An image evaluation method, device, electronic equipment and storage medium
By performing dehazing and clarity analysis on fundus images, the problem of low image clarity was solved, image quality was improved, and more accurate lesion detection was supported.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- EVISION TECH (BEIJING) CO LTD
- Filing Date
- 2023-02-20
- Publication Date
- 2026-05-22
Smart Images
Figure CN116167996B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the fields of computer vision and image analysis, specifically to an image evaluation method, apparatus, electronic device, and storage medium. Background Technology
[0002] In the detection of eye diseases, the recognition of fundus images is a very important diagnostic tool.
[0003] However, during the acquisition of fundus images, limitations such as the shooting environment, the adjustment of the imaging equipment, image exposure, and the influence of fundus structures and details result in low clarity and poor quality images, significantly impacting the accuracy of subsequent interpretation by doctors. Furthermore, besides hardware equipment and shooting techniques, the low clarity and poor quality of fundus images are also due to limitations imposed by the fundus structures and details captured in the images.
[0004] Therefore, how to evaluate the acquired fundus images has become a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention
[0005] This application provides an image evaluation method, apparatus, electronic device, and storage medium for evaluating captured fundus images.
[0006] According to a first aspect of the embodiments of this application, an image evaluation method is provided, comprising:
[0007] The fundus images to be evaluated are dehazed to obtain dehazed fundus images;
[0008] The vascular region in the defogging fundus image is analyzed to determine the clarity of the defogging fundus image;
[0009] The evaluation result of the fundus image is obtained based on the clarity of the defogging fundus image.
[0010] In one alternative embodiment of this application, the fundus image to be evaluated is obtained in the following manner:
[0011] The first fundus image is input into a pre-trained image preliminary evaluation model so that the image preliminary evaluation model can perform a preliminary evaluation of the first fundus image and obtain a preliminary evaluation result of the first fundus image.
[0012] If the preliminary evaluation result of the first fundus image determines that the first fundus image is a substandard image, the first fundus image shall be used as the fundus image to be evaluated.
[0013] In one optional embodiment of this application, the preliminary image evaluation model is trained in the following manner:
[0014] Obtain fundus images labeled with image evaluation results;
[0015] The fundus images labeled with the image evaluation results are used as training samples to train the preliminary image evaluation model.
[0016] In one optional embodiment of this application, the step of dehazing the fundus image to be evaluated to obtain a dehazed fundus image includes:
[0017] From the channel images separated from the fundus images to be evaluated, the channel image with the smallest pixel value is selected, and the pixel mean value information of the channel image is determined.
[0018] The channel image is subjected to mean filtering to obtain the mean-filtered channel image;
[0019] The dehazing parameters are determined based on the image after mean filtering and the image of the channel with the largest pixel value.
[0020] Based on preset pixel adjustment parameters and the pixel mean information of the channel image, pixel adjustment is performed on the channel image after mean filtering to determine the pixel-adjusted channel image;
[0021] Based on the dehazing parameters and the channel image with the smallest pixel value or the channel image after pixel adjustment, the fundus image to be evaluated is dehazed to obtain a dehazed fundus image.
[0022] In one optional embodiment of this application, before the step of dehazing the fundus image to be evaluated to obtain a dehazed fundus image, the method further includes:
[0023] The fundus image to be evaluated is denoised to obtain a denoised fundus image to be evaluated.
[0024] In one optional embodiment of this application, before the step of analyzing the vascular region in the dehazed fundus image to determine the clarity of the dehazed fundus image, the method further includes:
[0025] At least one channel of the dehazed fundus image is selected, and image enhancement processing is performed on the dehazed fundus image to obtain an enhanced fundus image.
[0026] In one optional embodiment of this application, selecting at least one channel from the dehazed fundus image and performing image enhancement processing on the dehazed fundus image to obtain an enhanced fundus image includes:
[0027] Image enhancement processing is performed on the G channel image in the dehazed image, and the G channel image after image enhancement processing is used as the enhanced fundus image.
