Method and system for generating training image, computer device, and storage medium

Abstract

Disclosed are a method and a system for generating a training image, a computer device, and a storage medium. The method comprises: determining, in a first image, a target region comprising sensitive frequency band components corresponding to a sensitive spatial frequency of the visual system of a subject; determining a target color on the basis of the severity of amblyopia in the subject; and filling the target region with the target color to give a second image for vision training of the subject.

Description

Training image generation method, system, computer device and storage medium

[0001] Related applications

[0002] This application claims priority to Chinese patent application number 202311405292.2, filed on October 25, 2023, entitled “Training image generation method, system, computer device and storage medium,” the entire text of which is hereby incorporated by reference. Technical Field

[0003] The present application relates to the field of image processing, and in particular to a training image generation method, system, computer device, and storage medium. Background Art

[0004] Amblyopia is a disease characterized by low visual acuity in the center of the macula of the fundus, which is usually manifested as a decrease in the eye's contrast sensitivity to signals of different spatial frequencies.

[0005] Contrast sensitivity (CS) refers to a type of resolution ability. In daily life, the human eye needs to distinguish objects with clear boundaries as well as objects with blurred boundaries.

[0006] Contrast sensitivity test (CSF for short) is a quantitative test of visual function that measures the black-and-white contrast (contrast) on the surface of an object required for the visual system to identify the spatial frequency (cycles / degree) of objects of different sizes. It is used to evaluate the visual system's ability to distinguish objects of different sizes.

[0007] For the treatment of amblyopia, related technologies have proposed visual stimulation therapy, which uses training images to stimulate the patient to improve the vision of the amblyopic eye. However, the training effect of this method is not ideal.

[0008] With respect to the problem that the training images used for vision training of amblyopic eyes in related technologies have poor training effects, no effective solution has been proposed so far.

[0009] Summary of the Invention

[0010] In this embodiment, a training image generation method, system, computer device and storage medium are provided to solve the problem in the related art that the training effect of training images used for amblyopic vision training is poor.

[0011] In a first aspect, a training image generation method is provided in this embodiment, comprising: determining a target area in a first image; wherein the target area contains a sensitive frequency band component adapted to the sensitive spatial frequency of the subject's visual system; determining a target color; wherein the target color is determined based on the subject's amblyopia; filling the target area with the target color to obtain a second image; wherein the second image is used for vision training of the subject.

[0012] In some embodiments, determining the target area in the first image includes: obtaining the sensitive spatial frequency of the subject's visual system; setting a sensitive frequency band filter based on the sensitive spatial frequency; applying the sensitive frequency band filter to the third image to obtain the first image and the target area determined in the first image.

[0013] In some embodiments, setting a sensitive frequency band filter according to the sensitive spatial frequency includes setting the sensitive frequency band filter with the sensitive spatial frequency as a cutoff frequency.

[0014] In some embodiments, applying the sensitive band filter to a third image to obtain the first image and the target area determined in the first image includes: multiplying a first frequency domain signal of the third image by the sensitive band filter to obtain a second frequency domain signal; converting the second frequency domain signal into a time domain signal, and using the time domain signal as the sensitive band component.

[0015] In some embodiments, determining the target color includes: determining the target color according to the amblyopia condition of the subject; wherein the amblyopia condition includes a degree of amblyopia, and the higher the degree of amblyopia of the subject, the greater the proportion of red light in the target color; or, the lower the degree of amblyopia of the subject, the greater the proportion of blue light in the target color; or, the amblyopia condition includes a type of amblyopia, and when the subject has hyperopic amblyopia, the target color is red, and when the subject has myopic amblyopia, the target color is green.

[0016] In some embodiments, before filling the target area with the target color, the method further includes: in the target area, setting the grayscale of pixels greater than a critical grayscale value to a grayscale maximum value, setting the grayscale of pixels less than the critical grayscale value to a grayscale minimum value, and setting the grayscale of pixels equal to the critical grayscale value to the grayscale maximum value or the grayscale minimum value.

