Image noise reduction method and device, equipment and storage medium

Abstract

The invention provides an image noise reduction method and device, equipment and a storage medium, and relates to the technical field of image processing. In some embodiments of the disclosure, color space conversion is performed on a first image corresponding to a first color space to obtain a second image corresponding to a second color space; performing noise reduction on the second image to obtain a third image after noise reduction; performing color recovery on the third image according to the second image to obtain a fourth image, and performing color recovery on the third image based on the second image to reduce color loss caused by image noise reduction; and performing color space conversion operation on the fourth image to obtain a target image corresponding to the first color space and having relatively high image noise reduction quality, thereby improving the image noise reduction quality.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing technologies, and in particular, to an image denoising method, apparatus, device, and storage medium. Background Art

[0002] With the continuous development of digital image technologies, image denoising technologies have been widely applied in various fields. Among them, the color noise reduction technology for images is a technology for processing the noise existing in color images. The noise in color images will affect the quality and clarity of the images, and reduce the visualization effect and information volume of the images.

[0003] Currently, the color noise reduction method for images has color loss, reducing the quality of image denoising. Summary of the Invention

[0004] The present disclosure provides an image denoising method, apparatus, device, and storage medium, so as to at least solve the problems that the existing color noise reduction method for images has color loss and the image denoising quality is relatively low.

[0005] The technical solution of the present disclosure is as follows:

[0006] An exemplary embodiment of the present disclosure provides an image denoising method, including:

[0007] Performing a color space conversion on a first image corresponding to a first color space to obtain a second image corresponding to a second color space;

[0008] Performing denoising on the second image to obtain a third denoised image;

[0009] Performing color restoration on the third image according to the second image to obtain a fourth image;

[0010] Performing a color space conversion operation on the fourth image to obtain a target image corresponding to the first color space.

[0011] Optionally, the second image includes: first color channel data, and the third image includes: second color channel data. The first color channel data and the second color channel data are data of the same color channels of the second image and the third image. The performing color restoration on the third image according to the second image to obtain a fourth image includes:

[0012] Performing a binarization operation on the first color channel data to obtain a binary image;

[0013] Screening out a target connected region from the binary image;

[0014] Perform connected component color extraction based on the target connected component, the first color channel data, and the second color channel data to obtain the color information of the target connected component;

[0015] Perform color restoration based on the color information of the target connected component and the second color channel data to obtain the fourth image.

[0016] Optionally, the screening of the target connected component from the binary image includes:

[0017] Perform connected component labeling on the binary image to obtain candidate connected components;

[0018] Select a target connected component from the candidate connected components whose connected component parameters meet the set connected component parameter conditions.

[0019] Optionally, the connected component parameters include at least one of the following: connected component area, connected component contour length, position of the circumscribed circle of the connected component, and radius of the circumscribed circle of the connected component.

[0020] Optionally, the performing connected component color extraction based on the target connected component, the first color channel data, and the second color channel data to obtain the color information of the target connected component includes:

[0021] Retain the color information corresponding to the target connected component in the first color channel data; and

[0022] Delete the color information other than the target connected component in the first color channel data to obtain the color information of the target connected component.

[0023] Optionally, the performing color restoration based on the color information of the target connected component and the second color channel data to obtain the fourth image includes:

[0024] Overlay the color information of the target connected component and the second color channel data to obtain the fourth image.

[0025] Optionally, the overlaying the color information of the target connected component and the second color channel data to obtain the fourth image includes:

[0026] Overlay the color information of the target connected component and the second color channel data according to the first weight corresponding to the color information of the target connected component and the second weight corresponding to the second color channel data to obtain the fourth image.

[0027] An exemplary embodiment of the present disclosure further provides an image denoising device, including:

[0028] The first conversion module is used to perform color space conversion on the first image corresponding to the first color space to obtain a second image corresponding to the second color space;

[0029] The noise reduction module is used to reduce noise of the second image to obtain a third image after noise reduction;

[0030] The color restoration module is used to perform color restoration on the third image according to the second image to obtain a fourth image;

[0031] The second conversion module performs a color space conversion operation on the fourth image to obtain a target image corresponding to the first color space.

