluster point area is subjected to connected domain analysis to obtain sub-images corresponding to multiple cluster points in the image to be processed.

[0019] In one embodiment, the cluster point extraction module is further used for:

[0020] For any cluster point, when the number of adjacent cluster points of the cluster point in the corresponding central image area is less than a preset number, the cluster point is determined as a target cluster point; the sub-images corresponding to each target cluster point are fused to obtain a cluster point fusion image corresponding to the image to be processed.

[0021] In one embodiment, the contrast determination module is further configured to:

[0022] The pixel mean values ​​corresponding to each row in the cluster point fusion image are counted to obtain the pixel statistical information of the first direction in the cluster point fusion image; the pixel mean values ​​corresponding to each row in the cluster point fusion image are counted to obtain the pixel statistical information of the second direction in the cluster point fusion image; the pixel statistical information of the first direction and the pixel statistical information of the second direction in the cluster point fusion image are fused to obtain the comprehensive pixel statistical information corresponding to the cluster point fusion image; based on the pixel maximum value in the comprehensive pixel statistical information, the pixel contrast corresponding to the cluster point fusion image is determined.

[0023] In one embodiment, the image to be processed is a fluorescent image containing base information obtained by image acquisition of nucleic acid fragments, the cluster points are fluorescent points corresponding to the base information in the nucleic acid fragments, and the target image is used for gene sequencing.

[0024] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned image processing method when executing the computer program.

[0025] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above-mentioned image processing method when executed by a processor.

[0026] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned image processing method when executed by a processor.

[0027] The above-mentioned image processing method, device, computer equipment, computer-readable storage medium and computer program product obtain the image to be processed, extract the sub-images corresponding to the multiple cluster points in the image to be processed, and fuse the multiple sub-images to obtain the cluster point fusion image corresponding to the image to be processed. Then, based on the pixel statistics in the first direction and the pixel statistics in the second direction in the cluster point fusion image, the pixel contrast corresponding to the cluster point fusion image is determined. Finally, based on the target sharpening operator corresponding to the contrast level to which the pixel contrast belongs, the image to be processed is sharpened to obtain the target image. In this way, by extracting multiple cluster points from the image to be processed, and fusing the sub-images corresponding to each cluster point to obtain the cluster point fusion image, the pixel statistics in the first direction and the second direction in the cluster point fusion image are comprehensively analyzed, and the pixel contrast obtained can accurately reflect the overall image quality of the image to be processed, for example, the clarity and contrast of the image. Then, the target sharpening operator corresponding to the pixel contrast corresponding to the image to be processed is used to sharpen the image to be processed, so that the best target sharpening operator is adaptively selected to perform sharpening processing according to the image quality of the image to be processed, which can effectively improve the effect of sharpening processing, thereby improving the accuracy of image recognition. In addition, compared with the traditional method of searching for the corresponding interference coefficient according to the distance between adjacent cluster points and correcting two adjacent cluster points based on the interference coefficient, the present application proposes determining the contrast level based on the cluster point fusion image and then performing sharpening processing according to the target sharpening operator corresponding to the contrast level. This can quickly eliminate the interference between adjacent cluster points, thereby improving the efficiency of image processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0029] FIG1 is a diagram of an application environment of an image processing method according to an embodiment;

[0030] FIG2 is a schematic diagram of a flow chart of an image processing method in one embodiment;

[0031] FIG3 is a schematic diagram of a fluorescent image in one embodiment;

[0032] FIG4 is a schematic diagram of a fluorescent image cluster point in one embodiment;

[0033] FIG5 is a schematic diagram of a process for determining a target sharpening operator in one embodiment;

[0034] FIG6 is a schematic diagram of integrated pixel statistical information in one embodiment;

[0035] Figure 7 is a schematic flow chart of an image processing method in another embodiment;

[0036] FIG8 is a block diagram of an image processing device according to an embodiment;

[0037] FIG9 is a diagram showing the internal structure of a computer device in one embodiment;

