Image denoising method, device and equipment and computer readable storage medium

Abstract

This application discloses an image denoising method, apparatus, device, and computer-readable storage medium, belonging to the field of display technology. The image denoising method includes: upon receiving an original video signal, decoding the original video signal to obtain image frames; performing denoising processing on the image frames to obtain a denoised image; and generating a screen display image with bright lines and gray edges removed based on the denoised image. This application, by denoising the original video image, eliminates the need for overall image enlargement and cropping, achieving the removal of bright lines or gray edges while avoiding image quality degradation or content loss.

Description

Technical Field

[0001] This application relates to the field of display technology, and in particular to image denoising methods, apparatus, devices, and computer-readable storage media. Background Technology

[0002] When a television receives a video signal transmitted by a television station, and the television plays the original image directly, there may be bright lines flickering or dark gray edges around the edges of the image. This problem usually occurs because the video signal was affected by electronic signal interference or shooting techniques during production, resulting in uneven edge processing and thus bright lines or gray edges in the original video image.

[0003] Currently, the usual method to solve this problem is to first enlarge the original image, then crop the image by 5% on each side, and then display the remaining 95% of the image.

[0004] However, this solution results in a processed image of lower quality than the original image, and also causes loss of edge image content. Summary of the Invention

[0005] The main objective of this application is to provide an image denoising method, apparatus, device, and computer-readable storage medium, which aims to remove bright lines and gray edges from images while ensuring that the image quality is not degraded and the image content is not lost.

[0006] To achieve the above objectives, this application provides an image denoising method, which includes the following steps:

[0007] Upon receiving the original video signal, the original video signal is decoded to obtain image frames;

[0008] The image frame is denoised to obtain a denoised image;

[0009] A screen display image with bright lines and gray edges removed is generated based on the denoised image.

[0010] Optionally, the step of denoising the image frame to obtain a denoised image includes:

[0011] The image frame is subjected to edge smoothing processing to obtain a smooth image;

[0012] Edge interpolation is performed on the smoothed image to obtain a denoised image.

[0013] Optionally, the step of performing edge smoothing processing on the image frame to obtain a smoothed image includes:

[0014] The boundary noise range of the image frame is determined according to the first preset noise reduction standard;

[0015] Smooth all pixels within the boundary noise range of the image frame to obtain a smooth image.

[0016] Optionally, the step of smoothing all pixels within the boundary noise range of the image frame to obtain a smoothed image includes:

[0017] A Gaussian filter is used to perform convolution calculations on all pixels within the boundary noise range of the image frame to remove noise and obtain a smooth image.

[0018] Optionally, the step of performing edge interpolation on the smoothed image to obtain a denoised image includes:

[0019] The boundary image of the smoothed image is determined according to the second preset denoising standard;

[0020] The boundary image is magnified and interpolated to obtain an interpolated image;

[0021] The interpolated image is used to replace the boundary image in the smoothed image to obtain a denoised image.

[0022] Optionally, the step of magnifying and interpolating the boundary image to obtain an interpolated image includes:

[0023] The boundary image is magnified to obtain a magnified image;

[0024] Interpolated pixel values ​​are added to the blank pixel positions in the magnified image to obtain an interpolated image.

[0025] Optionally, the step of adding interpolated pixel values ​​at the blank pixel positions in the magnified image includes:

[0026] Interpolated pixel values ​​are generated based on the neighboring pixel values ​​of the blank pixel positions in the magnified image;

[0027] The interpolated pixel value is added to the blank pixel position.

[0028] Furthermore, to achieve the above objectives, this application also provides an image denoising apparatus, the image denoising apparatus comprising:

[0029] A decoding module is used to decode the original video signal to obtain image frames when the original video signal is received.

[0030] A denoising module is used to perform denoising processing on the image frame to obtain a denoised image;

[0031] A generation module is used to generate a screen display image with bright lines and gray edges removed based on the denoised image.

[0032] In addition, to achieve the above objectives, this application also provides a display device, the display device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the image denoising method as described above.

[0033] In addition, to achieve the above objectives, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the image denoising method described above.

