Image denoising method and device, equipment and storage medium
Through the image denoising method based on the relationship model between brightness and denoising intensity, the denoising intensity data of each pixel is obtained, a denoising intensity matrix is formed, and the image is denoised, which solves the problem of uneven denoising in the existing technology. problem, achieving accurate denoising of images.
Patent Information
- Application Number
- CN202411357809.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-27
- Publication Date
- 2025-01-21
AI Technical Summary
When processing images, existing image denoising methods are difficult to effectively distinguish high-frequency and low-frequency areas, resulting in too strong or too weak denoising intensity, and failing to effectively remove noise or retain details.
Based on the pixel matrix of the image to be processed, based on the brightness and noise strength relationship model, the de -noise strength data of each pixel point is obtained to form a noise strength matrix, and the matrix is used to make noise treatment of the image.
The accurate noise of the image is achieved, and the problem of insufficient details caused by excessive or too weak due to excessive noise strength or too weak noise.
Smart Images
Figure CN119338712A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of data processing, and in particular to an image denoising method, device, equipment and storage medium. Background Art
[0002] At present, in order to improve the quality of images, images are usually denoised to reduce or eliminate noise in the images. Common image denoising methods may include, for example, denoising methods based on image frequency, etc., wherein the frequency of the image can be used to reflect the variation of the pixel grayscale of the image in space. Specifically, low-frequency components usually represent smooth areas of the image, such as the background area, while high-frequency components represent the details or edge parts of the image.
[0003] When denoising an image, since there may be high, medium and low areas in the image at the same time, if the position of image denoising is determined only by image frequency, there may be problems such as insufficient details in the low-frequency area due to excessive high-mid-frequency denoising intensity, or the high-frequency noise cannot be removed due to too weak high-mid-frequency denoising intensity. Summary of the invention
[0004] In order to solve the above technical problems, the embodiments of the present disclosure provide an image denoising method, apparatus, device and storage medium.
[0005] In a first aspect, the present disclosure provides an image denoising method, the method comprising:
[0006] Acquire a pixel matrix of an image to be processed; wherein the pixel matrix includes brightness values of pixel points in the image to be processed;
[0007] Based on a brightness and denoising intensity relationship model, obtaining denoising intensity data corresponding to a first pixel point in the pixel matrix; wherein the relationship model predefines a corresponding relationship between pixel brightness values and denoising intensity data;
[0008] Determine a denoising intensity matrix corresponding to the image to be processed based on the denoising intensity data of the first pixel point; wherein the denoising intensity matrix includes the denoising intensity data of the pixel points in the image to be processed;
[0009] The image to be processed is denoised using the denoising intensity matrix to obtain a denoised image corresponding to the image to be processed.
[0010] In an optional implementation, the acquiring, based on a brightness and denoising intensity relationship model, denoising intensity data corresponding to a first pixel in the pixel matrix includes:
[0011] Based on the brightness and denoising intensity relationship model, a denoising intensity range corresponding to a first pixel point in the pixel matrix is obtained, and a target value in the denoising intensity range is determined as denoising intensity data corresponding to the first pixel point.
[0012] In an optional implementation manner, the method further includes:
[0013] receiving an adjustment operation for the denoising intensity data of the first pixel point, and obtaining adjusted denoising intensity data corresponding to the first pixel point;
[0014] Correspondingly, determining the denoising intensity matrix corresponding to the image to be processed based on the denoising intensity data of the first pixel point includes:
[0015] Based on the denoising intensity data of the first pixel or the adjusted denoising intensity data corresponding to the first pixel, a denoising intensity matrix corresponding to the image to be processed is determined.
[0016] In an optional implementation manner, the method further includes:
[0017] Acquire a training sample image; wherein the training sample image includes a noise image and a denoised image, and pixels in the noise image have different brightness values;
[0018] The machine learning model is trained using the training sample images to obtain the brightness and denoising intensity relationship model.
[0019] In an optional implementation, the denoising intensity data is directly proportional to the pixel brightness value.
