Image noise reduction method and device, equipment and storage medium

By decomposing the image and multiple preset noise reduction processing, combined with algorithms such as mean filtering, the problem of insufficient clarity caused by size processing is solved, and higher image clarity and visual quality are achieved.

CN118918032APending Publication Date: 2024-11-08SHANGHAI WINGTECH INFORMATION TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411193819.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

In the prior art, in image denoising processing, the size processing leads to insufficient clarity. Images of different sizes will treat details as noise after synthesis.

Method used

By acquiring the target image, decomposing it into multiple images of different sizes to be processed, and at least two preset noise reduction processes are performed according to the noise reduction intensity of each image. Algorithms such as mean filtering and median filtering are used to process and adjust layer by layer Noise reduction intensity, fuse images of different sizes to improve clarity.

Benefits of technology

It effectively improves the clarity of the image after denoising, avoids the loss of details caused by excessive noise reduction, and ensures the visual quality and overall clarity of the image.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118918032A_ABST
    Figure CN118918032A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses an image noise reduction method and device, equipment and a storage medium, and the method comprises the steps: obtaining a target image, carrying out the processing of the target image, obtaining a plurality of to-be-processed images with different sizes, and carrying out the noise reduction of each to-be-processed image according to the noise reduction intensity needed by each to-be-processed image in the plurality of to-be-processed images, and the plurality of to-be-processed images. According to the image denoising method and device, at least two times of preset denoising processing are carried out according to the preset denoising intensity, the target image after denoising processing is obtained, the needed denoising intensity is the denoising intensity of the corresponding image when the preset denoising processing is carried out, and the image can be processed step by step, so that the definition of the image after denoising processing is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to image noise reduction technology, and relate to but are not limited to an image noise reduction method and apparatus, device, and storage medium. Background Art

[0002] In the prior art, when denoising an image, it is achieved through channel spatial noise filtering, by dividing the image into multiple sizes and processing them separately, denoising the brightness and chromaticity of each size, and then synthesizing the image. However, in the prior art, the processing of noise can only be debugged for a single size, and the problem still exists when multiple sizes are synthesized. When processing by size, details of different sizes are often treated as noise, resulting in insufficient clarity.

[0003] Therefore, how to improve the clarity of images after denoising is an urgent problem to be solved. Summary of the invention

[0004] In view of this, an image denoising method, apparatus, device, and storage medium provided in an embodiment of the present application can improve the clarity of an image after denoising. An image denoising method, apparatus, device, and storage medium provided in an embodiment of the present application is implemented as follows:

[0005] An image noise reduction method provided in an embodiment of the present application includes:

[0006] Get the target image;

[0007] Processing the target image to obtain a plurality of images to be processed of different sizes;

[0008] According to the noise reduction intensity required for each of the multiple images to be processed and the multiple images to be processed, at least two preset noise reduction processes are performed to obtain a target image after the noise reduction process, wherein the required noise reduction intensity is the noise reduction intensity of the corresponding image when the preset noise reduction process is performed.

[0009] In some embodiments, performing at least two preset noise reduction processes according to the noise reduction intensity required for each of the multiple images to be processed and the multiple images to be processed to obtain a target image after noise reduction process includes:

[0010] According to the noise reduction intensity required for each of the multiple images to be processed and the average of the noise reduction intensity required for each group of images to be processed, the preset noise reduction processing is performed on the multiple images to be processed, each group of images to be processed includes at least two images to be processed among the multiple images to be processed, to obtain the target image after the noise reduction processing.

[0011] In some embodiments, performing a preset noise reduction process on the multiple images to be processed according to the noise reduction intensity required for each image to be processed in the multiple images to be processed and the average value of the noise reduction intensity required for each group of images to be processed to obtain a target image after the noise reduction process includes:

[0012] Performing the preset noise reduction processing on each of the to-be-processed images according to the corresponding required noise reduction intensity to obtain a plurality of first noise-reduced sub-images;

[0013] According to the average value of the noise reduction strength required for each group of images to be processed, the preset noise reduction process is performed on the first noise reduction sub-images corresponding to each group of images to be processed to obtain a plurality of second noise reduction sub-images, wherein the first noise reduction sub-image is a first noise reduction sub-image corresponding to the image to be processed with a smaller size among the at least two first noise reduction sub-images corresponding to each group of images to be processed;

[0014] The plurality of second denoised sub-images are fused to obtain the denoised target image.