[0032] Optionally, the second image includes: first color channel data, the third image includes: second color channel data, and the first color channel data and the second color channel data are data of the same color channel of the second image and the third image; when the color restoration module performs color restoration on the third image according to the second image to obtain a fourth image, it is used for:

[0033] Perform a binarization operation on the first color channel data to obtain a binary image;

[0034] Screen out a target connected domain from the binary image;

[0035] Perform connected domain color extraction according to the target connected domain, the first color channel data and the second color channel data to obtain color information of the target connected domain;

[0036] Perform color restoration according to the color information of the target connected domain and the second color channel data to obtain the fourth image.

[0037] Optionally, when the color restoration module screens out a target connected domain from the binary image, it is used for:

[0038] Perform connected domain marking on the binary image to obtain candidate connected domains;

[0039] Select a target connected domain from the candidate connected domains whose connected domain parameters meet the set connected domain parameter conditions.

[0040] Optionally, the connected domain parameters include at least one of the following: connected domain area, connected domain contour length, connected domain circumcircle position, and connected domain circumcircle radius.

[0041] Optionally, when the color restoration module performs connected domain color extraction according to the target connected domain, the first color channel data and the second color channel data to obtain color information of the target connected domain, it is used for:

[0042] Retain the color information corresponding to the target connected region in the first color channel data; and

[0043] Delete the color information in the first color channel data except for the target connected region to obtain the color information of the target connected region.

[0044] Optionally, when the color restoration module performs color restoration according to the color information of the target connected region and the second color channel data to obtain the fourth image, it is configured to:

[0045] Overlay the color information of the target connected region and the second color channel data to obtain the fourth image.

[0046] Optionally, when the color restoration module overlays the color information of the target connected region and the second color channel data to obtain the fourth image, it is configured to:

[0047] Overlay the color information of the target connected region and the second color channel data according to the first weight corresponding to the color information of the target connected region and the second weight corresponding to the second color channel data to obtain the fourth image.

[0048] An exemplary embodiment of the present disclosure further provides an electronic device, including:

[0049] A processor;

[0050] A memory for storing instructions executable by the processor;

[0051] Wherein, the processor is configured to execute the instructions to implement the steps in the above method.

[0052] An exemplary embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above method are implemented.

[0053] An exemplary embodiment of the present disclosure further provides a computer program product, including a computer program / instructions, and when the computer program / instructions are executed by a processor, the steps in the above method are implemented.

[0054] The technical solutions provided by the embodiments of the present disclosure at least bring the following beneficial effects:

[0055] In some embodiments of the present disclosure, the first image corresponding to the first color space is subjected to a color space conversion to obtain a second image corresponding to the second color space; the second image is denoised to obtain a third denoised image; based on the second image, the third image is color restored to obtain a fourth image, and color restoration of the third image based on the second image reduces color loss caused by image denoising; the fourth image is subjected to a color space conversion operation to obtain a target image with a higher image denoising quality corresponding to the first color space, improving the image denoising quality.

[0056] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and do not limit the present disclosure. Brief Description of the Drawings

[0057] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure, and do not constitute an improper limitation to the present disclosure.

[0058] Figure 1 is a schematic flowchart of image denoising in the prior art;

[0059] Figure 2 is a schematic flowchart of an image denoising method provided by an exemplary embodiment of the present disclosure;

[0060] Figure 3 is a schematic structural diagram of an image denoising device provided by an exemplary embodiment of the present disclosure;

[0061] Figure 4 is a schematic structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure. Detailed Description of the Embodiments

[0062] In order to enable those of ordinary skill in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0063] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above accompanying drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure.

[0064] It should be noted that the user information involved in this disclosure includes, but is not limited to, user device information and user personal information; the collection, storage, use, processing, transmission, provision, and disclosure of user information in this disclosure comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0065] With the continuous development of digital media technology, video image processing technology has been widely applied in various fields. For example, in the field of video surveillance, video image processing technology can be used for face recognition, behavior analysis, etc.; in the medical field, video image processing technology can be used for the analysis and diagnosis of medical images; in the entertainment field, video image processing technology can be used for the production of video special effects and the development of video games, etc. However, the application of video image processing technology also faces some challenges. For example, video signals have the characteristics of time series and require more complex algorithms and technologies to process; video signals have a large amount of data and require efficient algorithms and technologies to process and transmit; the quality of video signals is affected by various factors and requires denoising, enhancement, etc. processing of video signals.