[0020] In a second aspect, the present disclosure provides an image denoising device, the device comprising:
[0021] A first acquisition module is used to acquire a pixel matrix of an image to be processed; wherein the pixel matrix includes brightness values of pixels in the image to be processed;
[0022] A second acquisition module is used to acquire denoising intensity data corresponding to a first pixel point in the pixel matrix based on a brightness and denoising intensity relationship model; wherein the relationship between pixel brightness value and denoising intensity data is predefined in the relationship model;
[0023] A determination module, configured to determine a denoising intensity matrix corresponding to the image to be processed based on the denoising intensity data of the first pixel point; wherein the denoising intensity matrix includes the denoising intensity data of the pixel points in the image to be processed;
[0024] The denoising module is used to perform denoising on the image to be processed by using the denoising intensity matrix to obtain a denoised image corresponding to the image to be processed.
[0025] In a third aspect, the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device implements the above method.
[0026] In a fourth aspect, the present disclosure provides an image denoising device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above method when executing the computer program.
[0027] In a fifth aspect, the present disclosure provides a computer program product, wherein the computer program product comprises a computer program / instructions, and the computer program / instructions implement the above method when executed by a processor.
[0028] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has at least the following advantages:
[0029] The disclosed embodiments provide an image denoising method, apparatus, device and storage medium, the method comprising: obtaining a pixel matrix of an image to be processed, the pixel matrix including brightness values of pixels in the image to be processed; obtaining denoising intensity data corresponding to a first pixel in the pixel matrix based on a brightness and denoising intensity relationship module; determining a denoising intensity matrix corresponding to the image to be processed based on the denoising intensity data of the first pixel; and denoising the image to be processed using the denoising intensity matrix to obtain a denoised image corresponding to the image to be processed. It can be seen that the disclosed embodiments can determine corresponding denoising intensity data for each pixel in the image according to the corresponding relationship between the brightness value and the denoising intensity data, and denoise the pixel using the denoising intensity data corresponding to each pixel, thereby achieving accurate denoising of the image, avoiding the problem of insufficient details in the low-frequency area due to excessively strong high-frequency denoising intensity, or the problem of inability to remove high-frequency noise due to too weak high-frequency denoising intensity. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0032] Figure 1 A flowchart of an image denoising method provided by an embodiment of the present disclosure;
[0033] Figure 2 A schematic diagram of a correspondence between a pixel brightness value and a denoising intensity range provided in an embodiment of the present disclosure;
[0034] Figure 3 A schematic diagram of an image denoising scenario provided by an embodiment of the present disclosure;
[0035] Figure 4 A schematic diagram of the structure of an image denoising device provided by an embodiment of the present disclosure;
[0036] Figure 5 A schematic diagram of the structure of an image denoising device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION
[0037] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.
[0038] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.
[0039] In order to improve the quality of images, images are usually denoised to reduce or eliminate noise in the images. Common image denoising methods may include, for example, denoising methods based on image frequency, wherein the frequency of the image can be used to reflect the variation of the pixel grayscale of the image in space. Specifically, low-frequency components usually represent smooth areas of the image, such as the background area, while high-frequency components represent the details or edge parts of the image.
[0040] Currently, when denoising an image, since the image may contain high, medium and low areas at the same time, when the image denoising position is determined only by the image frequency, there may be problems such as insufficient details in the low-frequency area due to excessive high-mid-frequency denoising intensity, or the high-frequency noise cannot be removed due to too weak high-mid-frequency denoising intensity.
[0041] To this end, the disclosed embodiment provides an image denoising method, specifically, obtaining a pixel matrix of an image to be processed, the pixel matrix including the brightness values of the pixels in the image to be processed; obtaining denoising intensity data corresponding to the first pixel in the pixel matrix based on a brightness and denoising intensity relationship module; determining a denoising intensity matrix corresponding to the image to be processed based on the denoising intensity data of the first pixel; and denoising the image to be processed using the denoising intensity matrix to obtain a denoised image corresponding to the image to be processed. It can be seen that the disclosed embodiment can determine the corresponding denoising intensity data for each pixel in the image according to the corresponding relationship between the brightness value and the denoising intensity data, and denoise the image using the denoising intensity data corresponding to each pixel, thereby achieving accurate denoising of the image, avoiding the problem of insufficient details in the low-frequency area due to excessively strong high-frequency denoising intensity, or the problem of inability to remove high-frequency noise due to too weak high-frequency denoising intensity.