[0034] This application proposes an image denoising method, apparatus, device, and computer-readable storage medium, overcoming the technical shortcomings of existing technologies that lead to image quality degradation and image content loss when removing bright lines or gray edges from video images. In the image denoising method, when a display device receives an original video signal, it first decodes the original video signal to obtain image frames; then, it performs denoising processing on the image frames to obtain a denoised image; finally, it generates a screen display image with bright lines and gray edges removed based on the denoised image. This application, by denoising the original video image, eliminates the need for overall image enlargement and cropping, thus achieving the removal of bright lines or gray edges while avoiding image quality degradation or image content loss. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only a part of the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a schematic flowchart of an image denoising method provided in an embodiment of this application;

[0037] Figure 2 A schematic diagram illustrating the parameter settings of a Gaussian convolution kernel involved in an image denoising method provided in an embodiment of this application;

[0038] Figure 3 This is a schematic diagram illustrating the principle of calculating interpolated pixel values ​​in an image denoising method provided in an embodiment of this application.

[0039] Figure 4 This is a schematic diagram of the structure of an image denoising device provided in an embodiment of this application;

[0040] Figure 5 This is a schematic diagram of the hardware structure of a display device provided in an embodiment of this application. Detailed Implementation

[0041] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that the embodiments of this application can also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the embodiments of this application with unnecessary detail.

[0042] It should be noted that although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0043] It should also be understood that references to "one embodiment" or "some embodiments" in the specification of embodiments of this application mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0044] When a television receives a video signal transmitted by a television station, and the television plays the original image directly, there may be bright lines flickering or dark gray edges around the edges of the image. This problem usually occurs because the video signal was affected by electronic signal interference or shooting techniques during production, resulting in uneven edge processing and thus bright lines or gray edges in the original video image.

[0045] Currently, the usual method to solve this problem is to first enlarge the original image, then crop the image by 5% on each side, and then display the remaining 95% of the image.

[0046] However, this solution results in a processed image of lower quality than the original image, and also causes loss of edge image content.

[0047] Based on this, embodiments of this application provide an image denoising method, apparatus, device, and computer-readable storage medium, overcoming the technical defects of existing technologies that lead to image quality degradation and image content loss when removing bright lines or gray edges from video images. In the image denoising method, when a display device receives an original video signal, it first decodes the original video signal to obtain image frames; then, it performs denoising processing on the image frames to obtain a denoised image; and finally, it generates a screen display image with bright lines and gray edges removed based on the denoised image. This application, by performing denoising processing on the original video image, eliminates the need for overall image enlargement and cropping, thus achieving the removal of bright lines or gray edges while avoiding image quality degradation or image content loss.

[0048] The image denoising method, apparatus, device, and computer-readable storage medium provided in this application are specifically described through the following embodiments. First, the image denoising method in this application is described.

[0049] This application provides an image denoising method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating an image denoising method according to an embodiment of this application. This image denoising method can be applied to display devices, such as... Figure 1 As shown, the image denoising method provided in this embodiment includes steps S10 to S30.

[0050] Step S10: Upon receiving the original video signal, decode the original video signal to obtain image frames;

[0051] It should be noted that the execution subject in this embodiment is a display device, which is capable of receiving raw video signals transmitted from an external video source. The display device has a decoder that can decode the received raw video signals to obtain image frames.

[0052] For example, the external video source could be a television station.

[0053] Step S20: Denoise the image frame to obtain a denoised image;

[0054] It should be noted that in this embodiment, the original video image is not directly enlarged and cropped. Instead, the image frames obtained by decoding the original video signal are denoised to eliminate the noise in the original image. This avoids bright lines or gray edges caused by the continuous change of noise during the continuous refresh of the image on the display device. The image frames with the noise eliminated are combined to form the denoised image.

[0055] In some feasible embodiments, step S20 may specifically include:

[0056] Step S21: Perform edge smoothing processing on the image frame to obtain a smooth image;

[0057] It should be noted that the denoising process in this embodiment includes edge smoothing, which is used to reduce edge noise in the image frame. The edge refers to the top, bottom, left, and right sides of the image frame. This is because the root cause of bright lines or gray edges around the image is that there is a lot of noise around the image, which causes the image to display bright lines and gray edges when refreshed quickly. The first step in solving this problem is to remove the noise. Once the noise is removed, the edge smoothing process is considered to be complete, and the image frame with the noise removed is considered to be a smooth image.