[0028] In one optional embodiment of this application, analyzing the vascular region in the dehazed fundus image to determine the clarity of the dehazed fundus image includes:
[0029] The contrast between the vascular region and other regions of the fundus image is determined, and the sharpness of the enhanced fundus image is determined based on the contrast.
[0030] According to a second aspect of the embodiments of this application, an image evaluation apparatus is provided, comprising:
[0031] The first unit is used to dehaze the fundus images to be evaluated, and obtain dehazed fundus images;
[0032] The second unit is used to analyze the vascular region in the defogging fundus image to determine the clarity of the defogging fundus image;
[0033] The third unit is used to obtain the evaluation result of the fundus image based on the clarity of the defogging fundus image.
[0034] According to a third aspect of the embodiments of this application, an electronic device is provided, comprising:
[0035] processor;
[0036] Memory used to store the processor's executable instructions;
[0037] The processor is configured to execute the image evaluation generation method described above by running instructions in the memory.
[0038] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided, the storage medium storing a computer program, which, when executed by a processor, performs the above-described image evaluation method.
[0039] Compared with the prior art, this application has the following advantages:
[0040] This application provides a method, apparatus, electronic device, and storage medium for evaluating fundus images. The method for evaluating fundus images includes: performing dehazing processing on the fundus image to be evaluated to obtain a dehazed fundus image; analyzing the vascular region in the dehazed fundus image to determine the clarity of the dehazed fundus image; and obtaining an evaluation result of the fundus image based on the clarity of the dehazed fundus image.
[0041] The aforementioned fundus image evaluation method involves, after obtaining the fundus image to be evaluated, performing dehazing processing on the fundus image to obtain a dehazed fundus image. Then, the fundus image to be evaluated is evaluated based on the clarity of the dehazed fundus image. This approach can effectively avoid the influence of low clarity and poor quality of fundus images, as well as the effects of fundus image acquisition hardware and acquisition techniques on fundus images. It is beneficial for the classification and processing of lesions in fundus images and the analysis of fundus images. Attached Figure Description
[0042] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.
[0043] Figure 1 A flowchart of an image evaluation method provided in an embodiment of this application;
[0044] Figure 2 This is a schematic diagram of the structure of an image evaluation device provided in another embodiment of this application;
[0045] Figure 3 This is a schematic diagram of an electronic device structure provided for another embodiment of this application. Detailed Implementation
[0046] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0047] In the detection of eye diseases, the recognition of fundus images is a very important diagnostic tool.
[0048] However, during the acquisition of fundus images, limitations such as the shooting environment, the adjustment of the imaging equipment, image exposure, and the influence of fundus structures and details result in low clarity and poor quality images, significantly impacting the accuracy of subsequent interpretation by doctors. Furthermore, besides hardware equipment and shooting techniques, the low clarity and poor quality of fundus images are also due to limitations imposed by the fundus structures and details captured in the images.
[0049] Therefore, how to evaluate the acquired fundus images has become a technical problem that urgently needs to be solved by those skilled in the art.
[0050] To address the aforementioned technical problems, this application provides a method, apparatus, electronic device, and storage medium for evaluating fundus images, which will be described in detail in the following embodiments.
[0051] Exemplary methods
[0052] This application first provides an image evaluation method, the core of which is that after obtaining the fundus image to be evaluated, the fundus image to be evaluated is dehazed to obtain a dehazed fundus image. Then, based on the clarity of the dehazed fundus image, the fundus image to be evaluated is evaluated. This method can effectively avoid the influence of low clarity and poor quality of fundus images, as well as the hardware equipment and shooting techniques used to capture fundus images, on fundus images, which is beneficial for the classification of lesions in fundus images and the analysis of fundus images.
[0053] In one optional embodiment of this application, the entity implementing the image evaluation method may be any combination of two or more user terminals such as laptops, tablets, desktop computers, set-top boxes, and mobile devices (e.g., mobile phones, personal digital assistants, dedicated messaging devices), or an image processor, medical analyzer, or server specifically designed for analyzing fundus images.