[0015] In some embodiments, each group of images to be processed includes a first image to be processed and a second image to be processed of different sizes, and the sizes of the images to be processed in different groups of images to be processed are all different.

[0016] In some embodiments, performing at least two preset noise reduction processes according to the noise reduction intensity required for each of the multiple images to be processed and the multiple images to be processed to obtain a target image after noise reduction process includes:

[0017] Performing the preset noise reduction process on each of the to-be-processed images to obtain a plurality of first noise-reduced sub-images;

[0018] Determine a first average noise reduction strength of a noise reduction strength corresponding to a first image to be processed and a noise reduction strength corresponding to a second image to be processed, wherein the first image to be processed is the image to be processed with the largest size and the second image to be processed is the image to be processed with the second largest size;

[0019] Performing denoising processing on a first denoised sub-image corresponding to the second image to be processed according to the first average denoising intensity to obtain a processed first denoised fused image;

[0020] Determine a second average noise reduction intensity of the noise reduction intensity of the processed first noise reduction fused image and the noise reduction intensity of a third image to be processed, wherein the third image to be processed is an image to be processed that is located after the second image to be processed after being sorted in descending order of size;

[0021] Processing the third image to be processed according to the second average noise reduction intensity to obtain a processed second noise reduction fused image;

[0022] When the fourth image to be processed is the image to be processed with the smallest size, a target image after noise reduction processing is obtained.

[0023] In some embodiments, the step of performing noise reduction processing on the multiple images to be processed of different sizes in sequence according to the sizes of the multiple images to be processed to obtain a target image after noise reduction processing includes:

[0024] The plurality of images to be processed are respectively subjected to chromaticity noise reduction processing and luminance noise reduction processing.

[0025] In some embodiments, the sizes of the multiple images to be processed of different sizes are reduced exponentially.

[0026] An image noise reduction device provided in an embodiment of the present application includes:

[0027] An acquisition module, used for acquiring a target image;

[0028] A processing module, used for processing the target image to obtain a plurality of images to be processed of different sizes;

[0029] The processing module is also used to perform at least two preset noise reduction processes according to the noise reduction intensity required for each of the multiple images to be processed and the multiple images to be processed, so as to obtain a target image after the noise reduction process, wherein the required noise reduction intensity is the noise reduction intensity of the corresponding image when the preset noise reduction process is performed.

[0030] The computer device provided in the embodiment of the present application includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the program, the method described in the embodiment of the present application is implemented.

[0031] The computer-readable storage medium provided in the embodiment of the present application stores a computer program thereon, and when the computer program is executed by a processor, the method provided in the embodiment of the present application is implemented.

[0032] The present application provides an image denoising method, device, computer equipment and computer-readable storage medium, which obtains a target image, processes the target image, obtains multiple images of different sizes to be processed, performs at least two preset denoising processes on the multiple images to be processed according to the denoising intensity required for each image to be processed, and obtains the target image after denoising, and the required denoising intensity is the denoising intensity of the corresponding image when the preset denoising is performed. In this way, the clarity of the image after denoising is improved, and the technical problems raised in the background technology are solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.

[0034] Figure 1 This is an application scenario diagram of an image noise reduction method disclosed in an embodiment of the present application;

[0035] Figure 2 It is a schematic diagram of an implementation process of an image noise reduction method disclosed in an embodiment of the present application;

[0036] Figure 3 It is a schematic diagram of the implementation process of another image noise reduction method disclosed in an embodiment of the present application;

[0037] Figure 4 It is a schematic diagram of the implementation process of another image noise reduction method disclosed in an embodiment of the present application;

[0038] Figure 5 It is a schematic diagram of the implementation process of another image noise reduction method disclosed in an embodiment of the present application;

[0039] Figure 6 is an application flow chart of an image noise reduction method disclosed in an embodiment of the present application;

[0040] Figure 7 is a structural schematic diagram of an image noise reduction device disclosed in an embodiment of the present application;

[0041] Figure 8 It is a computer device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the specific technical solution of the present application will be further described in detail below in conjunction with the drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application, but are not used to limit the scope of the present application.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0044] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0045] It should be pointed out that the terms "first\second\third" involved in the embodiments of the present application are used to distinguish similar or different objects, and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0046] In view of this, an embodiment of the present application provides an image noise reduction method, which is applied to a smart computer. Figure 1 FIG. 1 is an application scenario diagram of an image noise reduction method in an embodiment. Figure 1 As shown, the user can use an electronic device 10, which may include but is not limited to a tablet computer, a laptop computer, a PC (Personal Computer), etc. The function implemented by the method can be implemented by calling a program code by a processor in the electronic device, and of course the program code can be stored in a computer storage medium. It can be seen that the electronic device at least includes a processor and a storage medium.

