Wide-angle image processing method and device, electronic equipment and storage medium

Abstract

The invention provides a wide-angle image processing method and device, electronic equipment and a storage medium. The wide-angle image processing method comprises the following steps: acquiring a fundus leopard spot region image of a target object; performing image geometric transformation on the fundus leopard speckle area image to obtain a transformed image of the fundus leopard speckle area image; performing threshold segmentation on the transformed image to obtain a vortex vein center candidate region image; determining a target leopard spot region based on the vortex vein center candidate region image; and according to the leopard spot features of the target leopard spot region, determining a vortex vein central region. Through the wide-angle image processing method provided by the invention, the vortex vein information in the wide-angle eye fundus image can be accurately identified and extracted, the extraction effect is enhanced, and the vortex vein identification accuracy is improved. In addition, the functions of processing the fundus image in real time and rapidly extracting vortex vein information to detect whether the fundus image is abnormal or not are achieved. A doctor is helped to identify vortex veins, and reference is provided for image shooting standardization.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and particularly to a wide-angle image processing method, device, storage medium and electronic device. Background Art

[0002] The vortex veins are located behind the equator of the eyeball, generally 4 - 6 in number, and are used to collect blood from part of the iris, ciliary body and all choroids. The trunk of the vortex vein expands in a funnel shape before entering the sclera, and because of the addition of radial and curved venous branches, the whole appearance is in a spiral shape, so it is named the vortex vein. If the vortex vein is abnormal, it may cause myopia, diabetic retinopathy, and macular degeneration. Therefore, the detection and recognition of the vortex vein are very necessary for diagnosing the eye state and diseases.

[0003] The fundus images obtained by the ultra-wide-angle fundus imaging technology can show the image features of the vortex vein. However, since there are usually 4 - 6 vortex veins and they are radial, it is difficult to automatically identify the vortex vein in the ultra-wide-angle fundus image. And in the existing recognition technologies, the recognition effect of the vortex vein is not good, the accuracy is poor, and the abnormality of the vortex vein cannot be detected in time. Summary of the Invention

[0004] In view of this, the embodiments of the present application are committed to providing a wide-angle image processing method, device, storage medium and electronic device to solve the problems that the recognition effect of the vortex vein is not good, the accuracy is poor, and the abnormality of the vortex vein cannot be detected in time.

[0005] On the one hand, the present application provides a wide-angle image processing method, including:

[0006] Obtain an image of the fundus tessellated area of the target object; perform image geometric transformation on the image of the fundus tessellated area to obtain a transformed image of the fundus tessellated area; perform threshold segmentation on the transformed image to obtain an image of the candidate area of the vortex vein center; determine the target tessellated area based on the image of the candidate area of the vortex vein center; determine the vortex vein center area according to the tessellated features of the target tessellated area.

[0007] Combined with the first aspect, determining the vortex vein center area according to the tessellated features of the target tessellated area includes: calculating the number of tessellations in the target tessellated area; calculating the number of tessellations on the boundary of the target tessellated area; when the number of tessellations in the target tessellated area reaches a first quantity threshold and the number of tessellations on the boundary of the target tessellated area reaches a second quantity threshold, determine the target tessellated area as the vortex vein center area, where the first quantity threshold is less than the second quantity threshold.

[0008] Combined with the first aspect, the wide-angle image processing method further includes: determining the field of view angle of the fundus tessellated area image according to the number of vortex vein center areas of the target object.

[0009] In combination with the first aspect, the wide-angle image processing method further includes: determining a shooting quality score of the fundus tessellated area image according to the number of central areas of the vortex veins of the target object, and evaluating the quality of the fundus tessellated area image according to the shooting quality score, wherein the quality of the fundus tessellated area image includes the shooting range or shooting angle of the fundus tessellated area image.

[0010] In combination with the first aspect, the wide-angle image processing method further includes: obtaining the center line area of the fundus tessellated area image; based on the center line area, determining the average gray value of the area corresponding to the center line area of the transformed image; wherein, performing threshold segmentation on the transformed image to obtain a candidate area image of the vortex vein center, including: performing threshold segmentation on the transformed image according to the average gray value to obtain a candidate area image of the vortex vein center.