[0066] With the continuous development of digital image technology, image denoising technology has been widely applied in various fields. Among them, color image denoising technology is a technology for processing the noise existing in color images. The noise in color images will affect the quality and clarity of the images, reducing the visualization effect and information content of the images. At the same time, the application of color image denoising technology also faces some challenges. For example, there are various types of noise in color images and different types of noise need to be processed; the noise distribution in color images is uneven and different regions need to be processed differently; color image denoising technology needs to maintain the details and color information of the images and avoid image distortion caused by overprocessing.

[0067] Currently, an image denoising system can include processing processes such as raw data spatial domain denoising, yuv data temporal domain denoising, and yuv data spatial domain denoising. This disclosure is for yuv data denoising.

[0068] Figure 1 It is a schematic diagram of the process of image denoising in the prior art. As Figure 1As shown in the figure, first, a color space conversion is performed on the input image in RGB format to effectively split the luminance information and color information. The split luminance information and color information are respectively denoised, and color space conversion is performed using the denoised data, with the aim of obtaining image data in RGB format as the output result of the entire image processing link. In the above-mentioned conventional image denoising method, the main technical solution for color noise suppression is to use various low-pass filters for color information, including operations such as Gaussian filtering, bilateral filtering, non-local means filtering, and guided filtering. However, such filters will cause color loss while suppressing color noise, especially in areas with high saturation and small areas.

[0069] To address the above technical problems, in some embodiments of the present disclosure, a color space conversion is performed on a first image corresponding to a first color space to obtain a second image corresponding to a second color space; the second image is denoised to obtain a third denoised image; based on the second image, color restoration is performed on the third image to obtain a fourth image. Color restoration is performed on the third image based on the second image to reduce color loss caused by image denoising; a color space conversion operation is performed on the fourth image to obtain a target image with relatively high image denoising quality corresponding to the first color space, thereby improving the image denoising quality.

[0070] The following will detail the technical solutions provided by the embodiments of the present disclosure in conjunction with the accompanying drawings.

[0071] Figure 2 It is a flowchart of an image denoising method provided by an exemplary embodiment of the present disclosure. As Figure 1 shown, the method includes:

[0072] S201: Perform a color space conversion on a first image corresponding to a first color space to obtain a second image corresponding to a second color space;

[0073] S202: Denoise the second image to obtain a third denoised image;

[0074] S203: Based on the second image, perform color restoration on the third image to obtain a fourth image;

[0075] S204: Perform a color space conversion operation on the fourth image to obtain a target image corresponding to the first color space.

[0076] In this embodiment, the execution subject of the above method may be a terminal device or a server.

[0077] Among them, the terminal device includes, but is not limited to, a mobile station (MS), a mobile terminal, a mobile telephone, a handset, and portable equipment, etc. The terminal device can communicate with one or more core networks via a radio access network (RAN). For example, the terminal device can be a mobile telephone (or a "cellular" telephone), a computer with wireless communication functions, etc. The terminal device can also be a computer with wireless transceiver functions, a virtual reality (VR) terminal device, an AR terminal device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, etc. And the operating systems installed on the terminal device include, but are not limited to: IOS, Android, windows, linux, Mac OS and other operating systems. In different networks, the terminal can be called different names, such as: user equipment, mobile station, user unit, station, cellular telephone, personal digital assistant, wireless modem, wireless communication device, handheld device, laptop computer, cordless telephone, wireless local loop station, TV, etc. For the convenience of description, it is simply referred to as the terminal device in this embodiment.

[0078] In this embodiment, the implementation form of the server is not limited. For example, the server can be a conventional server, a cloud server, a cloud host, a virtual center and other server devices. Among them, the server mainly consists of a processor, a hard disk, a memory, a system bus, etc., and is of a general computer architecture type.

[0079] In this embodiment, the first image corresponding to the first color space is subjected to color space conversion to obtain a second image corresponding to the second color space; the second image is denoised to obtain a third denoised image; based on the second image, color restoration is performed on the third image to obtain a fourth image. Color restoration is performed on the third image based on the second image to reduce color loss caused by image denoising; the fourth image is subjected to a color space conversion operation to obtain a target image with a relatively high image denoising quality corresponding to the first color space, thereby improving the image denoising quality.