[0047] Figure 2 A schematic diagram of an implementation flow of an image noise reduction method provided in an embodiment of the present application. Figure 1 In the application scenario shown in Figure 2 As shown, the method may include the following steps 201 to 203:

[0048] Step 201, acquiring a target image.

[0049] In the embodiment of the present application, ensure that the resolution of the image meets the requirements, and check the resolution through the image viewer. Check whether the image is clear and confirm that there is no blur or motion blur. Check whether the image color is true, and verify it through a color card or color calibration tool. Check the noise level in the image to ensure that it is within a reasonable range. When the above requirements are met, acquire the image to obtain the target image.

[0050] Step 202, processing the target image to obtain a plurality of images to be processed of different sizes.

[0051] In the embodiment of the present application, the target image is resized to obtain multiple images of different sizes to be processed. This can be achieved by adjusting the size of the image, for example, the image can be cut into images of different sizes according to actual needs to obtain multiple images of different sizes to be processed.

[0052] For each image to be processed, determine its denoising intensity. The denoising intensity can be set based on the noise level and detail characteristics of the image. The selection of denoising intensity can be dynamically adjusted according to the actual situation of the image to ensure that it adapts to image features of different scales during the processing process.

[0053] Step 203 , performing at least two preset noise reduction processes according to the noise reduction intensity required for each of the multiple images to be processed and the multiple images to be processed, to obtain a target image after noise reduction process.

[0054] In the embodiment of the present application, a preset noise reduction processing algorithm is applied to each image to be processed. The preset noise reduction processing may include a variety of noise reduction techniques, such as mean filtering, median filtering, waveform denoising, etc.

[0055] In each denoising process, the denoising intensity is determined before. A certain intensity is used in the first denoising process, and another intensity is used in the second denoising process, or the intensity is adjusted according to the preset denoising process steps. Multiple images of different sizes after denoising are synthesized to obtain the final denoised target image. The synthesis method can be a simple weighted average or a more complex fusion algorithm.

[0056] The embodiment of the present application decomposes the target image into images of different sizes to be processed, and each size of the image can be subjected to special noise reduction processing according to its specific noise characteristics. Layer-by-layer processing and adjustment of the noise reduction intensity can effectively reduce the situation of excessive noise reduction. For areas with more details, a smaller noise reduction intensity can avoid the loss of details, while for areas with more noise, the noise reduction intensity can be increased to remove excess noise. According to the noise characteristics of images of different sizes, the noise reduction intensity is dynamically adjusted so that images of each size can receive suitable noise reduction processing. It can avoid the loss of details during the strong noise reduction process and ensure image clarity and visual quality.

[0057] In the above Figure 2 Based on this, the present application also provides another implementation flow diagram of an image noise reduction method. Figure 3 As shown, the method may include the following steps 301 to 303:

[0058] Step 301, acquiring a target image.

[0059] The specific implementation of step 301 is the same as that of the above-mentioned step 201, and will not be repeated herein.

[0060] Step 302: Process the target image to obtain a plurality of images to be processed of different sizes.

[0061] The specific implementation of step 302 is the same as that of the above-mentioned step 202, and will not be repeated herein.

[0062] Step 303: According to the noise reduction intensity required for each of the multiple images to be processed and the average of the noise reduction intensity required for each group of images to be processed, the preset noise reduction processing is performed on the multiple images to be processed, wherein each group of images to be processed includes at least two of the multiple images to be processed, to obtain the target image after the noise reduction processing.

[0063] In the embodiment of the present application, a plurality of images to be processed are extracted from a target image, and the target image is cut into a plurality of image blocks of different sizes, for example, large, medium and small size blocks, to meet different noise reduction processing requirements.

[0064] The images to be processed are grouped according to the similarity of the denoising intensity required. Each group contains at least two images to be processed. The grouping method can be determined based on the preliminary noise estimation value. For example, the denoising requirements of the image blocks can be divided into three categories: low, medium, and high.