[0011] In combination with the first aspect, performing threshold segmentation on the transformed image according to the average gray value to obtain a candidate area image of the vortex vein center, including: based on the average gray value, determining a target segmentation threshold; performing threshold segmentation on the transformed image according to the target segmentation threshold to obtain a candidate area image of the vortex vein center.

[0012] In combination with the first aspect, based on the candidate area image of the vortex vein center, determining the target tessellated area, including: extracting the optic disc diameter corresponding to the fundus tessellated area image and determining the target area radius value according to the optic disc diameter; in the candidate area image of the vortex vein center, taking the center of the candidate area image of the vortex vein center as the center of the circle and the target area radius value as the radius to obtain the target tessellated area.

[0013] In a second aspect, the present application further provides a wide-angle image processing device, including: an acquisition module for acquiring a fundus tessellated area image of a target object; an image geometric transformation module for performing image geometric transformation on the fundus tessellated area image to obtain a transformed image of the fundus tessellated area image; a threshold segmentation module for performing threshold segmentation on the transformed image to obtain a candidate area image of the vortex vein center; a determination module for determining a target tessellated area based on the candidate area image of the vortex vein center; a judgment module for determining the central area of the vortex vein according to the tessellated characteristics of the target tessellated area; a display module for displaying the annotation of the central area of the vortex vein.

[0014] In a third aspect, the present application further provides a computer-readable storage medium storing a computer program for executing the wide-angle image processing method mentioned in the first aspect above.

[0015] In a fourth aspect, the present application further provides an electronic device, including: a processor;

[0016] A memory for storing processor-executable instructions; a processor for executing the wide-angle image processing method mentioned in the first aspect above.

[0017] The wide-angle image processing method and apparatus, storage medium and electronic device provided by the embodiments of the present application effectively process the characteristics of the vortex veins for subsequent identification, improve the resolution and recognition ability of the vortex vein area, can accurately identify and extract the vortex vein information in the wide-angle fundus image, strengthen the extraction effect, and improve the accuracy of identifying the vortex veins. In addition, it realizes real-time processing of fundus images and quickly extracts the vortex vein information to detect whether it is abnormal. At the same time, it can also help doctors identify the vortex veins and provide a reference for the standardization of image shooting. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The flowchart of the wide-angle image processing method provided by an embodiment of the present application is shown.

[0019] Figure 2 The image of the fundus tessellata area provided by an embodiment of the present application is shown.

[0020] Figure 3 The transformed image obtained by geometric transformation of the image of the fundus tessellata area provided by an embodiment of the present application is shown.

[0021] Figure 4 The image of the candidate vein center area obtained by threshold segmentation of the transformed image provided by an embodiment of the present application is shown.

[0022] Figure 5 The target fundus tessellata area image provided by an embodiment of the present application is shown.

[0023] Figure 6 The flowchart of the wide-angle image processing method of another embodiment of the present application is shown.

[0024] Figure 7 The flowchart of the wide-angle image processing method of still another embodiment of the present application is shown.

[0025] Figure 8 The flowchart of the wide-angle image processing method of still another embodiment of the present application is shown.

[0026] Figure 9 The flowchart of the wide-angle image processing method of still another embodiment of the present application is shown.

[0027] Figure 10 The structural diagram of the wide-angle image processing apparatus provided by an embodiment of the present application is shown.

[0028] Figure 11The following is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0029] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0030] Overview of the Application

[0031] The ultra-wide-angle fundus imaging technology enables the range of fundus images to reach 200°, which is a major advancement in fundus imaging. This technology has only emerged in recent years. Therefore, the image features of ultra-wide-angle fundus images are unfamiliar to most people, and few people recognize the vorticose veins. Therefore, how to identify the vorticose veins in ultra-wide-angle fundus images has become a difficult point. In the existing identification technologies, the identification effect of vorticose veins is not good, the accuracy is poor, and the abnormalities of vorticose veins cannot be detected in time.

[0032] Based on the above-mentioned technical problems, the basic concept of the present application is to propose a wide-angle image processing method, device, computer-readable storage medium and electronic device to solve the problems that the identification effect of veins is not good, the accuracy is poor, and the abnormalities of vorticose veins cannot be detected in time.