[0042] Based on this, the present disclosure provides an image denoising method, referring to Figure 1 , is a flow chart of an image denoising method provided by an embodiment of the present disclosure, the method specifically comprising:
[0043] S101: Acquire a pixel matrix of an image to be processed; wherein the pixel matrix includes brightness values of pixel points in the image to be processed.
[0044] The image denoising method provided by the embodiments of the present disclosure can be applied to a client, for example, the client may include a client deployed on a smart phone, a client deployed on a tablet computer, etc., and can also be applied to a server, which is used to perform denoising and other operations on images uploaded by the client.
[0045] In the disclosed embodiment, the image to be processed may be any digital image that needs to be denoised, and the image to be processed may include multiple pixels. A pixel is the smallest unit that constitutes the image to be processed, and each pixel on the image to be processed contains specific information such as brightness and chromaticity values. The clarity and quality of the image mainly depend on the number and quality of pixels. A high-pixel image can usually present more details and more finely depict objects and scenes in the image.
[0046] In practical applications, the pixel matrix can be used to represent the coordinate information of each pixel in the image to be processed and the brightness value corresponding to each pixel. For example, for an m×n pixel matrix, where m and n represent the height and width of the image to be processed, respectively, (x, y) in the pixel matrix represents the coordinate data of a pixel, and the brightness value corresponding to the pixel can be represented by f(x, y).
[0047] In an optional implementation, the brightness value of each pixel in the image to be processed can be obtained using image processing software or tools, or the brightness value of each pixel can be obtained using an image processing library in a programming language, or the brightness value of each pixel can be obtained by reading metadata information of the image. Further, the pixel matrix of the image to be processed is determined based on the brightness value of each pixel, wherein the pixel matrix includes the brightness value of each pixel.
[0048] S102: Based on a brightness and denoising intensity relationship model, obtaining denoising intensity data corresponding to a first pixel point in the pixel matrix.
[0049] The relationship model predefines a corresponding relationship between pixel brightness values and denoising intensity data.
[0050] In practical applications, the brightness value of pixels will affect the visibility of noise. For example, in the same image, since the pixel brightness value in the darker area is lower, the noise in the area may not be obvious; while in the brighter area, since the pixel brightness value in the brighter area is higher, the noise in the area may be more obvious.
[0051] Based on this, after obtaining the pixel matrix of the image to be processed, the embodiment of the present disclosure can obtain the denoising intensity data corresponding to the first pixel point in the pixel matrix based on the brightness and denoising intensity relationship model. The first pixel point can be any pixel point in the pixel matrix of the image to be processed.
[0052] In the embodiment of the present disclosure, the corresponding relationship between the pixel brightness value and the denoising intensity data may be predefined in the brightness and denoising intensity relationship model. After determining the brightness of the first pixel, the denoising intensity data corresponding to the first pixel may be determined based on the corresponding relationship between the brightness value of the pixel and the denoising intensity data.
[0053] In practical applications, if the brightness value of a pixel is higher, it means that the noise of the pixel is more obvious or the impact of the noise is greater, and accordingly, the denoising intensity data for the pixel is also higher; if the brightness value of a pixel is lower, it means that the noise of the pixel is not too obvious or the impact of the noise on the pixel is small, and accordingly, the denoising intensity data for the pixel can be smaller.
[0054] In an optional implementation, a correspondence between the brightness value of a pixel and the denoising intensity data can be established in advance according to a method of mapping brightness values by a normalization factor, wherein the normalization factor, also known as the denoising intensity value, is a value used to normalize the data. As the brightness value of the pixel increases, the noise becomes more and more obvious, and the denoising intensity data represented by the corresponding normalization factor also increases.