[0038] FIG. 10 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0040] The image processing method provided in the embodiment of the present application can be applied in the application environment shown in FIG. 1. The terminal 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on a cloud or other network server. The terminal 102 collects the image to be processed and sends the image to be processed to the server 104. The server 104 obtains the image to be processed, extracts the sub-images corresponding to the multiple cluster points in the image to be processed, and fuses the multiple sub-images to obtain the cluster point fusion image corresponding to the image to be processed. The server 104 determines the pixel contrast corresponding to the cluster point fusion image based on the pixel statistics in the first direction and the pixel statistics in the second direction in the cluster point fusion image. The server 104 performs sharpening processing on the image to be processed based on the target sharpening operator corresponding to the contrast level to which the pixel contrast belongs, and obtains the target image. The server 104 can send the target image to the terminal 102, and the terminal 102 can display the target image to the user. The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 may be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0041] In an exemplary embodiment, as shown in FIG2 , an image processing method is provided, and the method is applied to a computer device as an example for explanation. The computer device may be a terminal or a server, and the method may be executed by the terminal or the server itself alone, or may be implemented through interaction between the terminal and the server. The image processing method includes the following steps 202 to 208. Among them:

[0042] Step 202: Obtain an image to be processed.

[0043] The image to be processed refers to an image that needs to be preprocessed before image recognition. For example, in the application scenario of text recognition, the image to be processed can be an image containing text acquired by an image acquisition device; in the application scenario of gene sequencing, the image to be processed can be an image acquired by an image acquisition device of a nucleic acid fragment labeled with a fluorescent dye; and so on.

[0044] Exemplarily, the server obtains the image to be processed directly acquired by the image acquisition device. After acquiring the image to be processed, it is necessary to perform image preprocessing on the image to be processed, and then perform image recognition on the image obtained after the preprocessing. By preprocessing the image to be processed in advance, the image quality can be effectively improved, thereby improving the accuracy of image recognition. In the actual implementation process, image preprocessing includes steps such as denoising and sharpening.

[0045] Step 204 , extracting sub-images corresponding to a plurality of cluster points in the image to be processed, and fusing the plurality of sub-images to obtain a cluster point fused image corresponding to the image to be processed.

[0046] Among them, cluster points refer to a group of fluorescent points composed of densely distributed and high-brightness fluorescent points in an image. For example, when the image to be processed is a fluorescent image obtained by image acquisition of a nucleic acid fragment in which bases are labeled with fluorescent dyes, the image to be processed can be as shown in FIG3, where a large number of cluster points are distributed in the image to be processed, and cluster points refer to the dots with high brightness in FIG3. Specifically, as shown in FIG4, each cluster point is composed of multiple pixel points with high brightness, and cluster point A and cluster point B are two adjacent cluster points.

[0047] The sub-image corresponding to the cluster point refers to the sub-images corresponding to each cluster point extracted from the image to be processed. For example, the image corresponding to the 10*10 pixel range centered on the cluster point itself can be used as the sub-image corresponding to the cluster point.

[0048] The cluster point fusion image refers to an image obtained by fusing sub-images corresponding to multiple cluster points in the image to be processed.

[0049] Exemplarily, the server extracts sub-images corresponding to multiple cluster points in the image to be processed. Then, the pixel values ​​corresponding to the same pixel position in each sub-image are accumulated to obtain the pixel values ​​corresponding to each pixel position, and the initial fused image is obtained from the pixel values ​​corresponding to each pixel position. Then, based on the number of accumulated sub-images, the pixel values ​​corresponding to each pixel point in the initial fused image are averaged to obtain a cluster point fused image. The pixel value of each pixel point on the cluster point fused image represents the average pixel value of each sub-image at the pixel position.

[0050] Step 206: Determine the pixel contrast corresponding to the cluster point fusion image based on the pixel statistical information in the first direction and the pixel statistical information in the second direction in the cluster point fusion image.

[0051] The first direction and the second direction are two linear directions perpendicular to each other. In actual implementation, the first direction and the second direction may be the horizontal direction and the vertical direction, that is, the x-axis direction and the y-axis direction.

[0052] The pixel statistics corresponding to the first direction are used to characterize the variation trend of the pixel values ​​of each pixel point in the cluster point fusion image in the first direction. The pixel statistics corresponding to the second direction are used to characterize the variation trend of the pixel values ​​of each pixel point in the cluster point fusion image in the second direction.