[0058] For example, this embodiment can remove noise using a median filter or a Gaussian filter.

[0059] Step S22: Perform edge interpolation processing on the smoothed image to obtain a denoised image.

[0060] It should be noted that the denoising process in this embodiment includes edge interpolation. After the image frame is cleaned by edge smoothing, the edges of the smoothed image will contain some missing pixels due to the removal of noise. Therefore, this embodiment performs interpolation on the edges of the smoothed image to supplement the missing image content, further improving the smoothed image and obtaining a denoised image with more complete image content.

[0061] For example, in this embodiment, the estimated value can be calculated by performing an estimation on the neighboring pixels of the missing content pixel to obtain the pixel value used to interpolate the position of the missing content pixel.

[0062] In some feasible embodiments, step S21 may specifically include:

[0063] Step S211: Determine the boundary noise range of the image frame according to the first preset noise reduction standard;

[0064] It should be noted that the first preset noise reduction standard can be set according to the actual situation. For example, if it is believed that there are noise points in the image content around the perimeter of the image frame, then the boundary noise range is the image content around the perimeter of the image frame.

[0065] Step S212: Smooth all pixels contained in the boundary noise range of the image frame to obtain a smooth image.

[0066] Understandably, once it is determined that there is noise in 5% of the image content around the perimeter of the image frame, it is necessary to smooth that 5% of the image content around the perimeter.

[0067] In some feasible embodiments, step S212 may specifically include:

[0068] Step A: Perform convolution calculation on all pixels contained in the boundary noise range of the image frame using a Gaussian filter to remove noise and obtain a smooth image.

[0069] For example, in this embodiment, Gaussian filter denoising is used as an example for illustration, which can be combined with Figure 2 To understand, Figure 2 This describes a 3x3 Gaussian convolution kernel parameter setting, with values ​​from left to right and top to bottom as follows: 0.057, 0.125, 0.057, 0.125, 0.272, 0.125, 0.057, 0.125, 0.057. This 3x3 Gaussian convolution kernel performs a 3x3 convolution on the pixels requiring smoothing, calculates new pixel values, and replaces the original pixel value with the new value, thus completing the noise removal process.

[0070] In some feasible embodiments, step S22 may specifically include:

[0071] Step S221: Determine the boundary image of the smoothed image according to the second preset denoising standard;

[0072] It should be noted that the second preset noise reduction standard can be set according to the actual situation. For example, if it is believed that there are missing pixels in the image content of 10% around the smooth image, then the boundary image is the image content of 10% around the smooth image.

[0073] Step S222: Enlarge the boundary image and perform interpolation to obtain an interpolated image;

[0074] It should be noted that after determining the boundary image that needs interpolation, this part of the boundary image can be extracted separately from the smoothed image and enlarged. After enlargement, it will be found that some pixels in the enlarged boundary image are missing image content. Therefore, it is necessary to calculate new pixel values ​​based on the content of the surrounding pixels to fill in the missing pixels. Once all the missing pixels in the enlarged boundary image have been filled in, the interpolated image is obtained.

[0075] Step S223: Replace the boundary image in the smoothed image with the interpolated image to obtain a denoised image.

[0076] It should be understood that the interpolated image is a local image obtained by enlarging and interpolating the boundary image in the original smooth image. Therefore, it needs to be reduced to the same size as the original boundary image before replacing the original boundary image in the smooth image to obtain the denoised image.

[0077] In some feasible embodiments, step S222 may specifically include:

[0078] Step X: Enlarge the boundary image to obtain an enlarged image;

[0079] It is understandable that to supplement the missing image content in the boundary image, the boundary image needs to be enlarged first. For example, if the original size of the boundary image is 100*20, then the enlarged size can be 200*40. The specific magnification factor and magnification method are not limited in this embodiment.

[0080] Step Y involves adding interpolated pixel values ​​to the blank pixel positions in the magnified image to obtain an interpolated image.