[0080] It should be noted that the present disclosure does not limit the color space type of the first image. The color space type of the first image includes, but is not limited to, the following: RGB color space, CMYK color space, HSV color space, LAB color space, and YUV color space. Optionally, the first color space may be the RGB color space, and the second color space may be the YUV color space.

[0081] Among them, the image corresponding to the YUV color space includes Y-channel data and UV-channel data. Y represents the luminance information of the image, while UV represents the chrominance information used to describe colors. The Y-channel data is usually one of the original data obtained from an image sensor, which reflects the brightness or light and dark level of the image. After being processed and encoded, the Y-channel data can generate a standard digital video signal, so it plays an important role in video production and transmission. The UV-channel data, that is, the U color channel data and the V color channel data, is a combination of two color components, which represent a specific color in the RGB color space. In color photography and image processing, the RGB color space is a commonly used color model, which consists of three channels: red, green, and blue. The intensity of each channel can be used to represent a color. The UV channels can provide a method to control a specific color in the image, which is very important for some specific image processing tasks (such as color correction, color separation, etc.).

[0082] In some embodiments of the present disclosure, the first image corresponding to the first color space is subjected to a color space conversion to obtain a second image corresponding to the second color space. For example, the first image corresponding to the RGB color space is subjected to a color space conversion to obtain a second image corresponding to the YUV color space.

[0083] In some embodiments of the present disclosure, the second image is denoised to obtain a third image after denoising. The present disclosure can perform denoising on the second image based on existing denoising algorithms, and the present disclosure does not limit this.

[0084] It should be noted that the first color channel data and the second color channel data are the data of the same color channel of the second image and the third image, that is, the first color channel data and the second color channel data are the U color channel data, or the V color channel data.

[0085] In some embodiments of the present disclosure, the third image is color restored according to the second image to obtain a fourth image. One implementable way is to perform a binarization operation on the first color channel data to obtain a binary image; screen out target connected components from the binary image; perform connected component color extraction according to the target connected components, the first color channel data, and the second color channel data to obtain the color information of the target connected components; perform color restoration according to the color information of the target connected components and the second color channel data to obtain the fourth image. The present disclosure considers the influence of the low-pass filter on objects with real colors and small areas during the image color noise reduction process, and then extracts corresponding image features for small objects and performs color restoration on the small object areas of the denoised image to ensure that the colors of small objects are not lost.

[0086] It should be noted that binarization is a method of image processing that converts a grayscale image into an image containing only two pixel values (usually black and white). The following is the general process of binarization: Obtain a grayscale image: First, obtain a grayscale image from a color image or other multi-channel images. This can be done by taking the weighted average of the red, green, and blue channels, etc. Select a threshold: Select a threshold that divides the pixels in the grayscale image into two categories. The selection of the threshold depends on the characteristics of the image and the processing requirements. Pixel classification: For each pixel, determine whether its grayscale value exceeds or is equal to the set threshold. If it exceeds or is equal to the threshold, set the pixel to white, otherwise set it to black. Generate a binary image: Generate the final binary image according to the results of pixel classification.

[0087] In some embodiments of the present disclosure, a binarization operation is performed on the first color channel data to obtain a binary image. For example, the present disclosure performs a binarization operation on the U color channel data of the second image to obtain a binary image of the U color channel data of the second image.

[0088] In some embodiments of the present disclosure, target connected components are screened out from the binary image. One implementable way is to perform connected component labeling on the binary image to obtain candidate connected components; select target connected components from the candidate connected components whose connected component parameters meet the set connected component parameter conditions. Among them, the connected component parameters include at least one of the following: connected component area, connected component contour length, connected component circumcircle position, and connected component circumcircle radius. The present disclosure completes the screening of connected components by setting reasonable numerical ranges for information such as area, contour, circumcircle, and color response through setting connected component parameter conditions to obtain target connected components, that is, select the areas corresponding to small objects with real colors in the color channel.

[0089] In the above embodiments of the present disclosure, there is no limitation on the method of connected component labeling, and existing connected component labeling algorithms can be used for labeling. For example, the algorithm in the connected component labeling function bwlabel in matlab can be used to traverse the image once, record the continuous clusters and the equivalent pairs of labels in each row (or column), and then relabel the original image through the equivalent pairs. For another example, the labeling algorithm in the open source library cvBlob can be used. It labels the entire image by locating the inner and outer contours of the connected regions, and the core of this algorithm is the contour search algorithm.