[0017] In some embodiments, the critical grayscale value is not lower than a preset ratio of the maximum amplitude of the image signal in the target area; or, the critical grayscale value includes a target segmentation threshold; wherein, when the target area is segmented into foreground and background parts according to the target segmentation threshold, the inter-class variance of the target area is maximized.

[0018] In a second aspect, a training image generation system is provided in this embodiment, comprising: an image acquisition module, a processing module and a display module; wherein the image acquisition module is used to acquire images; the processing module is used to receive the images and execute the training image generation method described in the first aspect on the images to generate training images; the display module is used to display the training images generated by the processing module.

[0019] In a third aspect, a computer device is provided in this embodiment, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the training image generation method described in the first aspect above.

[0020] In a fourth aspect, a computer-readable storage medium is provided in this embodiment, on which a computer program is stored. When the computer program is executed by a processor, the steps of the training image generation method described in the first aspect are implemented.

[0021] The above-mentioned training image generation method, system, computer device and storage medium enhance the stimulation targeting of the training image to the amblyopic eye by filling the target color into the target area to combine the sensitive frequency band components and the target color, thereby achieving better training effect of the training image.

[0022] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the conventional technology, the following briefly introduces the drawings required for use in the embodiments or the conventional technology descriptions. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the disclosed drawings without any creative work.

[0024] FIG1 is a block diagram of the hardware structure of a terminal for a training image generation method according to an embodiment.

[0025] FIG2 is a flowchart of a method for generating a training image in an embodiment.

[0026] FIG3 is a flowchart of a method for determining a target area according to an embodiment.

[0027] FIG4 is a schematic diagram of a Butterworth high-pass filter according to an embodiment.

[0028] FIG5 is a random screenshot of a sampled image during a training session in one embodiment.

[0029] FIG6 is a schematic diagram of sensitive frequency band components obtained after processing a sampled image in one embodiment.

[0030] FIG. 7 is a binary sensitive frequency band component template corresponding to FIG. 6 in one embodiment.

[0031] FIG8 is a training image finally generated in one embodiment.

[0032] FIG9 is a flowchart of a method for generating a training image in another embodiment.

[0033] FIG10 is a schematic structural diagram of a training image generation system according to an embodiment.

[0034] FIG11 is a diagram showing the internal structure of a computer device according to an embodiment. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0036] Unless otherwise defined, the technical terms or scientific terms involved in this application should have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. "One", "an", "a kind of", "the", "these" and similar words in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants involved in this application are intended to cover non-exclusive inclusion; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. "Connect", "be connected", "coupled" and similar words involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Multiple" involved in this application refers to two or more. "And / or" describes the relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, and B exists alone. Generally, the character " / " indicates that the related objects are in an "or" relationship. The terms "first," "second," "third," etc. used in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0037] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, when running on a terminal, Figure 1 is a hardware structure block diagram of a terminal of a training image generation method according to an embodiment of the present application. As shown in Figure 1, the terminal may include one or more (only one is shown in Figure 1) processors 11 and a memory 12 for storing data, wherein the processor 11 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above-mentioned terminal may also include a transmission device 13 and an input and output device 14 for communication functions. It will be understood by those skilled in the art that the structure shown in Figure 1 is only for illustration and does not limit the structure of the above-mentioned terminal. For example, the terminal may also include more or fewer components than those shown in Figure 1, or have a different configuration than that shown in Figure 1.

[0038] The memory 12 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the training image generation method in this embodiment. The processor 11 executes various functional applications and data processing by running the computer program stored in the memory 12, that is, implementing the above-mentioned method. The memory 12 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 12 may further include a memory remotely located relative to the processor 11, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0039] The transmission device 13 is used to receive or send data via a network. The network may include a wireless network provided by the terminal's communications provider. In one embodiment, the transmission device 13 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 13 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0040] In one embodiment, FIG2 provides a flowchart of a method for generating a training image, which is described by taking the method applied to the terminal in FIG1 as an example and includes the following steps.

[0041] Step S201 : determining a target area in a first image; wherein the target area includes a sensitive frequency band component adapted to a sensitive spatial frequency of a subject's visual system.