[0081] In this embodiment, after the boundary image is magnified, it can be found that there are some pixels with actual content in the magnified image. Therefore, it is necessary to calculate a new pixel value based on the content of the original pixels adjacent to the pixel to fill the pixel. When all pixels are filled, the interpolated image can be obtained.

[0082] In some feasible embodiments, step Y, which involves adding interpolated pixel values ​​at the blank pixel positions in the magnified image, may specifically include:

[0083] Step Y1: Generate interpolated pixel values ​​based on the neighboring pixel values ​​of the blank pixel positions in the magnified image;

[0084] Step Y2: Add the interpolated pixel value to the blank pixel position.

[0085] For example, this embodiment can be combined with Figure 3 To understand, Figure 3 This is a schematic diagram illustrating the principle of calculating interpolated pixel values ​​in this embodiment; Figure 3The horizontal and vertical coordinate systems in the image represent a portion of the magnified image. The horizontal coordinates include x1, x, and x2, and the vertical coordinates include y1, y, and y2. Q11 corresponds to coordinates (x1, y1), Q12 corresponds to coordinates (x1, y2), R1 corresponds to coordinates (x, y1), P corresponds to coordinates (x, y), R2 corresponds to coordinates (x, y2), Q21 corresponds to coordinates (x2, y1), and Q22 corresponds to coordinates (x2, y2). Point P represents the location of a blank pixel in the magnified image, and its adjacent pixels are Q11, Q12, Q21, and Q22. 2. Assuming that a new pixel value needs to be inserted at point P after magnification, firstly, calculate R2 using the values ​​of Q12 and Q22. The method for calculating R2 is to determine the percentage sum of Q12 and Q22 based on the distance between R2 and Q12 and Q22. Then, calculate R1 using a similar method. Finally, calculate the pixel value at point P based on the values ​​of R1 and R2. In this way, it can be ensured that the pixel value at point P is calculated based on the original pixel values ​​of the four adjacent points Q11, Q12, Q21 and Q22, with almost no noise.

[0086] Step S30: Generate a screen display image with bright lines and gray edges removed based on the denoised image.

[0087] It should be understood that a denoised image is an image that has undergone noise reduction and pixel compensation. After obtaining the denoised image, the display device can directly send the denoised image to the display screen for display. At this time, the image displayed on the screen is the original video signal image with bright lines and gray edges removed.

[0088] This embodiment provides an image denoising method. Considering that bright lines and gray edges around the image are caused by excessive noise, and the continuous refresh of the image causes the image and noise to change continuously, resulting in the appearance of bright lines or gray edges, this embodiment performs noise reduction processing on the image edges to solve this problem. Then, the image content of the neighboring area is followed up and filled at the image edges, and finally a noise-free edge image is obtained, thereby reducing the bright lines and gray edges in the original image.

[0089] This embodiment overcomes the technical shortcomings of existing technologies that lead to image quality degradation and content loss when removing bright lines or gray edges from video images. When the display device receives the original video signal, it first decodes the original video signal to obtain image frames; then, it performs denoising processing on the image frames to obtain denoised images; finally, it generates a screen display image with bright lines and gray edges removed based on the denoised image. This embodiment, by denoising the original video image, eliminates the need for overall image enlargement and cropping. While removing bright lines or gray edges from the image, it avoids image quality degradation or content loss, ensuring the integrity of the image information transmitted by the original video image and effectively improving the user's viewing experience.

[0090] In addition, in another embodiment, an image denoising method is provided, which covers the boundaries of the original video image with pixels. Multiple pixels that can form an overall pattern or decorative strip are used to cover the four sides of the original video image. This can solve the problem of bright lines or gray edges around the original video image and make the screen image more beautiful.

[0091] Furthermore, embodiments of this application also propose an image denoising apparatus, referring to... Figure 4 , Figure 4 This is a schematic diagram of the structure of an image denoising device provided in an embodiment of this application, as shown below. Figure 4 As shown, in this embodiment, the image denoising device includes: a decoding module 100, a denoising module 200, and a generation module 300.

[0092] Decoding module 100 is used to decode the original video signal to obtain image frames when the original video signal is received.