[0090] In the above embodiments of the present disclosure, target connected components whose connected component parameters meet the set connected component parameter conditions are selected from the candidate connected components. For example, target connected components with an area greater than T1 and less than T2 are selected from the candidate connected components.

[0091] In some embodiments of the present disclosure, connected component color extraction is performed based on the target connected component, the first color channel data, and the second color channel data to obtain the color information of the target connected component. One implementable way is to retain the color information corresponding to the target connected component in the first color channel data; and delete the color information in the first color channel data other than the target connected component to obtain the color information of the target connected component. For example, retain the color information corresponding to the target connected component in the U-channel color data of the second image, delete the color information in the U-channel color data of the second image other than the target connected component, and obtain the color information of the target connected component, that is, retain the color information of the small object region with the true color to perform color restoration on the denoised third image.

[0092] In some embodiments of the present disclosure, color restoration is performed based on the color information of the target connected component and the second color channel data to obtain a fourth image. One implementable way is to superimpose the color information of the target connected component and the second color channel data to obtain the fourth image. Among them, when superimposing the color information of the target connected component and the second color channel data, the weights of the color information of the target connected component and the second color channel data can be set to be the same, or different weights can be assigned to the color information of the target connected component and the second color channel data according to the actual situation. The present disclosure performs color restoration based on the color information of the target connected component and the second color channel data to perform color restoration on the denoised third image, minimizing color loss as much as possible and improving the quality of image denoising.

[0093] In an exemplary embodiment of the present disclosure, according to the first weight corresponding to the color information of the target connected region and the second weight corresponding to the second color channel data, the color information of the target connected region and the second color channel data are superimposed to obtain a fourth image. Wherein, the first weight and the second weight are not equal. For example, the first weight is 1 and the second weight is 0.5. According to the first weight 1 and the second weight, the color information of each pixel region in the fourth image is calculated.

[0094] In some embodiments of the present disclosure, a color space conversion operation is performed on the fourth image to obtain a target image corresponding to the first color space. For example, a color space conversion operation is performed on the fourth image in the YUV color space to obtain a target image corresponding to the RGB color space.

[0095] The following takes the first image as an image corresponding to the RGB color space and the second image as an image corresponding to the YUV color space to illustrate the image denoising method of the present disclosure:

[0096] Perform a color space conversion on the first image corresponding to the RGB color space to obtain a second image corresponding to the YUV color space.

[0097] Denoise the second image to obtain a denoised third image.

[0098] Perform a binarization operation on the U color channel data of the second image to obtain a binary image of the U color channel data of the second image; perform a connected region labeling on the binary image to obtain candidate connected regions; select target connected regions from the candidate connected regions whose connected region parameters meet the set connected region parameter conditions. The present disclosure completes the screening of the connected regions by setting reasonable numerical ranges for information such as area, contour, circumscribed circle, and color response in the set connected region parameter conditions to obtain the target connected regions, that is, select the regions corresponding to small objects with real colors in the color channel.

[0099] Extract the color information of the color target connected region from the target connected region, the U channel color data of the second image, and the U channel color data of the third image. Retain the color information corresponding to the target connected region in the U channel color data of the second image, and delete the color information in the U channel color data of the second image except for the target connected region to obtain the color information of the target connected region, that is, retain the color information of the small object regions with real colors to perform color restoration on the denoised third image.

[0100] According to the first weight corresponding to the color information of the target connected region and the second weight corresponding to the second color channel data, the color information of the target connected region and the second color channel data are superimposed to obtain a fourth image.

[0101] Similarly, the color data of the V channel is denoised and color restored in the same manner as the color data of the U channel described above, and the present disclosure does not limit this.

[0102] In the method embodiment of the present disclosure above, the first image corresponding to the first color space is subjected to a color space conversion to obtain a second image corresponding to the second color space; the second image is denoised to obtain a third denoised image; based on the second image, the third image is color restored to obtain a fourth image, and the color restoration of the third image based on the second image reduces the color loss caused by image denoising; the fourth image is subjected to a color space conversion operation to obtain a target image with a higher image denoising quality corresponding to the first color space, improving the image denoising quality.