[0042] The sensitive frequency band components are adapted to the sensitive spatial frequency of the subject's visual system, which means that the frequency of the sensitive frequency band components is not lower than the sensitive spatial frequency of the subject's visual system. The sensitive frequency band refers to the frequency band where the signal frequency is not lower than the sensitive spatial frequency.

[0043] Step S202 , determining a target color; wherein the target color is determined based on the amblyopia condition of the subject.

[0044] Most people have three types of cone cells in their eyes, corresponding to red, blue, and green. Amblyopia can be categorized as severe, moderate, and mild. Severe amblyopia has a visual acuity of ≤0.1, moderate amblyopia has a visual acuity of 0.2-0.5, and mild amblyopia has a visual acuity of 0.6-0.8. Red light, due to its longer wavelength, is suitable for stimulating red-sensitive cone cells in the fovea and is more effective for severe amblyopia. Blue light, on the other hand, has a shorter wavelength and slower propagation speed, stimulating blue-sensitive cone cells in the fovea, which aligns with the axial length of the eye in mild amblyopia and is more effective for treating mild amblyopia. Therefore, in some embodiments, a target color can be selected based on the subject's amblyopia severity, or even synthesized from the three primary colors. Amblyopia can be categorized into severity and type. When determining a target color based on amblyopia severity, the higher the subject's amblyopia, the greater the proportion of red light in the target color; the lower the subject's amblyopia, the greater the proportion of blue light in the target color. When determining the target color according to the type of amblyopia, red light can be used for visual stimulation for hyperopic amblyopia; and green light can be used for visual stimulation for myopic amblyopia.

[0045] Step S203: Fill the target area with the target color to obtain a second image; wherein the second image is used for vision training of the examinee.

[0046] On the one hand, the contrast sensitivity of the amblyopic eye to signals of different spatial frequencies is reduced, among which the contrast sensitivity to high spatial frequency signals is particularly reduced. By stimulating the amblyopic eye with high spatial frequencies, the visual nerve is easily excited and the visual nerve axons are activated, which is conducive to restoring visual function and establishing stereoscopic vision. On the other hand, in addition to distinguishing spatial frequency details, the center of the macula also has the function of distinguishing colors through cone cells. If during the training treatment of the amblyopic eye, the cone cells are stimulated by target colors to enhance their photosensitivity, thereby transmitting more accurate visual signals to the visual center, it can also play a role in treating amblyopia.

[0047] Based on the above analysis, in the above steps S201 to S203, by filling the target area with the target color to combine the sensitive frequency band components and the target color, the stimulation targeting of the training image to the amblyopic eye is enhanced, thereby making the training effect of the training image better.

[0048] In one embodiment, as shown in FIG3 , step S201 , determining a target area in a first image, can be implemented by the following steps.

[0049] Step S301, obtaining the sensitive spatial frequency of the subject's visual system. The sensitive spatial frequency of the subject's visual system can be obtained by obtaining electrophysiological data of the subject's amblyopic eye. The electrophysiological data of the amblyopic eye can be obtained through a CSF examination, that is, examining the subject's visual system's ability to recognize sinusoidal grating visual targets of different spatial frequencies, thereby obtaining the sensitive spatial frequency of the subject's visual system. For example, the CSF device used has a test distance of 400 mm, and a contrast of 1 is used as the test standard. The sensitive spatial frequency f of the amblyopic eye obtained is 4 CPD.

[0050] Step S302, setting a sensitive frequency band filter according to the sensitive spatial frequency. The sensitive frequency band filter can be set using the sensitive spatial frequency as the cutoff frequency. For example, when the sensitive spatial frequency f of the amblyopic eye is 4CPD, the sensitive spatial frequency band used for training is a frequency band slightly larger than 4CPD, that is, the cutoff frequency can be set to 4CPD. The filter types include but are not limited to Butterworth filter, Gaussian filter, and Chebyshev filter. Considering that the Butterworth filter has a smooth amplitude-frequency characteristic both inside and outside the passband, the Butterworth filter is used as an example for explanation below.