[0053] Pixel contrast is used to characterize the degree to which the image to be processed needs to be sharpened, and the pixel contrast is positively correlated with the degree to which the image to be processed needs to be sharpened.

[0054] Exemplarily, the server counts the changing trend of the pixel value of each pixel point on the cluster point fusion image in the first direction to obtain the first pixel statistical information. The changing trend of the pixel value of each pixel point on the cluster point fusion image in the second direction is counted to obtain the second pixel statistical value. Then, the pixel statistical information in the first direction and the pixel statistical information in the second direction are fused to determine the pixel contrast corresponding to the cluster point fusion image. For example, when the first direction is the x direction, the pixel average value corresponding to each column of pixels in the cluster point fusion image is counted, and the pixel average values ​​corresponding to each column of pixels respectively constitute the pixel statistical information of the cluster point fusion image in the first direction. When the second direction is the y direction, the pixel average value corresponding to each row of pixels in the cluster point fusion image is counted, and the pixel average values ​​corresponding to each row of pixels respectively constitute the pixel statistical information of the cluster point fusion image in the second direction. The pixel statistical information in the first direction and the pixel statistical information in the second direction are fused to obtain the comprehensive pixel statistical information corresponding to the cluster point fusion image. The pixel contrast corresponding to the cluster point fusion image is determined based on the comprehensive pixel statistical information.

[0055] Step 208: Based on the target sharpening operator corresponding to the contrast level to which the pixel contrast belongs, the image to be processed is sharpened to obtain a target image.

[0056] The target sharpening operator corresponding to the contrast level refers to a sharpening operator with the best sharpening effect set for the contrast level, with respect to the degree of sharpening required for the image at the contrast level.

[0057] The target image refers to the image obtained after the image to be processed is sharpened according to the target sharpening operator.

[0058] Exemplarily, the pixel contrast corresponding to the cluster point fusion image is compared with the pixel contrast corresponding to each contrast level to determine the contrast level to which the image to be processed belongs. Then, the target sharpening operator corresponding to the contrast level to which the image to be processed belongs is obtained, and the image to be processed is sharpened based on the target sharpening operator to obtain the target image corresponding to the image to be processed. Then, image recognition can be performed on the target image. For example, when the image to be processed is a text image, after the image to be processed is sharpened according to the target sharpening operator to obtain the target image, the target image is input into the text recognition model to obtain the text recognition result corresponding to the image to be processed; when the image to be processed is an image obtained by image acquisition of a nucleic acid fragment in which bases are labeled with fluorescent dyes, after the image to be processed is sharpened according to the target sharpening operator to obtain the target image, base recognition is performed on the target image to obtain the gene sequencing result corresponding to the image to be processed; and so on.

[0059] In the above-mentioned image processing method, by acquiring the image to be processed, extracting the sub-images corresponding to the multiple cluster points in the image to be processed, and fusing the multiple sub-images to obtain the cluster point fusion image corresponding to the image to be processed. Then, based on the pixel statistics in the first direction and the pixel statistics in the second direction in the cluster point fusion image, the pixel contrast corresponding to the cluster point fusion image is determined. Finally, based on the target sharpening operator corresponding to the contrast level to which the pixel contrast belongs, the image to be processed is sharpened to obtain the target image. In this way, by extracting multiple cluster points from the image to be processed, fusing the sub-images corresponding to each cluster point to obtain the cluster point fusion image, and comprehensively analyzing the pixel statistics in the first direction and the second direction in the cluster point fusion image, the obtained pixel contrast can accurately reflect the overall image quality of the image to be processed, for example, the clarity and contrast of the image. Then, the target sharpening operator corresponding to the pixel contrast corresponding to the image to be processed is used to sharpen the image to be processed, so that the best target sharpening operator is adaptively selected to perform sharpening processing according to the image quality of the image to be processed, which can effectively improve the effect of sharpening processing, thereby improving the accuracy of image recognition. In addition, compared with the traditional method of searching for the corresponding interference coefficient according to the distance between adjacent cluster points and correcting two adjacent cluster points based on the interference coefficient, the present application proposes determining the contrast level based on the cluster point fusion image and then performing sharpening processing according to the target sharpening operator corresponding to the contrast level. This can quickly eliminate the interference between adjacent cluster points, thereby improving the efficiency of image processing.