[0033] The wide-angle image processing method provided by the present application includes: obtaining an image of the fundus tessellated area of a target object; performing image geometric transformation on the image of the fundus tessellated area to obtain a transformed image of the fundus tessellated area; performing threshold segmentation on the transformed image to obtain an image of a candidate area for the center of the vorticose vein; determining a target tessellated area based on the image of the candidate area for the center of the vorticose vein; and determining the center area of the vorticose vein according to the tessellated features of the target tessellated area.

[0034] The wide-angle image processing method provided by the present application effectively processes the features of the vorticose veins for subsequent identification, improves the resolution and recognition ability of the vorticose vein area, can accurately identify and extract the vorticose vein information in the wide-angle fundus image, strengthens the extraction effect, and improves the accuracy of identifying the vorticose veins. In addition, it realizes the function of real-time processing of fundus images, quickly extracting the vorticose vein information and detecting whether it is abnormal. It can also help doctors identify the vorticose veins and provide a reference for the standardization of image shooting.

[0035] After introducing the basic principle of the present application, the various non-limiting embodiments of the present application will be specifically introduced below with reference to the accompanying drawings.

[0036] Exemplary Method

[0037] Figure 1 The figure shows a schematic flowchart of a wide-angle image processing method provided by an embodiment of the present application. Figure 2 The figure shows an image of the fundus tessellata area provided by an embodiment of the present application. Figure 3 The figure shows a transformed image obtained after geometric transformation of the image of the fundus tessellata area provided by an embodiment of the present application. Figure 4 The figure shows an image of a candidate area of the center of the vortex vein obtained after threshold segmentation of the transformed image provided by an embodiment of the present application. Figure 5 The figure shows an image of the target fundus tessellata area provided by an embodiment of the present application. Next, in conjunction with Figures 1 to 5 , it will be described in detail Figure 1 the wide-angle image processing method mentioned in an embodiment of the present application shown in the figure.

[0038] Step S10: Obtain an image of the fundus tessellata area of the target object.

[0039] Exemplarily, as Figure 2 shown in the figure, it is an image of the fundus tessellata area extracted from the original image obtained by ultra-widefield fundus imaging technology. The original image obtained by ultra-widefield fundus imaging technology can use the threshold segmentation method to remove the background area of the fundus image, and then obtain the region of interest (ROI), and then crop the image to obtain the image of interest. In an alternative embodiment, the image can also be processed such as enhanced, sharpened, filtered, smoothed, denoised, etc. to obtain the image of interest. Then, the fundus tessellata area containing the tessellata is extracted from the image of interest. Exemplarily, the image of interest is input into the tessellata feature extraction model to obtain an image of the fundus tessellata area. The present application does not limit the manner of obtaining the region of interest from the original image and extracting the image of the fundus tessellata area through the region of interest. The art already has mature image processing technologies to obtain the image of the fundus tessellata area. The image of the fundus tessellata area contains the characteristics of the exposed area of the fundus choroid.

[0040] Step S20: Perform geometric transformation on the image of the fundus tessellata area to obtain a transformed image of the fundus tessellata area.

[0041] Exemplarily, the image geometric transformation algorithm includes a distance transformation algorithm. Specifically, distance transformation is to convert each pixel point in the image into the distance from this point to the nearest background pixel point, so as to realize the distance measurement and analysis of different objects in the image. Therefore, through distance transformation, each pixel in the image can be divided into two categories: foreground pixel points and background pixel points. The embodiments of the present application do not limit the algorithm of image geometric transformation.

[0042] In the embodiments of the present application, exemplarily, as Figure 3As shown, a grayscale image highlighting the choroid features of the fundus tessellated pattern can be obtained through an image geometric transformation algorithm, facilitating the further extraction of vortex vein feature information.

[0043] Step S30: Perform threshold segmentation on the transformed image to obtain an image of the candidate region for the center of the vortex vein.