[0054] Please refer to Figure 1 , Figure 1 This is a flowchart of an image evaluation method provided in an embodiment of this application.
[0055] like Figure 1 As shown, the image evaluation method includes the following steps S101 to S103:
[0056] Step S101: Dehaze the fundus image to be evaluated to obtain a dehazed fundus image.
[0057] The fundus image to be evaluated can be understood as a fundus image of the patient obtained through fundus imaging technology, or a fundus image recorded in a medical record.
[0058] In actual shooting, unclear fundus images are usually attributed to factors such as improper equipment adjustment, abnormal exposure, undamaged lens, and inaccurate focus. However, the unclear fundus images may also be due to underlying eye diseases. For example, while regular fundus images clearly show fundus structures such as the optic disc, macula, and retinal blood vessels, images of cataract patients often fail to clearly visualize these structures and details.
[0059] In practical applications, images that are clearly visible and show fundus structures and details are considered acceptable and do not require further evaluation. Furthermore, fundus images in medical settings assist medical personnel in confirming the presence of lesions in the fundus; therefore, fundus images that clearly show no lesions also do not require further analysis.
[0060] To exclude fundus images that are clearly clear and acceptable, or that do not contain lesions, the fundus images can be screened before performing step S101 above to obtain the fundus images to be evaluated:
[0061] The first fundus image is input into a pre-trained image preliminary evaluation model so that the image preliminary evaluation model can perform a preliminary evaluation of the first fundus image and obtain a preliminary evaluation result of the first fundus image.
[0062] If the preliminary evaluation result of the first fundus image determines that the first fundus image is a qualified image, the first fundus image shall be used as the fundus image to be evaluated.
[0063] In practical applications, this application employs Machine Learning (ML) to train the preliminary image evaluation model. Machine learning (a multidisciplinary field involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, and other disciplines) is specifically used to study how computers can simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their capabilities. Machine learning typically includes techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, and inductive learning. Machine learning is a branch of Artificial Intelligence (AI) technology.
[0064] Specifically, the preliminary image evaluation model can be trained in the following way:
[0065] Obtain fundus images labeled with image evaluation results;
[0066] The preliminary image evaluation model is trained using fundus images labeled with image evaluation results as training samples.
[0067] The image evaluation result can be understood as a label for the fundus image. In one optional embodiment of this application, the image evaluation result can be 0 or 1. For example, in the classification process of whether there is a cataract in the fundus image, 0 indicates that the fundus image does not have a cataract; 1 indicates that the fundus image has a cataract.
[0068] Furthermore, the purpose of dehazing the fundus image to be evaluated is to reduce the influence of light on the image capturing process and improve the visibility and color contrast of the fundus in the fundus image.
[0069] In this embodiment of the application, the dehazing of the fundus image to be evaluated can be performed through the following steps S1 to S5:
[0070] Step S1: Select the channel image with the smallest pixel value from the channel images separated from the fundus image to be evaluated, and determine the pixel mean information of the channel image.
[0071] The channel image separated from the fundus image to be evaluated can be a single channel image or a combination of multiple channels; this application does not impose any restrictions on this.
[0072] Step S2: Perform mean filtering on the channel image to obtain the mean-filtered channel image;
[0073] Step S3: Determine the dehazing parameters based on the image after mean filtering and the channel image with the largest pixel value;
[0074] Step S4: According to the preset pixel adjustment parameters and the pixel mean information of the channel image, perform pixel adjustment on the channel image after mean filtering to determine the pixel-adjusted channel image;
[0075] Step S5: Based on the dehazing parameters and the channel image with the smallest pixel value or the channel image after pixel adjustment, perform dehazing processing on the fundus image to be evaluated to obtain a dehazed fundus image.
[0076] In one optional embodiment of this application, before dehazing the fundus image to be evaluated, the method further includes, in order to improve the dehazing effect:
[0077] The fundus image to be evaluated is denoised to obtain a dehazed fundus image, and the dehazed fundus image is used as the fundus image to be evaluated.