[0060] In an exemplary embodiment, as shown in FIG5 , the image processing method further includes steps 502 to 506. Among them:

[0061] Step 502: Acquire a sample image.

[0062] Step 504 , performing smoothing processing to the sample image to different degrees, and performing sharpening processing to the sample image to different degrees, to obtain reference images corresponding to a plurality of contrast levels.

[0063] Step 506, for any contrast level, sharpen the reference image corresponding to the contrast level according to each candidate sharpening operator, identify the target object of the sharpened reference image, determine the sharpening effect score according to the target object identification result, and determine the target sharpening operator corresponding to the contrast level according to the sharpening effect scores corresponding to each candidate sharpening operator.

[0064] The sample image refers to the original sample image used to generate reference images of different contrast levels. The candidate sharpening operator refers to a plurality of preset sharpening operators. The target object refers to the object to be recognized, for example, it can be text, gene sequence, face, etc. The sharpening effect score is used to indicate the accuracy of the target object recognition result.

[0065] Exemplarily, the server obtains a sample image, performs smoothing processing on the sample image to different degrees, obtains reference images corresponding to multiple different low contrast levels, and performs sharpening processing on the sample image to different degrees, obtains reference images corresponding to multiple different high contrast levels. In the actual implementation process, the sample image can be smoothed by a mean filter, a Gaussian filter, or a low-pass filter, and the sample image can be sharpened by a Laplace filter or a high-pass filter. After obtaining the reference images corresponding to multiple contrast levels, multiple candidate sharpening operators are determined according to a certain step size.

[0066] In the actual implementation process, the candidate sharpening operator can be expressed as:

[0067]

[0068] Usually, the value range of n is between 4 and 7. Therefore, multiple n values ​​can be determined between 4 and 7 by a certain step size to obtain multiple candidate sharpening operators. For example, the step size can be 0.1.

[0069] For any contrast level, the server performs sharpening processing on the reference image corresponding to the contrast level according to each candidate sharpening operator, and obtains multiple sharpened reference images. Then, target object recognition is performed on each sharpened reference image to obtain a target object recognition result. The sharpening effect score is determined based on the accuracy corresponding to the target recognition result, and then the candidate sharpening operator with the highest sharpening effect score is used as the target sharpening operator corresponding to the contrast level.

[0070] In this embodiment, by performing different degrees of smoothing or sharpening processing on the sample image, reference images corresponding to different contrast levels are obtained. For each contrast level, the target sharpening operator with the best sharpening effect corresponding to each contrast level is determined by a test search method, and a mapping relationship between the contrast level and the target sharpening operator is established. The sharpening effect of the image to be processed can be improved, thereby improving the accuracy of image recognition.

[0071] In an exemplary embodiment, extracting sub-images corresponding to a plurality of cluster points in an image to be processed includes:

[0072] Based on the brightness threshold of the pixel points, multiple target pixel points are determined from the image to be processed to form a cluster point area corresponding to the image to be processed; the cluster point area is subjected to connected domain analysis to obtain sub-images corresponding to multiple cluster points in the image to be processed.

[0073] The brightness threshold can be set according to the actual situation. The target pixel point refers to the pixel point whose pixel value is greater than the brightness threshold in the image to be processed. The cluster point area refers to the area composed of each pixel point in the image to be processed.

[0074] Exemplarily, the server obtains a brightness threshold for a pixel point. Pixel points in the image to be processed whose pixel values ​​are greater than the brightness threshold are determined as target pixels, and a cluster point region composed of each target pixel point is obtained. Then, a connected domain analysis is performed on the cluster point region to obtain multiple locally brighter connected regions in the image to be processed, each connected region corresponds to a cluster point, and each locally brighter connected region in the image to be processed is used as a sub-image corresponding to the cluster point.

[0075] In this embodiment, firstly, a cluster point area is extracted from the image to be processed according to a brightness threshold, and then a connected domain analysis is performed on the cluster point area. This can quickly and accurately extract sub-images corresponding to each cluster point from the image to be processed, effectively improve image processing efficiency, and reduce the consumption of computing resources.