[0044] The threshold segmentation algorithm is a region-based image segmentation technique. The principle is to divide the image pixel points into several classes. It is a traditional and most commonly used image segmentation method with small computational complexity and relatively stable performance, and is applicable to images where the target and the background occupy different gray-level ranges. The threshold segmentation algorithm makes a partition of the pixel set according to the gray level, and each subset obtained forms a region corresponding to the real scene. The internal parts of each region have consistent attributes, while adjacent regions do not have such consistent attributes. Additionally, it can also be achieved by selecting one or more thresholds starting from the gray level.

[0045] In the embodiment of the present application, exemplarily, as Figure 4 shown, by setting a suitable threshold, the vortex vein choroid feature contour can be clarified using the threshold segmentation algorithm, enhancing the demarcation from the background region, facilitating the further extraction of vortex vein feature information.

[0046] Step S40: Determine the target tessellated pattern region based on the image of the candidate region for the center of the vortex vein.

[0047] Specifically, the image of the candidate region for the center of the vortex vein is a candidate region for the center that includes the vortex vein and something similar to the vortex vein. Before further screening the candidate region image to identify the vortex vein, it is necessary to first determine the screening range, that is, the target tessellated pattern region. Exemplarily, step S40 further includes the following steps:

[0048] Extract the optic disc diameter corresponding to the image of the fundus tessellated pattern region and determine the target region radius value according to the optic disc diameter;

[0049] In the image of the candidate region for the center of the vortex vein, with the center of the image of the candidate region for the center of the vortex vein as the center and the target region radius value as the radius, obtain the target tessellated pattern region.

[0050] The optic disc is also known as the optic nerve head. It is located at a position about 3 mm nasal to the macula on the retina, with a diameter of about 1.5 mm. In ultra-widefield fundus images, it appears as a light red disc-shaped structure, called the optic nerve disc, abbreviated as the optic disc. The diameter of the optic disc can be extracted based on existing technologies, and this application does not further limit it. Preferably, the radius value of the target area can be 1 to 5 times the diameter of the optic disc. Further preferably, the radius value of the target area is taken as 2 times the diameter of the optic disc. Taking 2 times the diameter of the optic disc as the radius of the circular area for determining the target tessellated area, and with the center of the candidate area image of the vortex vein as the center, the target tessellated area is obtained. Based on the further identification of the target tessellated area, the vortex vein center area can be effectively screened out.

[0051] In an embodiment of this application, exemplarily, as Figure 5 shown, taking the center of the candidate area image of the vortex vein as the center and twice the diameter of the optic disc as the radius, the selected circular area is the target tessellated area image.

[0052] Step S50: Determine the vortex vein center area according to the tessellated features of the target tessellated area.

[0053] Specifically, step S50 includes the following steps:

[0054] Calculate the number of tessellations within the target tessellated area;

[0055] Calculate the number of tessellations on the boundary of the target tessellated area;

[0056] When the number of tessellations within the target tessellated area reaches the first quantity threshold and the number of tessellations on the boundary of the target tessellated area reaches the second quantity threshold, determine that the target tessellated area is the vortex vein center area.

[0057] Preferably, the first quantity threshold is less than the second quantity threshold.

[0058] Exemplarily, in the circular target tessellated area image as Figure 5 shown, take the first quantity threshold as 1 and the second quantity threshold as 10. It can be obtained that the number of tessellations within the target tessellated area is 1; the number of tessellations on the boundary of the target tessellated area is about 16. Therefore, the number of tessellations on the boundary of the target tessellated area is greater than 10, and it can be determined that the current target tessellated area is the vortex vein center area.

[0059] Through this method, by using advanced algorithms and image processing techniques, the vortex vein information in the wide-angle fundus image can be accurately identified and extracted, enhancing the extraction effect, which is more accurate than the prior art. By detecting whether the vortex vein is abnormal, doctors can clearly observe and analyze the fundus conditions of patients and the quality of wide-angle fundus images, which is beneficial to the standardization of wide-angle fundus images and improves the accuracy of diagnosis. In addition, the method for extracting vortex veins from wide-angle fundus images provided by this application can process fundus images in real time, quickly extract vortex vein information and detect whether it is abnormal to achieve auxiliary diagnosis.