[0051] The n-th order Butterworth high-pass filter is defined as follows:

[0052] Here, D0 is the distance between the cutoff frequency and the origin, and D(u,v) is the distance between the frequency point coordinates (u,v) and the origin. In practical applications, real-time image acquisition is performed using a computer camera. The display size is approximately 250mm × 140mm, the sampled image resolution is 1280 × 720, and the test distance remains at 400mm. The longer side is the width, and the corresponding field of view is approximately 250 × 180 / (400 × 3.14) = 36 degrees. Therefore, the sampling point positions corresponding to the sensitive spatial frequency f are 36 × 4 = 144, that is, D0 = 144. Taking n = 2, we can obtain the corresponding Butterworth frequency-domain high-pass filter. As an example, Figure 4 shows a schematic diagram of a Butterworth high-pass filter.

[0053] In step S303, a sensitive band filter is applied to the third image to obtain the first image and the target area determined in the first image. The first frequency domain signal of the third image can be multiplied by the sensitive band filter to obtain a second frequency domain signal; the second frequency domain signal is converted into a time domain signal, and the time domain signal is used as the sensitive band component.

[0054] The third image (i.e., the sampled image) is used as the input signal and a two-dimensional Fourier transform is performed on it to obtain the corresponding first frequency domain signal. The first frequency domain signal is then multiplied by the Butterworth frequency domain high-pass filter to obtain the second frequency domain signal. The second frequency domain signal is then subjected to a two-dimensional inverse Fourier transform to obtain the corresponding sensitive frequency band time domain component. As an example, Figure 5 shows a random screenshot of the sampled image of this training (i.e., the third image, which is actually in color). Correspondingly, Figure 6 shows a schematic diagram of the sensitive frequency band components obtained after processing the sampled image.

[0055] In one embodiment, step S203, before filling the target area with the target color, also includes the following steps: in the target area, the pixel grayscale greater than the critical grayscale value is set to the grayscale maximum value, the pixel grayscale less than the critical grayscale value is set to the grayscale minimum value, and the pixel grayscale equal to the critical grayscale value is set to the grayscale maximum value or the grayscale minimum value.

[0056] After calculating the critical grayscale value, for the sensitive band components, when the pixel grayscale value is greater than the critical grayscale value, it is set to 255; when it is less than the critical grayscale value, it is set to 0; when it is equal to the critical grayscale value, it is set to 255 or 0. This binarizes the sensitive band components and obtains a binary sensitive band component template. As an example, Figure 7 shows the binary sensitive band component template corresponding to Figure 6.

[0057] After obtaining the binary sensitive band component template, it can be ANDed with the image to be processed, set to the target color, and obtain the final training image. As an example, using red as an example, the final generated training image is shown in Figure 8, where the white areas are actually displayed as red.

[0058] There are two optional ways to set the critical grayscale value.

[0059] Solution 1: The critical grayscale value must be no less than a preset percentage of the maximum amplitude of the image signal in the target area. This can be determined by performing comparative analysis over multiple experiments, using a certain percentile of the maximum amplitude of the image signal in the target area as the preset percentage.

[0060] Solution 2: The critical grayscale value includes the target segmentation threshold; when the target region is segmented into foreground and background components according to the target segmentation threshold, the inter-class variance of the target region is maximized. The target region is segmented into foreground and background components based on the segmentation threshold, where the foreground primarily contains the image signal and the background primarily contains noise. The segmentation threshold is adjusted repeatedly until the inter-class variance of the target region reaches a maximum, thus obtaining the target segmentation threshold. The significance of maximizing the inter-class variance is that it minimizes the probability of misclassification.

[0061] In one embodiment, FIG9 provides another training image generation method. As shown in FIG9 , the process includes the following steps.

[0062] Step S401 : obtaining a sensitive spatial frequency band based on electrophysiological data of the subject's amblyopic eye.

[0063] Step S402 : designing a sensitive frequency band filter according to the sensitive spatial frequency band, and applying the sensitive frequency band filter to the third image to obtain the first image and a target area determined in the first image, wherein the target area includes a sensitive frequency band component.

[0064] Step S403: Determine the critical grayscale value according to the maximum inter-class variance criterion. For the sensitive frequency band component in FIG6 , calculate its critical grayscale value, for example, 20.