[0065] Perform preliminary noise reduction on each image to be processed. According to the noise characteristics of each image to be processed, select an appropriate noise reduction algorithm for initial processing. Common noise reduction algorithms include: Gaussian filtering: smoothing the image, suitable for removing Gaussian noise. Median filtering: by replacing the value of each pixel with the median of its neighboring pixels, suitable for removing salt and pepper noise. Wavelet transform: through threshold processing of wavelet coefficients, suitable for various types of noise.

[0066] Evaluate the image quality after the initial noise reduction, record the noise reduction strength and effect of each image, and provide reference data for subsequent processing. Calculate the mean noise reduction strength of each group of images to be processed. For each group of images, calculate the mean noise reduction strength of all images in the group. The following methods can be used: Average calculation: Add the noise reduction strength values ​​of all images in the group and calculate the average. Weighted average: If the noise levels of images in the group vary greatly, the noise reduction strength of each image can be weighted.

[0067] Set the parameters of the secondary denoising process according to the mean denoising strength. These parameters will affect the strength and effect of the secondary process. Apply an appropriate denoising algorithm for secondary processing based on the mean denoising strength of each group of images. This may include: Improved Gaussian filtering: adjust the standard deviation of the filter to adapt to the mean denoising strength. Improved median filtering: adjust the filter window size to better adapt to the mean denoising strength. Other denoising techniques: such as non-local means or adaptive filtering techniques. Evaluate the quality of the images after secondary processing to ensure that the denoising effect reaches the expected goal. Synthesize the processed image blocks into the final target image. Use image stitching or reconstruction techniques to synthesize the processed image blocks of different sizes into a complete target image. Image stitching: Use the average or weighted average of the overlapping area to stitch the image blocks. Image fusion: Apply an image fusion algorithm, such as Laplacian pyramid fusion, to synthesize the image. Process the transition of the stitching edges to ensure that there are no obvious seams or distortions at the edges of the synthesized image.

[0068] The embodiment of the present application performs mean denoising on the image group to ensure that the noise level of all image blocks after processing is consistent, avoiding uneven processing due to differences in noise characteristics of individual images. The mean denoising method helps to balance noise removal and detail retention, and prevents over-smoothing or detail loss that may occur when processing separately. Applying mean denoising can more effectively handle various noise types, optimize the noise performance of different areas in the image, and improve the visual effect of the overall image.

[0069] In the above Figure 3 Based on this, the present application also provides another implementation flow diagram of an image noise reduction method. Figure 4 As shown, the method may include the following steps 401 to 405:

[0070] Step 401, acquiring a target image.

[0071] The specific implementation of step 401 is the same as that of the above-mentioned step 301, and will not be repeated herein.

[0072] Step 402: Process the target image to obtain a plurality of images to be processed of different sizes.

[0073] The specific implementation of step 402 is the same as that of the above-mentioned step 302, and will not be repeated herein.

[0074] Step 403 : performing the preset noise reduction process on each of the to-be-processed images according to the corresponding required noise reduction intensity to obtain a plurality of first noise-reduced sub-images.

[0075] In the embodiment of the present application, a suitable denoising algorithm is selected according to the image noise characteristics, for example, Gaussian filtering is used for uniform noise, and median filtering is used for salt and pepper noise. The parameters of the denoising algorithm (such as the standard deviation of Gaussian filtering and the window size of median filtering) are set to match the denoising intensity requirements of the image. A plurality of first denoised sub-images are obtained.

[0076] Step 404: Perform the preset denoising process on the first denoised sub-images corresponding to each group of images to be processed according to the average value of the denoising intensity required for each group of images to be processed, to obtain a plurality of second denoised sub-images, wherein the first denoised sub-image is a first denoised sub-image corresponding to the smaller image to be processed among the at least two first denoised sub-images corresponding to each group of images to be processed.

[0077] In the embodiment of the present application, the mean of the first denoised sub-image of each group of images is calculated to evaluate the overall noise level. A secondary denoising algorithm is selected based on the mean denoising strength, such as weighted averaging or more complex filtering techniques. Advanced denoising methods such as block matching 3D filtering and non-local mean denoising are applied to enhance the detail retention of the image. The algorithm parameters are adjusted to ensure the best denoising effect while maintaining image quality.

[0078] Step 405: fuse the multiple second denoised sub-images to obtain the denoised target image.