[0103] Figure 3 It is a schematic structural diagram of an image denoising device 30 provided by an exemplary embodiment of the present disclosure. As Figure 3 shown, the image denoising device 30 includes: a first conversion module 31, a denoising module 32, a color restoration module 33, and a second conversion module 34.

[0104] Among them, the first conversion module 31 is configured to perform a color space conversion on the first image corresponding to the first color space to obtain a second image corresponding to the second color space;

[0105] The denoising module 32 is configured to denoise the second image to obtain a third denoised image;

[0106] The color restoration module 33 is configured to perform color restoration on the third image based on the second image to obtain a fourth image;

[0107] The second conversion module 34 performs a color space conversion operation on the fourth image to obtain a target image corresponding to the first color space.

[0108] Optionally, the second image includes: first color channel data, the third image includes: second color channel data, and the first color channel data and the second color channel data are data of the same color channel of the second image and the third image; when the color restoration module 33 performs color restoration on the third image based on the second image to obtain a fourth image, it is configured to:

[0109] Perform a binarization operation on the first color channel data to obtain a binary image;

[0110] Select a target connected domain from the binary image;

[0111] Extract the color information of the target connected domain according to the target connected domain, the first color channel data, and the second color channel data;

[0112] Color restoration is performed based on the color information of the target connected component and the second color channel data to obtain a fourth image.

[0113] Optionally, when the color restoration module 33 filters out the target connected component from the binary image, it is used for:

[0114] Perform connected component labeling on the binary image to obtain candidate connected components;

[0115] Select a target connected component from the candidate connected components whose connected component parameters meet the set connected component parameter conditions.

[0116] Optionally, the connected component parameters include at least one of the following: connected component area, connected component contour length, position of the circumscribed circle of the connected component, and radius of the circumscribed circle of the connected component.

[0117] Optionally, when the color restoration module 33 performs connected component color extraction based on the target connected component, the first color channel data, and the second color channel data to obtain the color information of the target connected component, it is used for:

[0118] Retain the color information corresponding to the target connected component in the first color channel data; and

[0119] Delete the color information other than the target connected component in the first color channel data to obtain the color information of the target connected component.

[0120] Optionally, when the color restoration module 33 performs color restoration based on the color information of the target connected component and the second color channel data to obtain a fourth image, it is used for:

[0121] Overlay the color information of the target connected component and the second color channel data to obtain a fourth image.

[0122] Optionally, when the color restoration module 33 overlays the color information of the target connected component and the second color channel data to obtain a fourth image, it is used for:

[0123] Overlay the color information of the target connected component and the second color channel data according to the first weight corresponding to the color information of the target connected component and the second weight corresponding to the second color channel data to obtain a fourth image.

[0124] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0125] Figure 4 It is a schematic structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure. As Figure 4 shown, the electronic device includes: a memory 41 and a processor 42. In addition, the electronic device further includes a power supply component 43 and a communication component 44.

[0126] A memory 41 for storing computer programs and configurable to store various other data to support operations on an electronic device. Examples of such data include instructions for any application or method operating on the electronic device.

[0127] The memory 41 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disks or optical discs.

[0128] A communication component 44 for data transmission with other devices.

[0129] A processor 42 that can execute computer instructions stored in the memory 41 to: perform a color space conversion on a first image corresponding to a first color space to obtain a second image corresponding to a second color space; perform noise reduction on the second image to obtain a third image after noise reduction; perform color restoration on the third image according to the second image to obtain a fourth image; perform a color space conversion operation on the fourth image to obtain a target image corresponding to the first color space.

[0130] Optionally, the second image includes: first color channel data, the third image includes: second color channel data, and the first color channel data and the second color channel data are data of the same color channel of the second image and the third image; when the processor 42 performs color restoration on the third image according to the second image to obtain a fourth image, it is used to:

[0131] Perform a binarization operation on the first color channel data to obtain a binary image;

[0132] Select a target connected component from the binary image;

[0133] Perform connected component color extraction according to the target connected component, the first color channel data and the second color channel data to obtain color information of the target connected component;

[0134] Perform color restoration according to the color information of the target connected component and the second color channel data to obtain a fourth image.