[0076] In an exemplary embodiment, fusing multiple sub-images to obtain a cluster point fused image corresponding to the image to be processed includes:

[0077] For any cluster point, when the number of adjacent cluster points of the cluster point in the corresponding central image area is less than a preset number, the cluster point is determined as a target cluster point; the sub-images corresponding to each target cluster point are fused to obtain a cluster point fusion image corresponding to the image to be processed.

[0078] The preset number can be set according to actual needs, for example, the preset number can be set to 1. The central image area refers to an image area of ​​a preset size determined with the cluster point as the center. For example, the central image area can be an area corresponding to a 13*13 pixel range with the cluster point as the center.

[0079] Exemplarily, for any cluster point, when the number of adjacent cluster points contained in the central image area corresponding to the cluster point is less than a preset number, the cluster point is used as a target cluster point. When the number of adjacent cluster points in the central image area of ​​the cluster point is less than a preset number, it indicates that the cluster point is not interfered by other cluster points or is less interfered by other cluster points. Therefore, the target cluster point has clearer boundaries and feature information. Then, the sub-images corresponding to each target cluster point are fused to obtain a cluster point fusion image corresponding to the image to be processed.

[0080] In this embodiment, the target cluster point is determined according to the number of adjacent cluster points of the cluster point in the corresponding central image area, and then the cluster point fusion image corresponding to the image to be processed is obtained based on each target cluster point. Since the target cluster point is less disturbed, the cluster point fusion image determined based on each target cluster point is more accurate and can more accurately reflect the pixel contrast corresponding to the image to be processed, thereby improving the accuracy of image processing.

[0081] In an exemplary embodiment, determining a pixel contrast corresponding to the cluster point fusion image based on pixel statistical information in a first direction and pixel statistical information in a second direction in the cluster point fusion image includes:

[0082] The pixel mean values ​​corresponding to each row in the cluster point fusion image are counted to obtain the pixel statistical information of the first direction in the cluster point fusion image; the pixel mean values ​​corresponding to each row in the cluster point fusion image are counted to obtain the pixel statistical information of the second direction in the cluster point fusion image; the pixel statistical information of the first direction and the pixel statistical information of the second direction in the cluster point fusion image are fused to obtain the comprehensive pixel statistical information corresponding to the cluster point fusion image; based on the pixel maximum value in the comprehensive pixel statistical information, the pixel contrast corresponding to the cluster point fusion image is determined.

[0083] Among them, the comprehensive pixel statistical information can characterize the pixel value change trend corresponding to the cluster point fusion image as a whole.

[0084] Exemplarily, the server calculates the pixel mean corresponding to each row of pixels in the cluster point fusion image, and obtains the pixel statistics of the cluster point fusion image in the first direction based on the pixel mean corresponding to each row of pixels. The pixel mean corresponding to each column of the cluster point fusion image is calculated, and the pixel statistics of the cluster point fusion image in the second direction is obtained based on the pixel mean corresponding to each column of pixels. Then, the pixel statistics corresponding to the first direction and the second direction are fused to obtain the comprehensive pixel statistics corresponding to the cluster point fusion image. Based on the maximum value of the pixel in the comprehensive pixel statistics, the pixel contrast corresponding to the cluster point fusion image is determined. Specifically, the reference pixel value can be determined based on the maximum value of the pixel, and the pixel contrast is determined based on the distance between the two pixel positions corresponding to the reference pixel value in the comprehensive pixel statistics. For example, the comprehensive pixel statistics is shown in FIG6, in which the horizontal axis is used to indicate the pixel position, the pixel position is in pixels, the vertical axis indicates the pixel value, point A corresponds to the maximum value of 1, the reference pixel value is determined based on the maximum value of the pixel, and 0.5 can usually be used as the reference pixel value. Points B and C correspond to the reference pixel value of 0.5, and the pixel distance between points B and C is used as the pixel contrast. This is because the smaller the distance between the two pixel points corresponding to the reference pixel value, the faster the pixel corresponding to the cluster point fusion image changes, indicating that the cluster points in the cluster point fusion image are clearer and more obvious, so the image to be processed needs to be sharpened to a smaller degree. Conversely, when the distance between the two pixel points corresponding to the reference pixel value is larger, it indicates that the cluster points in the cluster point fusion image are more blurred, so the image to be processed needs to be sharpened to a greater extent.