[0079] In an embodiment of the present application, an image stitching algorithm (such as SIFT, SURF) is used to seamlessly stitch image blocks together to handle the seam problem in overlapping areas. Weighted averaging or Laplace pyramid fusion technology is applied to synthesize all second denoised sub-images into a final image to maintain detail consistency. Edge smoothing technology, such as Gaussian blur, is applied to process the edges of image stitching and reduce seam traces. An image seam optimization algorithm (such as multi-scale fusion) is used to process the seam area to achieve a more natural transition. A sharpening filter (such as Unsharp Mask) is used to enhance image details and make the image clearer.

[0080] Each group of images to be processed includes a first image to be processed and a second image to be processed of different sizes, and the sizes of the images to be processed in different groups of images to be processed are all different.

[0081] Furthermore, the denoising process is performed on the multiple images to be processed of different sizes in sequence according to the sizes of the multiple images to be processed to obtain the target image after the denoising process, including: performing chroma denoising process and luminance denoising process on the multiple images to be processed respectively.

[0082] Specifically, chroma noise reduction is performed on each image to be processed. Chroma noise reduction focuses on the color information of the image and reduces the impact of noise on the color. Methods such as color space conversion (for example, conversion to HSV or Lab space), color channel separation, and then noise suppression on the chroma channel can be used. Luminance noise reduction is performed on each image to be processed. Luminance noise reduction focuses on the brightness information of the image and reduces the interference of noise on the brightness of the image. Usually, the brightness channel of the image is smoothed or filtered, for example, using Gaussian filtering, median filtering, and other methods.

[0083] The embodiment of the present application can adjust the noise reduction intensity more accurately by performing noise reduction processing on each image to be processed and each group of images respectively, thereby improving the quality of the final image. Individual processing processes the specific noise characteristics of each image, while mean processing takes into account the overall noise situation of multiple images, and can optimize the noise reduction effect in a global range. First, a preset noise reduction processing is performed on each image to be processed, and then a secondary processing is performed according to the overall requirements of each group of images, which helps to better retain image details and effectively remove noise. This staged processing method can better balance image details and noise removal, and avoid excessive smoothing or loss of details caused by a single processing. By processing the size and mean noise reduction intensity of each group of images, the noise problem in multi-scale images can be effectively handled, especially when the image size difference is large. When processing smaller images and larger images, the noise reduction intensity can be adjusted according to their noise characteristics to adapt to different image requirements. After preprocessing the first denoised sub-image, it is fused and processed to ensure that the noise reduction effect of the final image is more uniform. The processing method of the second denoised sub-image ensures that the noise of each part is effectively processed during the image fusion stage, while maintaining the details and consistency of the image.

[0084] In the above Figure 3 Based on this, the present application also provides another implementation flow diagram of an image noise reduction method. Figure 5 As shown, the method may include the following steps 501 to 508:

[0085] Step 501, acquiring a target image.

[0086] The specific implementation of step 501 is the same as that of the above-mentioned step 301, and will not be repeated herein.

[0087] Step 502: Process the target image to obtain a plurality of images to be processed of different sizes.

[0088] The specific implementation of step 502 is the same as that of the above-mentioned step 302, and will not be repeated herein.

[0089] Step 503: Perform the preset noise reduction process on each of the to-be-processed images to obtain a plurality of first noise-reduced sub-images.

[0090] In the embodiment of the present application, a suitable noise reduction algorithm (such as median filtering, bilateral filtering or convolutional neural network, etc.) is selected and applied to each image to be processed to obtain multiple noise reduction sub-images.

[0091] Step 504, determining a first average noise reduction strength of noise reduction strengths corresponding to a first image to be processed and noise reduction strengths corresponding to a second image to be processed, wherein the first image to be processed is the largest image to be processed and the second image to be processed is the second largest image to be processed.

[0092] In the embodiment of the present application, the noise reduction strengths of the first image to be processed with the largest size and the second image to be processed with the second largest size are measured (for example, by using mean square error or structural similarity measurement), and the average of the noise reduction strengths of the two images is calculated to obtain a first average noise reduction strength.

[0093] Step 505: Perform denoising processing on a first denoised sub-image corresponding to the second image to be processed according to the first average denoising intensity to obtain a processed first denoised fused image.

[0094] In the embodiment of the present application, the first average noise reduction intensity is used as a parameter to further reduce noise on the first noise reduction sub-image of the second image to be processed. Through this process, a processed first noise reduction fusion image is obtained, which matches the noise reduction intensity of the first image to be processed after noise reduction.