[0078] Specifically, the denoising process on the fundus image to be evaluated can be achieved by denoising methods such as median filtering, and this application does not impose any restrictions on this.
[0079] Step S102: Analyze the vascular region in the defogging fundus image to determine the clarity of the defogging fundus image.
[0080] In this embodiment of the application, the analysis of the vascular region in the dehazed fundus image refers to determining the vascular area of the vascular region in the fundus image; the pixel value of the vascular region; and the pixel difference between the pixel value of the vascular region and the pixel value of the non-vascular region; and then determining the contrast between the vascular region in the fundus image and the fundus image itself through the above content, so as to define the clarity of the fundus image through the contrast.
[0081] That is, step S102 above includes: determining the contrast between the blood vessel region and other regions of the fundus image, and determining the clarity of the dehazed fundus image based on the contrast.
[0082] In one optional embodiment of this application, the contrast between the vascular region and other regions of the fundus image is determined by the following method:
[0083] Determine the pixel difference between the pixel values of the vascular region and the pixel values of the non-vascular region in the dehazed fundus image; determine the contrast of the dehazed fundus image based on the pixel difference;
[0084] or,
[0085] Determine the area ratio between the vascular region and the non-vascular region in the defogging fundus image; determine the contrast of the defogging fundus image based on the area ratio.
[0086] or,
[0087] The contrast of the dehazed fundus image is determined based on the face value ratio and the pixel difference.
[0088] In an optional embodiment of this application, in order to more accurately determine the sharpness of the enhanced fundus image, the method further includes the following step before performing step S102:
[0089] At least one channel of the dehazed fundus image is selected, and image enhancement processing is performed on the dehazed fundus image to obtain the image-enhanced fundus image.
[0090] In one optional embodiment of this application, considering that the image detail features of the G channel (for example, the vascular features in the fundus image) are more obvious for fundus images, in order to improve the recognition ability of the dehazed fundus image, the above step S102 specifically involves performing image enhancement processing on the G channel image in the dehazed fundus image, and using the G channel image after image enhancement processing as the fundus image.
[0091] It should be noted that the above-described method of selecting the G channel from the dehazed fundus image for image enhancement is only one optional implementation of this application. In other embodiments, any combination of one or more channels from the RGB three-channel image of the dehazed fundus image can also be used for image enhancement to obtain an enhanced fundus image. This application does not impose any limitations on this.
[0092] Step S103: Obtain the evaluation result of the fundus image based on the clarity of the dehazed fundus image.
[0093] In one optional embodiment of this application, the evaluation of the fundus image based on the clarity of the dehazed fundus image is achieved based on a preset clarity threshold. The preset clarity threshold can be set based on actual conditions; for example, the preset clarity threshold can be 0.35.
[0094] For example, when evaluating whether the fundus in the fundus image is a cataract fundus, if the clarity of the fundus image after image enhancement is greater than or equal to a preset clarity threshold, the evaluation result of the fundus image is that the fundus image is not a cataract fundus image; if the clarity of the fundus image after image enhancement is less than the preset clarity threshold, the evaluation result of the fundus image is that the fundus image is a cataract fundus image.
[0095] In one exemplary embodiment of this application, the image evaluation method can be applied to detect the presence of cataracts in the fundus based on the evaluation of fundus images.
[0096] Specifically, after obtaining the fundus image, the fundus image is first evaluated using an image preliminary evaluation model to preliminarily determine whether the fundus image belongs to a cataract patient.
[0097] Furthermore, after initially determining that the fundus image is from a cataract patient, the fundus image is further dehazed to obtain a dehazed fundus image.
[0098] Furthermore, at least one channel of the dehazed fundus image is selected for image enhancement processing to obtain an enhanced fundus image.
[0099] Furthermore, the vascular region in the enhanced fundus image is analyzed, and the clarity of the enhanced fundus image is obtained by comparing the vascular region with the non-vascular region in the fundus image.
[0100] Finally, based on the clarity of the fundus image, it was determined whether the fundus image belonged to a cataract patient.