[0085] In this embodiment, by fusing the pixel statistics information corresponding to the cluster point fusion image in the first direction and the second direction, the comprehensive pixel statistics information obtained can characterize the pixel value change trend of the cluster point fusion image as a whole. The reference pixel value is determined based on the maximum pixel value, and the sharpening intensity required for the image to be processed, that is, the pixel contrast, can be quickly and accurately determined based on the pixel distance between the two pixel positions corresponding to the reference pixel value, thereby improving the accuracy of the contrast level determined based on the pixel contrast and the efficiency of image processing.

[0086] In an exemplary embodiment, the image to be processed is a fluorescent image containing base information obtained by image acquisition of nucleic acid fragments, the cluster points are fluorescent points corresponding to the base information in the nucleic acid fragments, and the target image is used for gene sequencing.

[0087] Among them, bases are one of the basic units that make up nucleic acids. There are four main types of bases in nucleic acids. The type and order of bases determine the specificity of nucleic acids. The type and order of bases carry genetic information. In the process of gene sequencing, by detecting and analyzing the information of these bases, the genome sequence of an organism can be determined, thereby studying its genetic characteristics.

[0088] Exemplarily, before gene sequencing, the bases in the nucleic acid fragments need to be fluorescently labeled, and then an image acquisition device, such as a high-resolution camera or scanner, is used to acquire the image to be processed corresponding to the nucleic acid fragment, i.e., a fluorescent image containing base information. Then, sub-images corresponding to multiple cluster points (i.e., fluorescent points) are extracted from the fluorescent image. The sub-images are fused to obtain a cluster point fusion image corresponding to the fluorescent image. Based on the target sharpening operator corresponding to the contrast level of the pixel contrast corresponding to the cluster point fusion image, the fluorescent image is sharpened to obtain a target image. Then, the target image is subjected to gene sequencing to obtain a gene sequencing result corresponding to the fluorescent image.

[0089] In this embodiment, during the gene sequencing process, a cluster point fusion image is determined according to each cluster point in the fluorescence image, and then the contrast level of the fluorescence image is determined based on the cluster point fusion image. Based on the target sharpening operator corresponding to the contrast level of the fluorescence image, the image to be processed is sharpened, which can effectively improve the sharpening effect, so that the target image obtained can be more accurate and clear, thereby improving the efficiency and accuracy of gene sequencing.

[0090] In a specific embodiment, the image processing method proposed in this application can be applied to gene sequencing equipment. Figure 7 As shown, the image processing method comprises the following steps:

[0091] 1. Obtain reference images at each contrast level

[0092] The gene sequencing equipment performs different degrees of smoothing on the sample image, and superimposes a certain amount of random noise on the smoothed image to obtain reference images corresponding to different low-contrast levels. It also performs different degrees of sharpening on the sample image, and superimposes a certain amount of random noise on the sharpened image to obtain reference images corresponding to different high-contrast levels.

[0093] 2. Calculate the pixel contrast corresponding to each contrast level

[0094] For any reference image corresponding to a contrast level, the gene sequencing device extracts sub-images corresponding to multiple cluster points from the reference image corresponding to the contrast level. When there are no other cluster points in the central image area corresponding to a cluster point, the cluster point is used as the target cluster point. The sub-images corresponding to each target cluster point are fused to obtain a cluster point fusion image corresponding to the contrast level. Based on the pixel statistics corresponding to the cluster point fusion image in the x-axis direction and the pixel statistics corresponding to the y-axis direction, the pixel contrast corresponding to the cluster point fusion image is determined.

[0095] 3. Determine the target sharpening operator corresponding to each contrast level

[0096] For any contrast level, the gene sequencing device sharpens the reference image corresponding to the contrast level according to each candidate sharpening operator, performs gene sequencing on the reference image obtained after the sharpening process, and takes the candidate sharpening operator corresponding to the gene sequencing result with the highest accuracy as the target sharpening operator corresponding to the contrast level.