[0055] In another optional implementation, after obtaining the pixel matrix of the image to be processed, the denoising intensity range corresponding to the first pixel point in the pixel matrix can be obtained based on the correspondence between the pixel brightness value and the denoising intensity range, and the target value in the denoising intensity range is determined as the denoising intensity data corresponding to the first pixel point. The target value may include values such as the median value and the mean value of the denoising intensity range.
[0056] like Figure 2 As shown, it is a schematic diagram of the correspondence between a pixel brightness value and a denoising intensity range provided by an embodiment of the present disclosure. The brightness value range is 0-256, and each brightness value corresponds to a denoising intensity range. As the brightness value increases, the corresponding denoising intensity range also increases.
[0057] For example, assuming that the brightness value of pixel A in the pixel matrix is 41, based on the above correspondence, it can be determined that the denoising intensity range corresponding to pixel A is 1-104. At this time, the middle value 52 of the denoising intensity range 1-104 can be determined as the denoising intensity data corresponding to the first pixel A (also called denoising intensity value).
[0058] In the disclosed embodiment, the denoising intensity data can be used to characterize the strength of the preset denoising algorithm in removing the noise of the target pixel point, wherein the preset denoising algorithm may include a mean filter algorithm, a median filter algorithm, a Gaussian filter algorithm, a bilateral filter algorithm, etc. It can be seen that the disclosed embodiment determines the middle value of the denoising intensity range corresponding to the brightness value of each pixel point as the denoising intensity value corresponding to the pixel point, so as to subsequently use the denoising intensity value to perform accurate denoising on each pixel point in the image to be processed.
[0059] S103: Determine a denoising intensity matrix corresponding to the image to be processed based on the denoising intensity data of the first pixel point.
[0060] The denoising intensity matrix includes denoising intensity data of pixels in the image to be processed.
[0061] In the disclosed embodiment, after obtaining the denoising intensity data corresponding to each pixel point in the pixel matrix of the image to be processed based on the brightness and denoising relationship model, the denoising intensity matrix corresponding to the image to be processed is determined based on the denoising intensity data corresponding to each pixel point. The denoising intensity matrix includes the denoising intensity data corresponding to each pixel point.
[0062] S104: performing denoising processing on the image to be processed by using the denoising intensity matrix to obtain a denoised image corresponding to the image to be processed.
[0063] In the disclosed embodiment, after determining the denoising intensity matrix corresponding to the image to be processed, the image to be processed is denoised using the denoising intensity matrix to obtain a denoised image corresponding to the image to be processed.
[0064] In an optional embodiment, since the denoising intensity data of the first pixel point can be used to characterize the denoising intensity of the first pixel point by a preset denoising algorithm, after obtaining a denoising intensity matrix containing the denoising intensity data corresponding to each pixel point, the denoising intensity represented by the denoising intensity data can be used to perform denoising on the image to be processed to obtain a denoised image corresponding to the image to be processed.
[0065] In an optional embodiment, after obtaining the denoising intensity data corresponding to the first pixel point in the pixel matrix based on the brightness and denoising intensity relationship model, it is also possible to receive the user's adjustment operation on the denoising intensity data of the first pixel point to obtain the adjusted denoising intensity data, and further, determine the denoising intensity matrix corresponding to the image to be processed based on the adjusted denoising intensity data.
[0066] In the disclosed embodiment, the adjustment operation on the denoising intensity data may include an intensity increase operation on the denoising intensity data or an intensity decrease operation on the denoising intensity data, etc. The user may customize the denoising intensity data through the adjustment operation on the denoising intensity data.
[0067] It can be seen that the embodiments of the present disclosure are capable of receiving an adjustment operation on denoising intensity data, and achieving accurate denoising of an image based on the adjusted denoising intensity data.