[0093] A denoising module 200 is used to perform denoising processing on the image frame to obtain a denoised image;

[0094] The generation module 300 is used to generate a screen display image with bright lines and gray edges removed based on the denoised image.

[0095] In some feasible embodiments, the denoising module 200 is further configured to perform edge smoothing processing on the image frame to obtain a smooth image;

[0096] Edge interpolation is performed on the smoothed image to obtain a denoised image.

[0097] In some feasible embodiments, the denoising module 200 is further configured to determine the boundary noise range of the image frame according to a first preset denoising standard;

[0098] Smooth all pixels within the boundary noise range of the image frame to obtain a smooth image.

[0099] In some feasible embodiments, the denoising module 200 is further configured to perform convolution calculations on all pixels contained in the boundary noise range of the image frame using a Gaussian filter to remove noise and obtain a smooth image.

[0100] In some feasible embodiments, the denoising module 200 is further configured to determine the boundary image of the smoothed image according to a second preset denoising standard;

[0101] The boundary image is magnified and interpolated to obtain an interpolated image;

[0102] The interpolated image is used to replace the boundary image in the smoothed image to obtain a denoised image.

[0103] In some feasible embodiments, the denoising module 200 is further configured to enlarge the boundary image to obtain an enlarged image;

[0104] Interpolated pixel values ​​are added to the blank pixel positions in the magnified image to obtain an interpolated image.

[0105] In some feasible embodiments, the denoising module 200 is further configured to generate interpolated pixel values ​​based on the neighboring pixel values ​​of the blank pixel positions in the magnified image;

[0106] The interpolated pixel value is added to the blank pixel position.

[0107] The image denoising device provided in this embodiment belongs to the same inventive concept as the image denoising method provided in the above embodiments. Technical details not described in detail in this embodiment can be found in any of the above embodiments. Furthermore, this embodiment has the same beneficial effects as performing the image denoising method.

[0108] Furthermore, this application embodiment also provides a display device. The image denoising method applied to the display device described above can be executed by an image denoising device, which can be implemented by software and / or hardware and integrated into the display device. The display device can be a television, PC (Personal Computer), laptop, tablet computer, or other display device containing a display screen, etc., with decoding capabilities.

[0109] Reference Figure 5 , Figure 5 This is a schematic diagram of the hardware structure of a display device provided in one embodiment of this application. Figure 5As shown, the display device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk storage device. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0110] Those skilled in the art will understand that Figure 5 The structure shown does not constitute a limitation on the display device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0111] like Figure 5 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and computer programs.

[0112] exist Figure 5 In the display device shown, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and memory 1005 in this embodiment can be located in the display device, and the display device calls the computer program stored in the memory 1005 through the processor 1001 and performs the following operations:

[0113] Upon receiving the original video signal, the original video signal is decoded to obtain image frames;

[0114] The image frame is denoised to obtain a denoised image;

[0115] A screen display image with bright lines and gray edges removed is generated based on the denoised image.

[0116] Furthermore, the processor 1001 can call a computer program stored in the memory 1005 and also perform the following operations:

[0117] The image frame is subjected to edge smoothing processing to obtain a smooth image;

[0118] Edge interpolation is performed on the smoothed image to obtain a denoised image.

[0119] Furthermore, the processor 1001 can call a computer program stored in the memory 1005 and also perform the following operations:

[0120] The boundary noise range of the image frame is determined according to the first preset noise reduction standard;

[0121] Smooth all pixels within the boundary noise range of the image frame to obtain a smooth image.

[0122] Furthermore, the processor 1001 can call a computer program stored in the memory 1005 and also perform the following operations:

[0123] A Gaussian filter is used to perform convolution calculations on all pixels within the boundary noise range of the image frame to remove noise and obtain a smooth image.

[0124] Furthermore, the processor 1001 can call a computer program stored in the memory 1005 and also perform the following operations:

[0125] The boundary image of the smoothed image is determined according to the second preset denoising standard;

[0126] The boundary image is magnified and interpolated to obtain an interpolated image;

[0127] The interpolated image is used to replace the boundary image in the smoothed image to obtain a denoised image.