[0097] 4. Apply the target sharpening operator corresponding to each contrast level

[0098] The gene sequencing device obtains the image to be processed and calculates the pixel contrast corresponding to the image to be processed. Based on the target sharpening operator corresponding to the contrast level of the pixel contrast corresponding to the image to be processed, the image to be processed is sharpened to obtain the target image. Then, the target image is subjected to gene sequencing to obtain the gene sequencing result corresponding to the image to be processed.

[0099] In the above embodiment, when generating reference images corresponding to each contrast level, random noise is superimposed on each reference image, which can increase the randomness of the image, help reduce the bias of the data, and help restore statistical authenticity. Then, through the traversal search method, the target sharpening operator corresponding to each contrast level is determined, and the adaptive adjustment of the sharpening operator is achieved, which can improve the image sharpening effect, thereby specifically reducing the interference between adjacent cluster points in the image and improving the accuracy of gene sequencing.

[0100] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0101] Based on the same inventive concept, the embodiment of the present application also provides an image processing device for implementing the above-mentioned image processing method. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above-mentioned method, so the specific limitations in one or more image processing device embodiments provided below can refer to the limitations on the image processing method above, and will not be repeated here.

[0102] In an exemplary embodiment, as shown in FIG8 , an image processing device is provided, comprising: an image acquisition module, a cluster point extraction module, a contrast determination module and an image sharpening module, wherein:

[0103] The image acquisition module is used to acquire the image to be processed.

[0104] The cluster point extraction module is used to extract sub-images corresponding to multiple cluster points in the image to be processed, and fuse the multiple sub-images to obtain a cluster point fused image corresponding to the image to be processed.

[0105] The contrast determination module is used to determine the pixel contrast corresponding to the cluster point fusion image based on the pixel statistical information in the first direction and the pixel statistical information in the second direction in the cluster point fusion image.

[0106] The image sharpening module is used to perform sharpening processing on the image to be processed based on the target sharpening operator corresponding to the contrast level to which the pixel contrast belongs, so as to obtain the target image.

[0107] In one embodiment, the image processing apparatus further includes:

[0108] The operator determination module is used to obtain a sample image; perform different degrees of smoothing on the sample image, perform different degrees of sharpening on the sample image, and obtain reference images corresponding to multiple contrast levels; for any contrast level, perform sharpening on the reference image corresponding to the contrast level according to each candidate sharpening operator, perform target object recognition on the sharpened reference image, determine a sharpening effect score according to the target object recognition result, and determine a target sharpening operator corresponding to the contrast level according to the sharpening effect scores corresponding to each candidate sharpening operator.

[0109] In one embodiment, the cluster point extraction module is further used to:

[0110] Based on the brightness threshold of the pixel points, multiple target pixel points are determined from the image to be processed to form a cluster point area corresponding to the image to be processed; the cluster point area is subjected to connected domain analysis to obtain sub-images corresponding to multiple cluster points in the image to be processed.

[0111] In one embodiment, the cluster point extraction module is further used to:

[0112] For any cluster point, when the number of adjacent cluster points of the cluster point in the corresponding central image area is less than a preset number, the cluster point is determined as a target cluster point; the sub-images corresponding to each target cluster point are fused to obtain a cluster point fusion image corresponding to the image to be processed.

[0113] In one embodiment, the contrast determination module is further configured to:

[0114] The pixel mean values ​​corresponding to each row in the cluster point fusion image are counted to obtain the pixel statistical information of the first direction in the cluster point fusion image; the pixel mean values ​​corresponding to each row in the cluster point fusion image are counted to obtain the pixel statistical information of the second direction in the cluster point fusion image; the pixel statistical information of the first direction and the pixel statistical information of the second direction in the cluster point fusion image are fused to obtain the comprehensive pixel statistical information corresponding to the cluster point fusion image; based on the pixel maximum value in the comprehensive pixel statistical information, the pixel contrast corresponding to the cluster point fusion image is determined.

[0115] In one embodiment, the image to be processed is a fluorescent image containing base information obtained by collecting images of nucleic acid fragments, the cluster points are fluorescent points corresponding to the base information in the nucleic acid fragments, and the target image is used for gene sequencing.