[0135] Optionally, when the processor 42 selects a target connected component from the binary image, it is used to:

[0136] Perform connected component labeling on the binary image to obtain candidate connected components;

[0137] Select a target connected component from the candidate connected components whose connected component parameters meet the set connected component parameter conditions.

[0138] Optionally, the connected component parameters include at least one of the following: connected component area, connected component contour length, connected component circumcircle position, and connected component circumcircle radius.

[0139] Optionally, when the processor 42 performs connected component color extraction based on the target connected component, the first color channel data, and the second color channel data to obtain the color information of the target connected component, it is used for:

[0140] Retain the color information corresponding to the target connected component in the first color channel data; and

[0141] Delete the color information other than the target connected component in the first color channel data to obtain the color information of the target connected component.

[0142] Optionally, when the processor 42 performs color restoration based on the color information of the target connected component and the second color channel data to obtain the fourth image, it is used for:

[0143] Overlay the color information of the target connected component and the second color channel data to obtain the fourth image.

[0144] Optionally, when the processor 42 overlays the color information of the target connected component and the second color channel data to obtain the fourth image, it is used for:

[0145] Overlay the color information of the target connected component and the second color channel data according to the first weight corresponding to the color information of the target connected component and the second weight corresponding to the second color channel data to obtain the fourth image.

[0146] Correspondingly, an embodiment of the present disclosure further provides a computer-readable storage medium storing a computer program. When the computer-readable storage medium stores the computer program and the computer program is executed by one or more processors, one or more processors are caused to execute Figure 2 the steps in the method embodiments.

[0147] Correspondingly, an embodiment of the present disclosure further provides a computer program product. The computer program product includes a computer program / instructions, and the computer program / instructions are executed by a processor Figure 2 the steps in the method embodiments.

[0148] The above Figure 4The communication component therein is configured to facilitate communication, either wired or wireless, between the device where the communication component is located and other devices. The device where the communication component is located can access wireless networks based on communication standards, such as WiFi, 2G, 3G, 4G / LTE, 5G and other mobile communication networks, or combinations thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component further includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0149] The above-mentioned Figure 4 The power component therein provides power for various components of the device where the power component is located. The power component may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the device where the power component is located.

[0150] The above-mentioned electronic device further includes a display screen and an audio component.

[0151] The display screen includes a screen, and the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from users. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can not only sense the boundaries of touch or swipe actions, but also detect the duration and pressure associated with the touch or swipe operations.

[0152] The audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC). When the device where the audio component is located is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive external audio signals. The received audio signals can be further stored in the memory or transmitted via the communication component. In some embodiments, the audio component further includes a speaker for outputting audio signals.

[0153] In the above-mentioned embodiments of the device, equipment, storage medium, and program product of the present disclosure, the first image corresponding to the first color space is subjected to color space conversion to obtain a second image corresponding to the second color space; the second image is denoised to obtain a third image after denoising; based on the second image, color restoration is performed on the third image to obtain a fourth image. Color restoration is performed on the third image based on the second image to reduce color loss caused by image denoising; the fourth image is subjected to a color space conversion operation to obtain a target image with higher image denoising quality corresponding to the first color space, thereby improving the image denoising quality.

[0154] Those skilled in the art will understand that the embodiments of the present disclosure may be provided as a method, a system, or a computer program product. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0155] The present disclosure is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices produce means for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0156] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0157] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are performed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0158] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0159] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0160] A computer-readable medium includes both permanent and non-permanent, removable and non-removable media and can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transitory media that can be used to store information that can be accessed by a computing device. As defined herein, a computer-readable medium does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0161] It should be noted that in this document, 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 actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0162] The above are only specific embodiments of the present disclosure, enabling those skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can 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 these embodiments herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. An image noise reduction method, characterized in that, Including: Performing a color space conversion on a first image corresponding to a first color space to obtain a second image corresponding to a second color space; Denosing the second image to obtain a denoised third image; Performing color restoration on the third image according to the second image to obtain a fourth image; Performing a color space conversion operation on the fourth image to obtain a target image corresponding to the first color space.