[0060] Therefore, by means of the above-mentioned image processing technology, the automation of vortex vein recognition can be realized, the processing efficiency of a large number of wide-angle fundus images and the accuracy of extracting vortex vein information can be improved. The workload of doctors is reduced and the utilization efficiency of medical resources is improved.

[0061] In addition, by using the above-mentioned wide-angle image processing method to record and store the extracted vortex vein information, doctors and researchers can trace and compare the fundus feature conditions at different time points, understand the development process of diseases, and provide valuable data for subsequent treatment and research.

[0062] Figure 6 The following shows a schematic flowchart of the wide-angle image processing method according to another embodiment of this application, which extends from the Figure 1 embodiment shown and Figure 6 the embodiment shown is extended. Below, the differences between the Figure 6 embodiment shown and the Figure 1 embodiment shown will be mainly described, and the same parts will not be elaborated.

[0063] As Figure 6 shown, in the wide-angle image processing method provided by the embodiments of this disclosure, the following steps are further included.

[0064] Step S12: Obtain the central line area of the fundus tessellata area image.

[0065] Preferably, the central line area is the skeleton line area of all the fundus tessellata in the fundus tessellata area image. Specifically, an area is a set of pixels with common attributes, and the skeleton line area is a set of areas with a width of one pixel. The skeleton line area is the central line area of the fundus tessellata area image.

[0066] Step S14: Based on the central line area, determine the average gray value of the area corresponding to the transformed image and the central line area.

[0067] The average gray value obtained based on the central line area can make the threshold selection for threshold segmentation more accurate, and the image obtained after threshold segmentation can clearly segment the fundus tessellata area and the background area.

[0068] Among them, step S30 includes the following steps.

[0069] Step S32: Perform threshold segmentation on the transformed image according to the average gray value to obtain an image of the candidate region of the vortex vein center.

[0070] The wide-angle image processing method provided by the embodiment of the present application can make the threshold selection of the threshold-segmented image adapt to the currently processed image by means of the skeleton line of the leopard pattern, improving the image processing effect of the threshold segmentation.

[0071] Preferably, Figure 7 The following is a schematic flowchart of the wide-angle image processing method according to another embodiment of the present application. On the basis of the embodiment shown in Figure 6 The embodiment shown is extended to Figure 7 The embodiment shown below focuses on describing Figure 7 The differences between the embodiment shown and Figure 6 The embodiment shown, and the same parts will not be described in detail.

[0072] As Figure 7 shown, step S32 includes the following steps.

[0073] Step S321: Determine the target segmentation threshold based on the average gray value.

[0074] Exemplarily, if the average gray value corresponding to the center line in the above-mentioned transformed image is Leopard CenterLine Gray Value, the target segmentation threshold is determined to be (Leopard Center Line Gray Value * 3, 255). The present application does not make specific limitations on the threshold setting. According to the specific situation of different images, different threshold ranges can be selected to better achieve the effect of threshold segmentation.

[0075] Step S322; Perform threshold segmentation on the transformed image according to the target segmentation threshold to obtain an image of the candidate region of the vortex vein center.

[0076] Exemplarily, in the obtained threshold-segmented image, the gray value of the pixel points in the transformed image that are greater than the target segmentation threshold is set to 1, that is, white; the gray value of the pixel points that are less than the target segmentation threshold is set to 0, that is, black, thereby obtaining a binary image, as Figure 4 shown.

[0077] The wide-angle image processing method provided by the embodiment of the present application can obtain an image of the candidate region of the vortex vein center with relatively clear vortex vein choroid features, facilitating the subsequent extraction of the vortex vein center region.

[0078] Figure 8 The following is a schematic flowchart of the wide-angle image processing method according to another embodiment of the present application. InFigure 1 Based on the illustrated embodiment, an extended Figure 8 embodiment is shown. The following focuses on Figure 8 the differences between the Figure 1 illustrated embodiment and the

[0079] As Figure 8 shown, in the wide-angle image processing method provided by the embodiments of the present disclosure, the following steps are further included.

[0080] Step S60: Determine the field of view angle of the fundus tessellata area image according to the number of vortex vein center regions of the target object.