[0116] Each module in the above image processing device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0117] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG9. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as images to be processed and cluster point fusion images. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, an image processing method is implemented.

[0118] In an exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG10. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, an image processing method is implemented. The display unit of the computer device is used to form a visually visible picture, which may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0119] Those skilled in the art will understand that the structures shown in FIGS. 9 and 10 are merely block diagrams of partial structures related to the scheme of the present application, and do not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device may include more or fewer components than those shown in the figures, or combine certain components, or have a different arrangement of components.

[0120] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0121] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0122] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0123] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0124] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0125] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0126] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An image processing method, characterized in that: The method comprises: Get the image to be processed; Extracting sub-images corresponding to a plurality of cluster points in the image to be processed, respectively, and fusing the plurality of sub-images to obtain a cluster point fused image corresponding to the image to be processed; Determine a pixel contrast corresponding to the cluster point fusion image based on pixel statistical information in a first direction and pixel statistical information in a second direction in the cluster point fusion image; Based on the target sharpening operator corresponding to the contrast level to which the pixel contrast belongs, the image to be processed is sharpened to obtain a target image.

2. The method according to claim 1, characterized in that: The method further comprises: Get a sample image; Performing different degrees of smoothing processing on the sample image, and performing different degrees of sharpening processing on the sample image, to obtain reference images corresponding to multiple contrast levels respectively; For any of the contrast levels, the reference image corresponding to the contrast level is sharpened according to each candidate sharpening operator, the target object is identified on the sharpened reference image, a sharpening effect score is determined according to the target object identification result, and the target sharpening operator corresponding to the contrast level is determined according to the sharpening effect scores corresponding to each of the candidate sharpening operators.

3. The method according to claim 1, characterized in that The extracting of sub-images corresponding to a plurality of cluster points in the image to be processed includes: Based on a brightness threshold for a pixel point, a plurality of target pixel points are determined from the image to be processed to form a cluster point area corresponding to the image to be processed; Connected domain analysis is performed on the cluster point region to obtain sub-images corresponding to the multiple cluster points in the image to be processed.

4. The method according to claim 1, characterized in that: The fusing of the multiple sub-images to obtain a cluster point fused image corresponding to the image to be processed includes: For any of the cluster points, when the number of adjacent cluster points of the cluster point in the corresponding central image area is less than a preset number, the cluster point is determined as a target cluster point; The sub-images corresponding to the target cluster points are fused to obtain a cluster point fused image corresponding to the image to be processed.

5. The method according to claim 1, characterized in that The determining the pixel contrast corresponding to the cluster point fusion image based on the pixel statistical information in the first direction and the pixel statistical information in the second direction in the cluster point fusion image includes: Counting the pixel means corresponding to each row in the cluster point fusion image, to obtain pixel statistical information in a first direction in the cluster point fusion image; Counting the pixel means corresponding to each row in the cluster point fusion image, and obtaining pixel statistical information in a second direction in the cluster point fusion image; Fusing pixel statistical information in a first direction and pixel statistical information in a second direction in the cluster point fusion image to obtain comprehensive pixel statistical information corresponding to the cluster point fusion image; Based on the maximum value of the pixel in the comprehensive pixel statistical information, the pixel contrast corresponding to the cluster point fusion image is determined.

6. The method according to claim 1, characterized in that The image to be processed is a fluorescent image containing base information obtained by image acquisition of nucleic acid fragments, the cluster points are fluorescent points corresponding to the base information in the nucleic acid fragments, and the target image is used for gene sequencing.

7. An image processing device, characterized in that: The device comprises: An image acquisition module, used for acquiring an image to be processed; A cluster point extraction module, used to extract sub-images corresponding to a plurality of cluster points in the image to be processed, and fuse the plurality of sub-images to obtain a cluster point fused image corresponding to the image to be processed; A contrast determination module, configured to determine a pixel contrast corresponding to the cluster point fusion image based on pixel statistical information in a first direction and pixel statistical information in a second direction in the cluster point fusion image; The image sharpening module is used to perform sharpening processing on the image to be processed based on the target sharpening operator corresponding to the contrast level to which the pixel contrast belongs, so as to obtain a target image.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.