2. The method according to claim 1, characterized in that, The second image includes: first color channel data, and the third image includes: second color channel data. The first color channel data and the second color channel data are data of the same color channel of the second image and the third image. The performing color restoration on the third image according to the second image to obtain a fourth image includes: Performing a binarization operation on the first color channel data to obtain a binary image; Selecting a target connected component from the binary image; Performing connected component color extraction according to the target connected component, the first color channel data, and the second color channel data to obtain color information of the target connected component; Performing color restoration according to the color information of the target connected component and the second color channel data to obtain the fourth image.

3. The method according to claim 2, wherein The selecting a target connected component from the binary image includes: Performing connected component labeling on the binary image to obtain candidate connected components; Selecting a target connected component from the candidate connected components whose connected component parameters meet the set connected component parameter conditions.

4. The method according to claim 3, wherein The connected component parameters include at least one of the following: connected component area, connected component contour length, position of the circumscribed circle of the connected component, and radius of the circumscribed circle of the connected component.

5. The method according to claim 2, characterized in that, The performing connected component color extraction according to the target connected component, the first color channel data, and the second color channel data to obtain color information of the target connected component includes: Retaining the color information corresponding to the target connected component in the first color channel data; and Deleting the color information other than the target connected component in the first color channel data to obtain the color information of the target connected component.

6. The method according to claim 2, characterized in that The performing color restoration according to the color information of the target connected component and the second color channel data to obtain the fourth image includes: Superimposing the color information of the target connected component and the second color channel data to obtain the fourth image.

7. The method according to claim 6, wherein The superimposing the color information of the target connected component and the second color channel data to obtain the fourth image includes: Superimposing the color information of the target connected component and the second color channel data according to a first weight corresponding to the color information of the target connected component and a second weight corresponding to the second color channel data to obtain the fourth image.

8. An image noise reduction device, characterized in that, Including: A first conversion module for performing a color space conversion on a first image corresponding to a first color space to obtain a second image corresponding to a second color space; A denoising module for denosing the second image to obtain a denoised third image; A color restoration module for performing color restoration on the third image according to the second image to obtain a fourth image; A second conversion module for performing a color space conversion operation on the fourth image to obtain a target image corresponding to the first color space.

9. The device according to claim 8, characterized in that, The second image includes: first color channel data, and the third image includes: second color channel data. The first color channel data and the second color channel data are data of the same color channel of the second image and the third image. When the color restoration module performs color restoration on the third image according to the second image to obtain a fourth image, it is configured to: Perform a binarization operation on the first color channel data to obtain a binary image; Select a target connected component from the binary image; Perform connected component color extraction according to the target connected component, the first color channel data, and the second color channel data to obtain color information of the target connected component; Perform color restoration according to the color information of the target connected component and the second color channel data to obtain the fourth image.

10. The device according to claim 9, characterized in that When the color restoration module selects a target connected component from the binary image, it is configured to: Perform connected component labeling on the binary image to obtain candidate connected components; Select a target connected component from the candidate connected components whose connected component parameters meet the set connected component parameter conditions.

11. The device according to claim 10, characterized in that, The connected component parameters include at least one of the following: connected component area, connected component contour length, connected component circumcircle position, and connected component circumcircle radius.

12. The device according to claim 9, characterized in that, When the color restoration module performs connected component color extraction according to the target connected component, the first color channel data, and the second color channel data to obtain color information of the target connected component, it is configured to: Retain the color information corresponding to the target connected component in the first color channel data; and Delete the color information in the first color channel data other than the target connected component to obtain the color information of the target connected component.

13. The device according to claim 9, characterized in that, When the color restoration module performs color restoration according to the color information of the target connected component and the second color channel data to obtain the fourth image, it is configured to: Overlay the color information of the target connected component and the second color channel data to obtain the fourth image.

14. The device according to claim 13, characterized in that, When the color restoration module overlays the color information of the target connected component and the second color channel data to obtain the fourth image, it is configured to: Overlay the color information of the target connected component and the second color channel data according to a first weight corresponding to the color information of the target connected component and a second weight corresponding to the second color channel data to obtain the fourth image.

15. An electronic device, characterized in that, Includes: A processor; A memory for storing instructions executable by the processor; Wherein, the processor is configured to execute the instructions to implement the steps in the method according to any one of claims 1-7.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps in the method according to any one of claims 1-7.

17. A computer program product comprising computer programs / instructions, characterized in that, When the computer program / instructions are executed by the processor, it implements the steps in the method according to any one of claims 1-7.

Images