[0068] In another optional implementation, after obtaining the denoising intensity data corresponding to the first pixel point in the pixel matrix, when a brightness value adjustment operation for the first pixel point input by the user is received, the adjusted brightness value can be obtained, and based on the correspondence between the pixel brightness value and the denoising intensity data, the adjusted denoising intensity data corresponding to the adjusted brightness value can be determined, and further, the first pixel point can be denoised based on the adjusted denoising intensity data.
[0069] In the image denoising method provided by the embodiment of the present disclosure, a pixel matrix of the image to be processed is obtained, and the matrix includes the brightness values of the pixels in the image to be processed; based on the brightness and denoising intensity relationship module, denoising intensity data corresponding to the first pixel in the pixel matrix is obtained; based on the denoising intensity data of the first pixel, a denoising intensity matrix corresponding to the image to be processed is determined; and the image to be processed is denoised using the denoising intensity matrix to obtain a denoised image corresponding to the image to be processed. It can be seen that the embodiment of the present disclosure can determine the corresponding denoising intensity data for each pixel in the image according to the corresponding relationship between the brightness value and the denoising intensity data, and denoise the image using the denoising intensity data corresponding to each pixel, thereby achieving accurate denoising and avoiding the problem of insufficient details in the low-frequency area due to excessively strong high-frequency denoising intensity, or the problem of inability to remove high-frequency noise due to too weak high-frequency denoising intensity.
[0070] In practical applications, before obtaining the denoising intensity data corresponding to the first pixel point in the pixel matrix based on the brightness and denoising intensity relationship model, the brightness and denoising intensity relationship model can also be obtained by machine learning training.
[0071] Specifically, firstly, a training sample image is obtained, wherein the training sample image includes a noise image and a denoised image, and the pixels in the noise image have different brightness values; then, the training sample image is used to train a machine learning model to obtain a brightness and denoising intensity relationship model.
[0072] The brightness and denoising intensity model is used to output denoising intensity data corresponding to the first pixel based on the brightness value of the first pixel.
[0073] In an embodiment of the present disclosure, after obtaining a training sample image containing a noisy image and a denoised image, the noisy image and the denoised image are used as inputs to a machine learning model, and the machine learning model is used to learn the relationship between the pixel brightness value in the noisy image and the denoising intensity data of the denoised image to obtain a brightness and denoising intensity relationship model.
[0074] like Figure 3 , which is a schematic diagram of an image denoising scenario provided by an embodiment of the present disclosure, is specifically introduced by taking an image processing server and a client as examples.
[0075] After receiving the image to be processed uploaded by the client, the image processing server first obtains the brightness value of each pixel in the image to be processed, and then determines the denoising intensity range corresponding to each pixel based on the brightness and denoising intensity relationship model, and determines the middle value in the denoising intensity range as the corresponding denoising intensity data.
[0076] After determining the denoising intensity data corresponding to each pixel in the image to be processed, the image processing server performs denoising on each pixel based on the denoising intensity data of each pixel to obtain a denoised image, and sends the denoised image and the denoising intensity data of each pixel to the client.
[0077] After receiving the denoised image and the denoised intensity data of each pixel, the client displays the denoised image. When receiving the user's adjustment operation for the denoised intensity data of the first pixel, the client can upload the adjustment operation for the denoised intensity data of the first pixel to the image processing server.
[0078] When the image processing server receives an adjustment operation on the denoising intensity data of the first pixel, it first obtains the adjusted denoising intensity data corresponding to the first pixel; then, based on the adjusted denoising intensity data, it updates the denoising intensity matrix corresponding to the image to be processed to obtain an updated denoising intensity matrix; then, it uses the updated denoising intensity matrix to perform denoising on the image to be processed to obtain an adjusted denoising image corresponding to the image to be processed.
[0079] The image processing server performs denoising on the image to be processed based on the adjusted denoising intensity data, and after obtaining the adjusted denoised image corresponding to the image to be processed, sends the adjusted denoised image to the client, which displays it to the user.
[0080] It can be seen that the embodiment of the present disclosure sends the denoising intensity data of each pixel in the image to be processed to the client, thereby facilitating the user to adjust the denoising intensity data to obtain a denoised image that better meets the user's needs.