[0128] Furthermore, the processor 1001 can call a computer program stored in the memory 1005 and also perform the following operations:

[0129] The boundary image is magnified to obtain a magnified image;

[0130] Interpolated pixel values ​​are added to the blank pixel positions in the magnified image to obtain an interpolated image.

[0131] Furthermore, the processor 1001 can call a computer program stored in the memory 1005 and also perform the following operations:

[0132] Interpolated pixel values ​​are generated based on the neighboring pixel values ​​of the blank pixel positions in the magnified image;

[0133] The interpolated pixel value is added to the blank pixel position.

[0134] The display device proposed in this embodiment and the image denoising method for display devices proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in any of the above embodiments. Furthermore, this embodiment has the same beneficial effects as the image denoising method.

[0135] Furthermore, embodiments of this application also propose a computer-readable storage medium for use in a computer. The computer-readable storage medium may be a non-volatile computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the image denoising method of any of the embodiments described above.

[0136] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0137] The above is a detailed description of the preferred embodiments of this application. However, the embodiments of this application are not limited to the above-described implementation methods. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the embodiments of this application. All such equivalent modifications or substitutions are included within the scope defined by the claims of the embodiments of this application.

Claims

1. An image denoising method, characterized in that, The image denoising method includes the following steps: Upon receiving the original video signal, the original video signal is decoded to obtain image frames; The image frame is subjected to edge smoothing processing to obtain a smooth image, wherein the edge smoothing processing is used to remove noise at the edges of the image frame; If there are missing pixels in the image content around the first preset percentage of the smoothed image, the boundary image of the smoothed image is determined as the image content around the first preset percentage of the smoothed image. The boundary image is magnified and interpolated to obtain an interpolated image; The interpolated image is used to replace the boundary image in the smoothed image to obtain a denoised image, in order to compensate for the image content lost due to the removal of the noise. A screen display image is generated based on the denoised image, which has removed bright lines and gray edges caused by the continuous changes in the noise.

2. The image denoising method of claim 1, wherein, The step of performing edge smoothing processing on the image frame to obtain a smoothed image includes: If there is noise in the image content around the second preset percentage of the image frame, the boundary noise range of the image frame is determined as the image content around the second preset percentage of the image frame. Smooth all pixels within the boundary noise range of the image frame to obtain a smooth image.

3. The image denoising method of claim 2, wherein, The step of smoothing all pixels within the boundary noise range of the image frame to obtain a smoothed image includes: A Gaussian filter is used to perform convolution calculations on all pixels within the boundary noise range of the image frame to remove noise and obtain a smooth image.

4. The image denoising method of claim 1, wherein, The step of magnifying and interpolating the boundary image to obtain an interpolated image includes: The boundary image is magnified to obtain a magnified image; Interpolated pixel values ​​are added to the blank pixel positions in the magnified image to obtain an interpolated image.

5. The image denoising method of claim 4, wherein, The step of adding interpolated pixel values ​​at the blank pixel positions in the magnified image includes: Interpolated pixel values ​​are generated based on the neighboring pixel values ​​of the blank pixel positions in the magnified image; The interpolated pixel value is added to the blank pixel position.

6. An image denoising apparatus characterized by comprising: The image denoising device includes: A decoding module is used to decode the original video signal to obtain image frames when the original video signal is received. A denoising module is used to perform edge smoothing processing on the image frame to obtain a smooth image, wherein the edge smoothing processing is used to remove noise at the edges of the image frame; when there are pixel missing pixels in the image content around the smooth image at a first preset percentage, the boundary image of the smooth image is determined as the image content around the smooth image at the first preset percentage; the boundary image is enlarged and interpolated to obtain an interpolated image; the interpolated image replaces the boundary image in the smooth image to obtain a denoised image, in order to compensate for the image content missing due to the removal of noise; A generation module is used to generate a screen display image based on the denoised image, in which bright lines and gray edges have been removed due to the continuous changes in noise.

7. A display device, characterized by The display device comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program, when executed by the processor, implements the steps of the image denoising method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer program is stored on the computer readable storage medium and, when executed by the processor, implements the steps of the image denoising method according to any one of claims 1 to 5.

Images