[0081] It can be understood that if the number of captured vortex vein center regions is larger, that is, the number of vortex veins is larger, it indicates that the selected field of view angle is appropriate; on the contrary, if the number of vortex vein center regions is smaller, it indicates that the selected field of view angle is inappropriate. At the same time, when the shooting point is fixed, if the number of captured vortex vein center regions is larger, that is, the number of vortex veins is larger, it indicates that the selected field of view angle is larger; on the contrary, if the number of vortex vein center regions is smaller, it indicates that the selected field of view angle is smaller. By determining the field of view angle of the fundus tessellata area image according to the number of vortex vein center regions of the target object, the operator or the photographer can be assisted in adjusting the field of view angle during shooting to improve the shooting quality.

[0082] Figure 9 Shown is a schematic flowchart of the wide-angle image processing method according to another embodiment of the present application. Based on the Figure 1 illustrated embodiment, an extended Figure 9 embodiment is shown. The following focuses on Figure 9 the differences between the Figure 1 illustrated embodiment and the

[0083] As Figure 9 shown, in the wide-angle image processing method provided by the embodiments of the present disclosure, the following steps are further included.

[0084] Step S70: Determine the shooting quality score of the fundus tessellata area image according to the number of vortex vein center regions of the target object, and evaluate the quality of the fundus tessellata area image according to the shooting quality score. The quality of the fundus tessellata area image includes the shooting range / shooting angle of the fundus tessellata area image.

[0085] It can be understood that if the number of captured vortex vein center regions is larger, that is, the number of vortex veins is larger, it proves that the shooting range of the wide-angle image is wider, and thus the obtained score is higher; on the contrary, if the number of vortex vein center regions is smaller, the score is lower. By scoring the wide-angle fundus tessellata area image, the image standardization can be assisted.

[0086] Exemplarily, when the central regions of 4 vortex veins are captured, the captured quality score is 8. Optionally, the captured quality score threshold can be set to 8. When the number of central regions of vortex veins is less than 4, i.e., less than the quality score threshold, the quality of the fundus tessellated area image is evaluated as low; when the number of central regions of vortex veins is greater than or equal to 4, i.e., greater than or equal to the quality score threshold, the quality of the fundus tessellated area image is evaluated as high. After the quality score is output, the photographer or operator can reshoot to ensure the optimal viewing angle, the best shooting range and shooting angle.

[0087] Figure 10 The following shows a schematic structural diagram of a wide-angle image processing device provided by an embodiment of the present application. As Figure 10 shown, the wide-angle image processing device 1000 provided by the embodiment of the present application includes: an acquisition module 1010, an image geometric transformation module 1020, a threshold segmentation module 1030, a determination module 1040, and a judgment module 1050.

[0088] Specifically, the acquisition module 1010 is configured to acquire an image of the fundus tessellated area of a target object; the image geometric transformation module 1020 is configured to perform image geometric transformation on the image of the fundus tessellated area to obtain a transformed image of the fundus tessellated area; the threshold segmentation module 1030 is configured to perform threshold segmentation on the transformed image to obtain an image of a candidate central region of the vortex vein; the determination module 1040 is configured to determine a target tessellated area based on the image of the candidate central region of the vortex vein; the judgment module 1050 is configured to determine the central region of the vortex vein according to the tessellated features of the target tessellated area.

[0089] In an embodiment of the present application, when the judgment module 1050 executes the step: determining the central region of the vortex vein according to the tessellated features of the target tessellated area, the following steps are executed: calculating the number of tessellations in the target tessellated area; calculating the number of tessellations on the boundary of the target tessellated area; when the number of tessellations in the target tessellated area reaches a first quantity threshold and the number of tessellations on the boundary of the target tessellated area reaches a second quantity threshold, determining the target tessellated area as the central region of the vortex vein, where the first quantity threshold is less than the second quantity threshold.

[0090] In an embodiment of the present application, the acquisition module 1010 is further configured to execute the steps: acquiring the center line region of the fundus tessellated area image; determining the average gray value of the region corresponding to the transformed image and the center line region based on the center line region. The threshold segmentation module 1030 is configured to perform threshold segmentation on the transformed image according to the average gray value to obtain an image of a candidate central region of the vortex vein.