[0065] Step S404: Binarize the target area according to the critical grayscale value to obtain a binary sensitive band component template, that is, set the grayscale of pixels greater than 20 to 255, set the grayscale of pixels less than 20 to 0, and set the grayscale of pixels equal to 20 to 255 or 0.

[0066] Step S405: Select a target color according to the degree of amblyopia of the subject.

[0067] Step S406: Fill the target area with the target color to obtain a second image.

[0068] The above steps can be applied to different degrees of amblyopic eye stimulation. As an example, for patients with severe amblyopia, the target color can be red. Among them, the Butterworth high-pass frequency domain filter is shown in Figure 4, a random screenshot of a certain training frame is shown in Figure 5, the sensitive frequency band components of the obtained training image are shown in Figure 6, the binarized sensitive frequency band component template is shown in Figure 7, and the final generated real-time training image is shown in Figure 8. The red edge amblyopia training image corresponding to the sensitive frequency band generated according to the above steps is more targeted in stimulating the cone cells of the amblyopic eye. By stimulating them to be excited, it indirectly plays a role in treating amblyopia. Moreover, the treatment method is simple and easy to implement.

[0069] Based on the same inventive concept, in one embodiment, a training image generation system is also provided. Figure 10 shows a schematic structural diagram of the training image generation system. As shown in Figure 10 , the system includes an image acquisition module 21, a processing module 22, and a display module 23. The image acquisition module 21 is used to acquire images; the processing module 22 is used to receive images and execute the training image generation method of any of the above-described embodiments on the images to generate training images; and the display module 23 is used to display the training images generated by the processing module 22.

[0070] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0071] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in Figure 11. The computer device includes a processor, memory, a communication interface, a display unit, and an input device connected via a system bus. 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 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 computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal via wired or wireless communication. The wireless communication may be achieved via Wi-Fi, a mobile cellular network, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements a training image generation method. The display unit of the computer device may be a liquid crystal display unit or an electronic ink display unit. The input device of the computer device may be a touch layer covering the display unit, or may be buttons, a trackball, or a touchpad provided on the computer device housing, or may be an external keyboard, touchpad, or mouse.

[0072] Those skilled in the art will understand that the structure shown in FIG11 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0073] In addition, in conjunction with the training image generation method provided in the above embodiments, a storage medium may be provided in this embodiment to implement the method. The storage medium stores a computer program that, when executed by a processor, implements any of the training image generation methods in the above embodiments.

[0074] In one embodiment, when the computer program is executed by a processor, the following method is implemented: determining a target area in a first image; wherein the target area contains a sensitive frequency band component that is adapted to the sensitive spatial frequency of the subject's visual system; determining a target color; wherein the target color is determined based on the subject's amblyopia; filling the target area with the target color to obtain a second image; wherein the second image is used for vision training of the subject.

[0075] In one embodiment, when the computer program is executed by a processor, the following method is implemented: obtaining the sensitive spatial frequency of the subject's visual system; setting a sensitive frequency band filter based on the sensitive spatial frequency; applying the sensitive frequency band filter to the third image to obtain the first image and the target area determined in the first image.

[0076] In one embodiment, when the computer program is executed by a processor, the following method is implemented: a sensitive frequency band filter is set with the sensitive spatial frequency as the cutoff frequency.

[0077] In one embodiment, when the computer program is executed by a processor, the following method is implemented: multiplying a first frequency domain signal of the third image by a sensitive frequency band filter to obtain a second frequency domain signal; converting the second frequency domain signal into a time domain signal, and using the time domain signal as a sensitive frequency band component.

[0078] In one embodiment, when the computer program is executed by the processor, the following method is implemented: determining the target color according to the amblyopia condition of the subject; wherein the amblyopia condition includes the degree of amblyopia, and the higher the degree of amblyopia of the subject, the greater the proportion of red light in the target color, or, the lower the degree of amblyopia of the subject, the greater the proportion of blue light in the target color; or, the amblyopia condition includes the type of amblyopia, and when the subject has hyperopic amblyopia, the target color is red, and when the subject has myopic amblyopia, the target color is green.