[0095] Step 506, determining a second average noise reduction intensity of the noise reduction intensity of the processed first noise reduction fusion image and the noise reduction intensity of the third image to be processed, wherein the third image to be processed is an image to be processed that is sorted in descending order of size and is located after the second image to be processed.

[0096] In the embodiment of the present application, the noise reduction strength of the processed first noise reduction fusion image is measured. The noise reduction strength of the third image to be processed with the third largest size is measured. The average of the noise reduction strengths of the two images is calculated to obtain a second average noise reduction strength.

[0097] Step 507: Process the third image to be processed according to the second average noise reduction intensity to obtain a processed second noise reduction fused image.

[0098] In the embodiment of the present application, the first denoised sub-image of the third image to be processed is further denoised using the second average denoising intensity as a parameter to obtain a processed second denoised fused image, which after denoising matches the denoising intensity of the processed first denoised fused image.

[0099] Step 508: When the fourth image to be processed is the image to be processed with the smallest size, a target image after noise reduction processing is obtained.

[0100] In the embodiment of the present application, the processed images are fused together, and finally the fourth image to be processed with the smallest size is subjected to the final noise reduction process. All processed images are combined to generate the final noise reduction process target image.

[0101] Specifically, the present application also provides an application flow chart of an image noise reduction method. Figure 6 As shown, first, the image is divided into multiple images of different sizes, and the images are arranged from large to small as the first image to be processed, and the size is the original size. The second image to be processed has a size reduced by 4 / 1. The third image to be processed has a size reduced by 16 / 1. The fourth image to be processed has a size reduced by 64 / 1.

[0102] The first image to be processed, the second image to be processed, the third image to be processed and the fourth image to be processed are denoised to obtain the first image to be processed, the second image to be processed, the third image to be processed and the fourth image to be processed after denoising. Since the smaller the size in the image, the stronger the denoising intensity required for the noise, the fourth image to be processed is merged with the third image to be processed, and the average value of the denoising intensity of the chromaticity and brightness of the two images is obtained and applied to the third image to be processed.

[0103] The third image to be processed after the application is fused with the second image to be processed, and based on the average value of the chromaticity and brightness denoising intensity values ​​of the two images, the average value is applied to the second image to be processed.

[0104] The second image to be processed after application is fused with the first image to be processed, and based on the average value of the chromaticity and brightness denoising intensity values ​​of the two images, it is applied to the first image to be processed to obtain the target image. The sizes of multiple images to be processed of different sizes can be reduced exponentially.

[0105] This application uses multiple preset noise reduction processes and gradual optimization processes to accurately adjust the noise reduction intensity of each image to be processed. This ensures that the noise reduction effect of images at different sizes is more balanced and consistent, thereby improving the overall quality and clarity of the final target image. This multi-level, step-by-step noise reduction process allows the noise reduction intensity to be more closely matched to the actual needs of the image, and the resulting image is of higher quality and detail fidelity.

[0106] It should be understood that, although the steps in the above-mentioned flowcharts are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above-mentioned flowcharts may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0107] Based on the foregoing embodiments, an embodiment of the present application provides an image noise reduction device, which includes the modules included and the units included in the modules, which can be implemented by a processor; of course, it can also be implemented by a specific logic circuit; in the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA), etc.

[0108] Figure 7 A schematic diagram of the structure of an image noise reduction device provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, the device 700 includes an acquisition module 701 and a processing module 702, wherein:

[0109] An acquisition module 701 is used to acquire a target image;

[0110] The processing module 702 is used to process the target image to obtain a plurality of images to be processed of different sizes;

[0111] The processing module 702 is also used to perform at least two preset noise reduction processes according to the noise reduction intensity required for each of the multiple images to be processed and the multiple images to be processed, to obtain a target image after the noise reduction process, wherein the required noise reduction intensity is the noise reduction intensity of the corresponding image when the preset noise reduction process is performed.

[0112] In some embodiments, the processing module 702 is further specifically used to perform the preset noise reduction processing on the multiple images to be processed according to the noise reduction intensity required for each of the multiple images to be processed and the average of the noise reduction intensity required for each group of images to be processed, wherein each group of images to be processed includes at least two images to be processed among the multiple images to be processed, to obtain the target image after the noise reduction processing.