[0091] In an embodiment of the present application, when the threshold segmentation module 1030 executes the steps: performing threshold segmentation on the transformed image according to the average gray value to obtain the candidate image of the vortex vein center region, the following steps are further executed: determining a target segmentation threshold based on the average gray value; performing threshold segmentation on the transformed image according to the target segmentation threshold to obtain the candidate image of the vortex vein center region.

[0092] In an embodiment of the present application, when the determination module 1040 executes the steps: determining the target leopard spot region based on the candidate image of the vortex vein center region, the following steps are executed: extracting the optic disc diameter corresponding to the fundus leopard spot region image and determining the target region radius value according to the optic disc diameter; in the candidate image of the vortex vein center region, taking the center of the candidate image of the vortex vein center region as the center of the circle and the target region radius value as the radius, obtaining the target leopard spot region.

[0093] In an embodiment of the present application, the judgment module 1050 is further configured to execute the steps: determining the field of view angle of the fundus leopard spot region image according to the number of vortex vein center regions of the target object.

[0094] In an embodiment of the present application, the judgment module 1050 is further configured to execute the steps: determining the shooting quality score of the fundus leopard spot region image according to the number of vortex vein center regions of the target object, and evaluating the quality of the fundus leopard spot region image according to the shooting quality score, where the quality of the fundus leopard spot region image includes the shooting range or shooting angle of the fundus leopard spot region image.

[0095] In an embodiment of the present application, the wide-angle image processing device 1000 further includes: a display module 1060, configured to display the annotation information of the vortex vein center region. The present application does not limit the annotation form, and the vortex vein center region can be annotated in any form to assist the doctor in diagnosing the fundus image.

[0096] Figure 11 The following shows the structural schematic diagram of an electronic device provided by an embodiment of the present application. As Figure 11 shown, the electronic device 1100 includes: a memory 1120, and one or more processors 1110 communicatively connected to the memory 1120; instructions are stored in the memory 1120 and can be executed by the one or more processors 1110, and when the instructions are executed by the one or more processors 1110, the one or more processors 1110 are caused to implement the wide-angle image processing method provided by any of the foregoing embodiments.

[0097] The processor 1110 may be a central processing unit (CPU) or other form of processing unit having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 1100 to perform desired functions.

[0098] The memory 1120 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache, etc. The non-volatile memory may include, for example, read only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage media, and the processor 1110 may run the program instructions to implement the wide-angle image processing method of various embodiments of the present application described above and / or other desired functions. Various contents such as images of the candidate regions of the vortex vein centers and target leopard spot regions may also be stored in the computer-readable storage media.

[0099] In one example, the electronic device 1100 may further include: an input device 1130 and an output device 1140, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0100] The input device 1130 may include, for example, a keyboard, a mouse, etc.

[0101] The output device 1140 may output various information to the outside, including the annotation information of the vortex vein center region, etc. The output device 1140 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0102] Of course, for simplicity, Figure 11 only some of the components related to the present application in the electronic device 1100 are shown, and components such as buses, input / output interfaces, etc. are omitted. In addition, according to specific application scenarios, the electronic device 1100 may further include any other appropriate components.

[0103] In addition to the above methods and devices, the embodiments of the present application may also be a computer program product, which includes computer program instructions that, when run by a processor, cause the processor to execute the steps in the wide-angle image processing method according to various embodiments of the present application described above in this specification.

[0104] The computer program product may be written in any combination of one or more programming languages for executing the program code of the operations of the embodiments of the present application. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's device, executed as an independent software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0105] It can be understood that the specific examples herein are only for helping those skilled in the art to better understand the embodiments of this specification, rather than limiting the scope of the present invention.

[0106] It can be understood that in various embodiments of this specification, the magnitudes of the sequence numbers of the various processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of this specification.

[0107] It can be understood that the various embodiments described in this specification can be implemented alone or in combination, and this specification does not limit this.