[0079] In one embodiment, the computer program implements the following method when executed by a processor: in the target area, the pixel grayscale greater than the critical grayscale value is set to the grayscale maximum value, the pixel grayscale less than the critical grayscale value is set to the grayscale minimum value, and the pixel grayscale equal to the critical grayscale value is set to the grayscale maximum value or the grayscale minimum value.

[0080] It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0081] Obviously, the accompanying drawings are merely examples or embodiments of the present application. A person skilled in the art can also apply the present application to other similar situations based on these drawings without inventive effort. Furthermore, it is understandable that, although the work involved in this development process may be complex and lengthy, certain design, manufacturing, or production changes based on the technical content disclosed in this application are merely routine technical means for a person skilled in the art and should not be considered to constitute a deficiency in the disclosure of the present application.

[0082] The term "embodiment" as used in this application refers to specific features, structures, or characteristics described in conjunction with the embodiment that can be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily mean that the embodiment is the same, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is understood, either explicitly or implicitly, by those skilled in the art that the embodiments described in this application can be combined with other embodiments when there is no conflict.

[0083] 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, storage, and display, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. The acquisition, storage, use, and processing of data involved in the embodiments of this application comply with the relevant provisions of national laws and regulations.

[0084] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented 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 memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may 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 may include random access memory (RAM) or external cache memory, etc. By way of 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 the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0085] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned 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 specification.

[0086] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of patent protection. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A training image generation method, characterized in that: include: Determine a target area in the first image; wherein the target area contains a sensitive frequency band component adapted to a sensitive spatial frequency of a visual system of the subject; Determining a target color; wherein the target color is determined based on the amblyopia of the subject; The target area is filled with the target color to obtain a second image; wherein the second image is used for vision training of the subject.

2. The training image generation method according to claim 1, wherein: Determining the target area in the first image includes: Acquiring a sensitive spatial frequency of the visual system of the subject; According to the sensitive spatial frequency, a sensitive frequency band filter is set; The sensitive frequency band filter is applied to the third image to obtain the first image and the target area determined in the first image.

3. The training image generation method according to claim 2, wherein: According to the sensitive spatial frequency, setting a sensitive frequency band filter comprises: The sensitive frequency band filter is set with the sensitive spatial frequency as the cutoff frequency.

4. The training image generation method according to claim 2, wherein: Applying the sensitive frequency band filter to the third image to obtain the first image and the target area determined in the first image includes: multiplying the first frequency domain signal of the third image by the sensitive band filter to obtain a second frequency domain signal; The second frequency domain signal is converted into a time domain signal, and the time domain signal is used as the sensitive frequency band component.

5. The training image generation method according to claim 1, wherein: Determining the target color includes: determining the target color according to the amblyopia of the subject; wherein, The amblyopia condition includes the degree of amblyopia. The higher the amblyopia degree of the subject, the greater the proportion of red light in the target color. Alternatively, the lower the amblyopia degree of the subject, the greater the proportion of blue light in the target color. Alternatively, The amblyopia condition includes a weak type. When the subject has hyperopic amblyopia, the target color is red. When the subject has myopic amblyopia, the target color is green.

6. The training image generation method according to claim 1, wherein: Before filling the target area with the target color, the method further includes: In the target area, the pixel grayscale greater than the critical grayscale value is set to the grayscale maximum value, the pixel grayscale less than the critical grayscale value is set to the grayscale minimum value, and the pixel grayscale equal to the critical grayscale value is set to the grayscale maximum value or the grayscale minimum value.

7. The training image generation method according to claim 6, wherein: The critical grayscale value is not lower than a preset ratio of the maximum amplitude of the image signal in the target area; or The critical grayscale value includes a target segmentation threshold; wherein, when the target region is segmented into a foreground and a background according to the target segmentation threshold, the inter-class variance of the target region is maximized.

8. A training image generation system, characterized in that: include: Image acquisition module, processing module and display module; wherein, The image acquisition module is used to acquire images; The processing module is used to receive the image and execute the training image generation method according to any one of claims 1 to 7 on the image to generate a training image; The display module is used to display the training image generated by the processing module.

9. A computer device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the training image generation method according to any one of claims 1 to 7.

10. 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 training image generation method according to any one of claims 1 to 7 are implemented.

Images