[0101] In summary, the fundus image evaluation method, after obtaining the fundus image to be evaluated, performs dehazing processing on the fundus image to obtain a dehazed fundus image. Then, based on the clarity of the dehazed fundus image, the fundus image to be evaluated is evaluated. This scheme can effectively avoid the influence of low clarity and poor quality of fundus images, as well as the impact of fundus image acquisition hardware and acquisition techniques on fundus images, which is beneficial for the classification of lesions in fundus images and the analysis of fundus images.
[0102] Exemplary device
[0103] Accordingly, this application also provides an image evaluation device, please refer to... Figure 2 , Figure 2 This is a schematic diagram of the structure of an image evaluation device provided in another embodiment of this application.
[0104] like Figure 2 As shown, the device includes:
[0105] Unit 201 is used to dehaze the fundus image to be evaluated to obtain a dehazed fundus image;
[0106] The second unit 202 is used to analyze the vascular region in the defogging fundus image and determine the clarity of the defogging fundus image;
[0107] The third unit 203 is used to obtain the evaluation result of the fundus image based on the clarity of the defogging fundus image.
[0108] In one alternative embodiment of this application, the fundus image to be evaluated is obtained in the following manner:
[0109] The first fundus image is input into a pre-trained image preliminary evaluation model so that the image preliminary evaluation model can perform a preliminary evaluation of the first fundus image and obtain a preliminary evaluation result of the first fundus image;
[0110] If the preliminary evaluation result of the first fundus image determines that the first fundus image is a substandard image, the first fundus image shall be used as the fundus image to be evaluated.
[0111] In one optional embodiment of this application, the preliminary image evaluation model is trained in the following manner:
[0112] Obtain fundus images labeled with image evaluation results;
[0113] The fundus images labeled with the image evaluation results are used as training samples to train the preliminary image evaluation model.
[0114] In one optional embodiment of this application, the step of dehazing the fundus image to be evaluated to obtain a dehazed fundus image includes:
[0115] From the channel images separated from the fundus images to be evaluated, the channel image with the smallest pixel value is selected, and the pixel mean value information of the channel image is determined.
[0116] The channel image is subjected to mean filtering to obtain the mean-filtered channel image;
[0117] The dehazing parameters are determined based on the image after mean filtering and the image of the channel with the largest pixel value.
[0118] Based on preset pixel adjustment parameters and the pixel mean information of the channel image, pixel adjustment is performed on the channel image after mean filtering to determine the pixel-adjusted channel image;
[0119] Based on the dehazing parameters and the channel image with the smallest pixel value or the channel image after pixel adjustment, the fundus image to be evaluated is dehazed to obtain a dehazed fundus image.
[0120] In one optional embodiment of this application, before the step of dehazing the fundus image to be evaluated to obtain a dehazed fundus image, the method further includes:
[0121] The fundus image to be evaluated is denoised to obtain a denoised fundus image to be evaluated.
[0122] In one optional embodiment of this application, before the step of analyzing the vascular region in the dehazed fundus image to determine the clarity of the dehazed fundus image, the method further includes:
[0123] At least one channel of the dehazed fundus image is selected, and image enhancement processing is performed on the dehazed fundus image to obtain an enhanced fundus image.
[0124] In one optional embodiment of this application, selecting at least one channel from the dehazed fundus image and performing image enhancement processing on the dehazed fundus image to obtain an enhanced fundus image includes:
[0125] Image enhancement processing is performed on the G channel image in the dehazed image, and the G channel image after image enhancement processing is used as the enhanced fundus image.
[0126] In one optional embodiment of this application, analyzing the vascular region in the dehazed fundus image to determine the clarity of the dehazed fundus image includes:
[0127] The contrast between the vascular region and other regions of the fundus image is determined, and the sharpness of the enhanced fundus image is determined based on the contrast.