[0081] Based on the above method embodiment, the present disclosure also provides an image denoising device, referring to Figure 4 , is a schematic diagram of the structure of an image denoising device provided by an embodiment of the present disclosure, the device comprising:
[0082] A first acquisition module 401 is used to acquire a pixel matrix of an image to be processed; wherein the pixel matrix includes brightness values of pixels in the image to be processed;
[0083] A second acquisition module 402 is used to acquire denoising intensity data corresponding to a first pixel point in the pixel matrix based on a brightness and denoising intensity relationship model; wherein the relationship between pixel brightness value and denoising intensity data is predefined in the relationship model;
[0084] A determination module 403 is used to determine a denoising intensity matrix corresponding to the image to be processed based on the denoising intensity data of the first pixel point; wherein the denoising intensity matrix includes the denoising intensity data of the pixel points in the image to be processed;
[0085] The first denoising module 404 is configured to perform denoising on the image to be processed by using the denoising intensity matrix to obtain a denoised image corresponding to the image to be processed.
[0086] In an optional implementation manner, the second acquisition module includes:
[0087] The acquisition submodule is used to acquire the denoising intensity range corresponding to the first pixel point in the pixel matrix based on the brightness and denoising intensity relationship model, and determine the target value in the denoising intensity range as the denoising intensity data corresponding to the first pixel point.
[0088] In an optional implementation, the device further includes:
[0089] A receiving module, configured to receive an adjustment operation on the denoising intensity data of the first pixel point, and obtain the adjusted denoising intensity data corresponding to the first pixel point;
[0090] An updating module, configured to update a denoising intensity matrix corresponding to the image to be processed based on the adjusted denoising intensity data corresponding to the first pixel point, to obtain an updated denoising intensity matrix;
[0091] The second denoising module is used to perform denoising on the image to be processed by using the updated denoising intensity matrix to obtain an adjusted denoised image corresponding to the image to be processed.
[0092] In an optional implementation, the device further includes:
[0093] A third acquisition module is used to acquire a training sample image; wherein the training sample image includes a noise image and a denoised image, and the pixels in the noise image have different brightness values;
[0094] A training module is used to train the machine learning model using the training sample image to obtain the brightness and denoising intensity relationship model; wherein the brightness and denoising intensity model is used to output the denoising intensity data corresponding to the first pixel point based on the brightness value of the first pixel point.
[0095] In an optional implementation, the denoising intensity data is directly proportional to the pixel brightness value.
[0096] In the image denoising method provided by the embodiment of the present disclosure, a pixel matrix of the image to be processed is obtained, and the matrix includes the brightness values of the pixels in the image to be processed; based on the brightness and denoising intensity relationship module, denoising intensity data corresponding to the first pixel in the pixel matrix is obtained; based on the denoising intensity data of the first pixel, a denoising intensity matrix corresponding to the image to be processed is determined; and the image to be processed is denoised using the denoising intensity matrix to obtain a denoised image corresponding to the image to be processed. It can be seen that the embodiment of the present disclosure can determine the corresponding denoising intensity data for each pixel in the image according to the corresponding relationship between the brightness value and the denoising intensity data, and denoise the image using the denoising intensity data corresponding to each pixel, thereby achieving accurate denoising and avoiding the problem of insufficient details in the low-frequency area due to excessively strong high-frequency denoising intensity, or the problem of inability to remove high-frequency noise due to too weak high-frequency denoising intensity.
[0097] In addition to the above-mentioned method and apparatus, the embodiments of the present disclosure further provide a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal device, the terminal device implements the image denoising method described in the embodiments of the present disclosure.
[0098] The embodiment of the present disclosure further provides a computer program product, which includes a computer program / instructions. When the computer program / instructions are executed by a processor, the image denoising method described in the embodiment of the present disclosure is implemented.