[0113] In some embodiments, the processing module 702 is further specifically configured to perform the preset noise reduction processing on each of the to-be-processed images according to the corresponding required noise reduction intensity to obtain a plurality of first noise reduction sub-images;

[0114] The processing module 702 is further specifically configured to perform the preset denoising process on the first denoised sub-images corresponding to each group of images to be processed according to the average value of the denoising intensity required by each group of images to be processed, so as to obtain a plurality of second denoised sub-images, wherein the first denoised sub-image is a first denoised sub-image corresponding to the image to be processed with a smaller size among the at least two first denoised sub-images corresponding to each group of images to be processed;

[0115] The acquisition module 701 is further specifically configured to fuse the plurality of second denoised sub-images to obtain the denoised target image.

[0116] In some embodiments, the processing module 702 is further specifically configured to perform the preset noise reduction process on each of the images to be processed to obtain a plurality of first noise reduction sub-images;

[0117] The acquisition module 701 is further specifically used to determine a first average noise reduction strength of a noise reduction strength corresponding to a first image to be processed and a noise reduction strength corresponding to a second image to be processed, wherein the first image to be processed is the image to be processed with the largest size, and the second image to be processed is the image to be processed with the second largest size;

[0118] The processing module 702 is further specifically configured to perform denoising processing on a first denoised sub-image corresponding to the second image to be processed according to the first average denoising intensity to obtain a processed first denoised fused image;

[0119] The processing module 702 is further specifically used to determine a second average noise reduction intensity of the noise reduction intensity of the processed first noise reduction fused image and the noise reduction intensity of the third image to be processed, wherein the third image to be processed is an image to be processed that is sorted in descending order of size and is located after the second image to be processed;

[0120] The processing module 702 is further specifically configured to process the third image to be processed according to the second average noise reduction intensity to obtain a processed second noise reduction fused image;

[0121] The acquisition module 701 is further specifically configured to obtain a target image after noise reduction processing when the fourth image to be processed is the image to be processed with the smallest size.

[0122] In some embodiments, the processing module 702 is further specifically configured to perform chroma noise reduction processing and luminance noise reduction processing on the multiple images to be processed.

[0123] The description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device embodiment of the present application, please refer to the description of the method embodiment of the present application for understanding.

[0124] It should be noted that in the embodiments of this application Figure 7 The division of modules in the image noise reduction device shown is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit in each embodiment of the present application may be integrated into a processing unit, or may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit. It may also be implemented in the form of a combination of software and hardware.

[0125] It should be noted that in the embodiment of the present application, if the above method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present application can be essentially or partly embodied in the form of a software product that contributes to the relevant technology. The computer software product is stored in a storage medium, including several instructions to enable an electronic device to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific combination of hardware and software.

[0126] The embodiment of the present application provides a computer device, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0127] An embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the method provided in the above embodiment are implemented.

[0128] An embodiment of the present application provides a computer program product including instructions, which, when executed on a computer, enables the computer to execute the steps of the method provided in the above method embodiment.

[0129] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part 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 those shown in the figure, or combine certain components, or have a different arrangement of components.

[0130] In one embodiment, an image noise reduction device provided by the present application can be implemented in the form of a computer program. The computer program can be Figure 8 The computer device shown in the figure is run. The memory of the computer device can store various program modules constituting the above-mentioned device. The computer program composed of various program modules enables the processor to execute the steps in the method of each embodiment of the present application described in this specification.

[0131] It should be noted here that the description of the above storage medium and device embodiments is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium, storage medium and device embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0132] It should be understood that "one embodiment" or "an embodiment" or "some embodiments" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in one embodiment" or "in some embodiments" appearing throughout the specification may not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. The above-mentioned sequence numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments. The above description of each embodiment tends to emphasize the differences between the various embodiments, and the same or similarities can be referenced to each other. For the sake of brevity, this article will not repeat them.

[0133] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, object A and / or object B can represent three situations: object A exists alone, object A and object B exist at the same time, and object B exists alone.

[0134] It should be noted that, in this article, the terms "include", "comprises" or any other variations 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, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0135] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as: multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or modules can be electrical, mechanical or other forms.

[0136] The modules described above as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules; they may be located in one place or distributed on multiple network units; some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0137] In addition, all functional modules in the embodiments of the present application may be integrated into one processing unit, or each module may be a separate unit, or two or more modules may be integrated into one unit; the above-mentioned integrated modules may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0138] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, etc., various media that can store program codes.