[0128] The image evaluation apparatus provided in this embodiment belongs to the same concept as the image evaluation method provided in the above embodiments of this application. It can execute the image evaluation method provided in any of the above embodiments of this application and has the corresponding functional modules and beneficial effects for executing the image evaluation method. Technical details not described in detail in this embodiment can be found in the specific processing content of the image evaluation method provided in the above embodiments of this application, and will not be repeated here.
[0129] Exemplary electronic devices
[0130] Another embodiment of this application also proposes an electronic device, please refer to Figure 3 , Figure 3 A schematic diagram of an electronic device structure provided in another embodiment of this application, such as... Figure 3 As shown, the electronic device includes:
[0131] Memory 200 and processor 210;
[0132] The memory 200 is connected to the processor 210 and is used to store programs;
[0133] The processor 210 is configured to implement the image evaluation method disclosed in any of the above embodiments by running the program stored in the memory 200.
[0134] Specifically, the aforementioned electronic device may also include: a bus, a communication interface 220, an input device 230, and an output device 240.
[0135] The processor 210, memory 200, communication interface 220, input device 230, and output device 240 are interconnected via a bus. Among them:
[0136] A bus can include a pathway for transmitting information between various components of a computer system.
[0137] The processor 210 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present invention. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.
[0138] Processor 210 may include a main processor, as well as a baseband chip, modem, etc.
[0139] The memory 200 stores a program that executes the technical solution of this invention, and may also store an operating system and other key business functions. Specifically, the program may include program code, which includes computer operation instructions. More specifically, the memory 200 may include read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), other types of dynamic storage devices capable of storing information and instructions, disk storage, flash memory, etc.
[0140] Input device 230 may include a device for receiving user input data and information, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor.
[0141] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.
[0142] The communication interface 220 may include a device that uses any transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.
[0143] The processor 210 executes the program stored in the memory 200 and calls other devices, which can be used to implement the various steps of any of the image evaluation methods provided in the above embodiments of this application.
[0144] Exemplary computer program products and storage media
[0145] In addition to the methods and apparatus described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the image evaluation methods according to various embodiments of this application as described in the "Exemplary Methods" section of this specification.
[0146] The computer program product can be written in any combination of one or more programming languages to perform the operations of the embodiments of this application. The programming languages include object-oriented programming languages such as Java and C++, as well as conventional procedural programming languages such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone 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.
[0147] Furthermore, embodiments of this application may also be storage media storing a computer program, which is executed by a processor in the image evaluation methods according to various embodiments of this application described in the "Exemplary Methods" section above, specifically implementing the following steps:
[0148] Step S101: Dehaze the fundus image to be evaluated to obtain a dehazed fundus image;
[0149] Step S102: Select at least one channel in the dehazed fundus image and perform image enhancement processing on the dehazed fundus image to obtain the image-enhanced fundus image.
[0150] Step S103: Based on the enhanced fundus image, obtain the evaluation result of the fundus image.
[0151] For the foregoing method embodiments, in order to simplify the description, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.
[0152] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For apparatus embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.
[0153] The steps in the methods of the various embodiments of this application can be adjusted, merged, or deleted in order according to actual needs, and the technical features described in each embodiment can be replaced or combined.
[0154] The modules and sub-modules in the apparatus and terminal in the various embodiments of this application can be merged, divided, and deleted according to actual needs.
[0155] It should be understood that the disclosed terminals, devices, and methods can be implemented in other ways, given the several embodiments provided in this application. For example, the terminal embodiments described above are merely illustrative. For instance, the division of modules or sub-modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple sub-modules or modules may be combined or integrated into another module, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.
[0156] The modules or submodules described as separate components may or may not be physically separate. The components that constitute a module or submodule may or may not be physical modules or submodules; that is, they may be located in one place or distributed across multiple network modules or submodules. Some or all of the modules or submodules can be selected to achieve the purpose of this embodiment's solution, depending on actual needs.
[0157] Furthermore, the functional modules or sub-modules in the various embodiments of this application can be integrated into one processing module, or each module or sub-module can exist physically separately, or two or more modules or sub-modules can be integrated into one module. The integrated modules or sub-modules described above can be implemented in hardware or in the form of software functional modules or sub-modules.