[0108] Unless otherwise specified, all technical and scientific terms used in the embodiments of this specification have the same meaning as commonly understood by those skilled in the technical field of this specification. The terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the scope of this specification. The term "and / or" used in the embodiments of this specification and the appended claims includes any and all combinations of one or more of the related listed items. The singular forms "a", "above-mentioned", and "the" used in the embodiments of this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0109] It can be understood that the processor in the embodiments of this specification can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiments can be completed by the integrated logic circuit in the hardware of the processor or instructions in the form of software. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this specification. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of this specification can be directly embodied as being executed and completed by a hardware decoding processor, or can be executed and completed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0110] It can be understood that the memory in the embodiments of this specification can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0111] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this specification.

[0112] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0113] In the several embodiments provided in this specification, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0114] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0115] In addition, in each embodiment of this specification, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0116] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this specification, in essence, or the part that contributes to the prior art or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of this specification. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0117] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A wide-angle image processing method, characterized in that: include: Acquire an image of the fundus leopard spot region of the target object; Performing image geometric transformation on the fundus leopard spot region image to obtain a transformed image of the fundus leopard spot region image; Performing threshold segmentation on the transformed image to obtain a vortex vein center candidate region image; Determining a target leopard spot area based on the vortex vein center candidate area image; The vortex vein center area is determined according to the leopard spot characteristics of the target leopard spot area.

2. The wide-angle image processing method according to claim 1, characterized in that: Determining the vortex vein center area according to the leopard spot characteristics of the target leopard spot area includes: Calculating the number of leopard spots in the target leopard spot area; Calculating the number of leopard spots on the boundary of the target leopard spot area; When the number of leopard spots in the target leopard spot area reaches a first quantity threshold and the number of leopard spots on the boundary of the target leopard spot area reaches a second quantity threshold, the target leopard spot area is determined to be the vortex vein center area, wherein the first quantity threshold is less than the second quantity threshold.

3. The wide-angle image processing method according to claim 1, characterized in that: Also includes: The field of view of the fundus leopard spot area image is determined according to the number of the vortex vein center areas of the target object.

4. The wide-angle image processing method according to claim 1, characterized in that: Also includes: The shooting quality score of the fundus leopard spot area image is determined according to the number of the vortex vein central areas of the target object, and the quality of the fundus leopard spot area image is evaluated according to the shooting quality score, wherein the quality of the fundus leopard spot area image includes the shooting range or shooting angle of the fundus leopard spot area image.

5. The wide-angle image processing method according to claim 1, characterized in that: Also includes: Acquire the centerline area of ​​the fundus leopard spot area image; Based on the centerline region, determining an average grayscale value of a region of the transformed image corresponding to the centerline region; The step of performing threshold segmentation on the transformed image to obtain a vortex vein center candidate region image includes: The transformed image is subjected to threshold segmentation according to the average gray value to obtain the vortex vein center candidate region image.

6. The wide-angle image processing method according to claim 5, characterized in that: The step of performing threshold segmentation on the transformed image according to the average gray value to obtain the vortex vein center candidate area image comprises: Based on the average gray value, determining a target segmentation threshold; The transformed image is subjected to threshold segmentation according to the target segmentation threshold to obtain the vortex vein center candidate region image.

7. The wide-angle image processing method according to claim 1, characterized in that: The step of determining a target leopard spot region based on the vortex vein center candidate region image comprises: Extracting the optic disc diameter corresponding to the fundus leopard spot area image and determining the radius value of the target area according to the optic disc diameter; In the vortex vein center candidate area image, the target leopard spot area is obtained by taking the center of the vortex vein center candidate area image as the center of a circle and taking the target area radius value as the radius.

8. A wide-angle image processing device, characterized in that: include: An acquisition module, used for acquiring an image of a fundus leopard spot region of a target object; An image geometric transformation module, used for performing image geometric transformation on the fundus leopard spot region image to obtain a transformed image of the fundus leopard spot region image; A threshold segmentation module, used for performing threshold segmentation on the transformed image to obtain a candidate region image of the vortex vein center; A determination module, used for determining a target leopard spot area based on the vortex vein center candidate area image; A judgment module, used for determining the vortex vein center area according to the leopard spot characteristics of the target leopard spot area; The display module is used to display the marking information of the vortex vein center area.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the wide-angle image processing method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is used to execute the wide-angle image processing method according to any one of claims 1 to 7.

Images