[0139] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can essentially or in other words, the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling an electronic device to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0140] The methods disclosed in several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0141] The features disclosed in several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0142] The features disclosed in several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0143] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An image denoising method, characterized in that: The method comprises: Get the target image; Processing the target image to obtain a plurality of images to be processed of different sizes; According to the noise reduction intensity required for each of the multiple images to be processed and the multiple images to be processed, at least two preset noise reduction processes are performed to obtain a target image after the noise reduction process, wherein the required noise reduction intensity is the noise reduction intensity of the corresponding image when the preset noise reduction process is performed.

2. The method according to claim 1, characterized in that The step of performing at least two preset noise reduction processes according to the noise reduction intensity required for each of the plurality of images to be processed and the plurality of images to be processed to obtain a target image after the noise reduction process comprises: According to the noise reduction intensity required for each of the multiple images to be processed and the average of the noise reduction intensity required for each group of images to be processed, the preset noise reduction processing is performed on the multiple images to be processed, each group of images to be processed includes at least two images to be processed among the multiple images to be processed, to obtain the target image after the noise reduction processing.

3. The method according to claim 2, characterized in that According to the noise reduction intensity required for each of the multiple images to be processed and the average of the noise reduction intensity required for each group of images to be processed, the multiple images to be processed are subjected to a preset noise reduction process to obtain a target image after the noise reduction process, including: Performing the preset noise reduction processing on each of the to-be-processed images according to the corresponding required noise reduction intensity to obtain a plurality of first noise-reduced sub-images; According to the average value of the noise reduction strength required for each group of images to be processed, the preset noise reduction process is performed on the first noise reduction sub-images corresponding to each group of images to be processed to obtain a plurality of second noise reduction sub-images, wherein the first noise reduction sub-image is a first noise reduction sub-image corresponding to the image to be processed with a smaller size among the at least two first noise reduction sub-images corresponding to each group of images to be processed; The plurality of second denoised sub-images are fused to obtain the denoised target image.

4. The method according to any one of claims 2 or 3, characterized in that: Each group of images to be processed includes a first image to be processed and a second image to be processed of different sizes, and the sizes of the images to be processed in different groups of images to be processed are all different.

5. The method according to any one of claims 1 or 2, characterized in that: The step of performing at least two preset noise reduction processes according to the noise reduction intensity required for each of the plurality of images to be processed and the plurality of images to be processed to obtain a target image after the noise reduction process comprises: Performing the preset noise reduction process on each of the to-be-processed images to obtain a plurality of first noise-reduced sub-images; Determine a first average noise reduction strength of a noise reduction strength corresponding to a first image to be processed and a noise reduction strength corresponding to a second image to be processed, wherein the first image to be processed is the image to be processed with the largest size and the second image to be processed is the image to be processed with the second largest size; Performing denoising processing on a first denoised sub-image corresponding to the second image to be processed according to the first average denoising intensity to obtain a processed first denoised fused image; Determine a second average noise reduction intensity of the noise reduction intensity of the processed first noise reduction fused image and the noise reduction intensity of a third image to be processed, wherein the third image to be processed is an image to be processed that is located after the second image to be processed after being sorted in descending order of size; Processing the third image to be processed according to the second average noise reduction intensity to obtain a processed second noise reduction fused image; When the fourth image to be processed is the image to be processed with the smallest size, a target image after noise reduction processing is obtained.

6. The method according to any one of claims 2 or 3, characterized in that: The step of performing noise reduction processing on the multiple images to be processed of different sizes in sequence according to the sizes of the multiple images to be processed to obtain a target image after noise reduction processing includes: The plurality of images to be processed are respectively subjected to chromaticity noise reduction processing and luminance noise reduction processing.

7. The method according to claim 4, characterized in that The sizes of the multiple images to be processed of different sizes are reduced exponentially.

8. An image noise reduction device, characterized in that: include: An acquisition module, used for acquiring a target image; A processing module, used for processing the target image to obtain a plurality of images to be processed of different sizes; The processing module is also used to perform at least two preset noise reduction processes according to the noise reduction intensity required for each of the multiple images to be processed and the multiple images to be processed, so as to obtain a target image after the noise reduction process, wherein the required noise reduction intensity is the noise reduction intensity of the corresponding image when the preset noise reduction process is performed.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, wherein: When the processor executes the program, the steps of the method according to any one of claims 1 to 7 are implemented.

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 method according to any one of claims 1 to 7 is implemented.

Citation Information

Cited By

  • Image processing method and device, storage medium and program product

    CN119251089A