[0158] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0159] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software unit executed by a processor, or a combination of both. The software unit can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.
[0160] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0161] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. An image evaluation method, characterized in that, include: The fundus images to be evaluated are dehazed to obtain dehazed fundus images; The process of dehazing the fundus image to be evaluated to obtain a dehazed fundus image includes: selecting the channel image with the smallest pixel value from the channel images separated from the fundus image to be evaluated, and determining the pixel mean information of the channel image; performing mean filtering on the channel image to obtain a mean-filtered channel image; determining dehazing parameters based on the mean-filtered image and the channel image with the largest pixel value; adjusting the pixel values of the mean-filtered channel image based on preset pixel adjustment parameters and the pixel mean information of the channel images to determine a pixel-adjusted channel image; and performing dehazing on the fundus image to be evaluated based on the dehazing parameters and either the channel image with the smallest pixel value or the pixel-adjusted channel image to obtain a dehazed fundus image. Analyzing the vascular region in the dehazed fundus image to determine the clarity of the dehazed fundus image; wherein analyzing the vascular region in the dehazed fundus image to determine the clarity of the dehazed fundus image includes: determining the contrast between the vascular region and other regions of the fundus image, and determining the clarity of the dehazed fundus image based on the contrast. The evaluation result of the fundus image is obtained based on the clarity of the defogging fundus image.
2. The method according to claim 1, characterized in that, The fundus images to be evaluated were obtained in the following manner: The first fundus image is input into a pre-trained image preliminary evaluation model so that the image preliminary evaluation model can perform a preliminary evaluation of the first fundus image and obtain a preliminary evaluation result of the first fundus image. If the preliminary evaluation result of the first fundus image determines that the first fundus image is a substandard image, the first fundus image shall be used as the fundus image to be evaluated.
3. The method according to claim 2, characterized in that, The preliminary image evaluation model was trained in the following manner: Obtain fundus images labeled with image evaluation results; The fundus images labeled with the image evaluation results are used as training samples to train the preliminary image evaluation model.
4. The method according to claim 1, characterized in that, Before the step of dehazing the fundus image to be evaluated to obtain the dehazed fundus image, the method further includes: The fundus image to be evaluated is denoised to obtain a denoised fundus image to be evaluated.
5. The method according to claim 1, characterized in that, Before the step of analyzing the vascular region in the dehazed fundus image to determine the clarity of the dehazed fundus image, the method further includes: At least one channel of the dehazed fundus image is selected, and image enhancement processing is performed on the dehazed fundus image to obtain an enhanced fundus image.
6. An image evaluation device, characterized in that, include: The first unit is used to dehaze the fundus images to be evaluated, and obtain dehazed fundus images; The process of dehazing the fundus image to be evaluated to obtain a dehazed fundus image includes: selecting the channel image with the smallest pixel value from the channel images separated from the fundus image to be evaluated, and determining the pixel mean information of the channel image; performing mean filtering on the channel image to obtain a mean-filtered channel image; determining dehazing parameters based on the mean-filtered image and the channel image with the largest pixel value; adjusting the pixel values of the mean-filtered channel image based on preset pixel adjustment parameters and the pixel mean information of the channel images to determine a pixel-adjusted channel image; and performing dehazing on the fundus image to be evaluated based on the dehazing parameters and either the channel image with the smallest pixel value or the pixel-adjusted channel image to obtain a dehazed fundus image. The second unit is used to analyze the vascular region in the defogging fundus image and determine the clarity of the defogging fundus image; wherein analyzing the vascular region in the defogging fundus image and determining the clarity of the defogging fundus image includes: determining the contrast between the vascular region and other regions of the fundus image, and determining the clarity of the defogging fundus image based on the contrast. The third unit is used to obtain the evaluation result of the fundus image based on the clarity of the defogging fundus image.
7. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the image evaluation method according to any one of claims 1-5 by running instructions in the memory.
8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, performs the image evaluation method according to any one of claims 1-5.