[0099] In addition, the present disclosure also provides an image denoising device, see Figure 5 As shown, this may include:
[0100] Processor 501, memory 502, input device 503 and output device 504. The number of processors 501 in the image denoising device can be one or more. Figure 5 In some embodiments of the present disclosure, the processor 501, the memory 502, the input device 503 and the output device 504 may be connected via a bus or other means, wherein: Figure 5 The example of connecting through bus is taken in the following.
[0101] The memory 502 can be used to store software programs and modules. The processor 501 executes various functional applications and data processing of the image denoising device by running the software programs and modules stored in the memory 502. The memory 502 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc. In addition, the memory 502 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. The input device 503 may be used to receive input digital or character information, and to generate signal input related to user settings and function control of the image denoising device.
[0102] Specifically in this embodiment, the processor 501 will load the executable files corresponding to the processes of one or more applications into the memory 502 according to the following instructions, and the processor 501 will run the applications stored in the memory 502, so as to realize various functions of the above-mentioned image denoising device.
[0103] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0104] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be 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 the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. An image denoising method, characterized in that: The method comprises: Acquire a pixel matrix of an image to be processed; wherein the pixel matrix includes brightness values of pixel points in the image to be processed; Based on a brightness and denoising intensity relationship model, obtaining denoising intensity data corresponding to a first pixel point in the pixel matrix; wherein the relationship model predefines a corresponding relationship between pixel brightness values and denoising intensity data; Determine a denoising intensity matrix corresponding to the image to be processed based on the denoising intensity data of the first pixel point; wherein the denoising intensity matrix includes the denoising intensity data of the pixel points in the image to be processed; The image to be processed is denoised using the denoising intensity matrix to obtain a denoised image corresponding to the image to be processed.
2. The method according to claim 1, characterized in that The acquiring denoising intensity data corresponding to the first pixel point in the pixel matrix based on the brightness and denoising intensity relationship model includes: Based on the correspondence between the pixel brightness value and the denoising intensity range, the denoising intensity range corresponding to the first pixel point in the pixel matrix is obtained, and the target value in the denoising intensity range is determined as the denoising intensity data corresponding to the first pixel point.
3. The method according to claim 1, characterized in that The method further comprises: receiving an adjustment operation for the denoising intensity data of the first pixel point, and obtaining the adjusted denoising intensity data corresponding to the first pixel point; Based on the adjusted denoising intensity data corresponding to the first pixel point, the denoising intensity matrix corresponding to the image to be processed is updated to obtain an updated denoising intensity matrix; The image to be processed is denoised using the updated denoising intensity matrix to obtain an adjusted denoised image corresponding to the image to be processed.
4. The method according to claim 1, characterized in that: The method further comprises: Acquire a training sample image; wherein the training sample image includes a noise image and a denoised image, and pixels in the noise image have different brightness values; The machine learning model is trained using the training sample images to obtain the brightness and denoising intensity relationship model; wherein the brightness and denoising intensity model is used to output denoising intensity data corresponding to the first pixel point based on the brightness value of the first pixel point.
5. The method according to claim 1, characterized in that The denoising intensity data is directly proportional to the pixel brightness value.
6. An image denoising device, characterized in that: The device comprises: A first acquisition module is used to acquire a pixel matrix of an image to be processed; wherein the pixel matrix includes brightness values of pixels in the image to be processed; A second acquisition module is used to acquire denoising intensity data corresponding to a first pixel point in the pixel matrix based on a brightness and denoising intensity relationship model; wherein the relationship between pixel brightness value and denoising intensity data is predefined in the relationship model; A determination module, configured to determine a denoising intensity matrix corresponding to the image to be processed based on the denoising intensity data of the first pixel point; wherein the denoising intensity matrix includes the denoising intensity data of the pixel points in the image to be processed; The first denoising module is used to perform denoising on the image to be processed by using the denoising intensity matrix to obtain a denoised image corresponding to the image to be processed.
7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device implements the method according to any one of claims 1 to 5.
8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.
9. A computer program product, characterized in that The computer program product comprises a computer program / instruction, and when the computer program / instruction is executed by a processor, the method according to any one of claims 1 to 5 is implemented.