Image processing method and device, storage medium and electronic device

Abstract

Embodiments of the present application provide an image processing method and device, a storage medium and an electronic device, the method comprising: determining a noise reduction amount for noise reduction processing of a to-be-processed image according to each noise reduction strength in N noise reduction strengths, and determining N noise reduction amounts, wherein N is a natural number greater than or equal to 1; determining a target noise reduction interval based on the N noise reduction amounts, wherein the target noise reduction interval includes noise reduction amounts within a preset range; and performing noise reduction processing on the to-be-processed image according to the target noise reduction interval to obtain a target image. Through the present application, the problem of image denoising in related technologies is solved, effectively removing noise and ensuring image clarity.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of image processing, and more specifically, to an image processing method and apparatus, a storage medium, and an electronic device. Background Technology

[0002] Images have a wide range of applications, including biomedicine, military, transportation security, and machine vision. Image quality directly affects the effectiveness of these applications. However, images are inevitably affected by noise during acquisition, processing, and transmission. Therefore, filtering noise from images is of paramount importance.

[0003] Existing image denoising methods often suffer from incomplete noise removal or blurred signal. Summary of the Invention

[0004] This invention provides an image processing method, apparatus, storage medium, and electronic device to at least solve the problem of image denoising in related technologies.

[0005] According to an embodiment of the present invention, an image processing method is provided, comprising: determining a noise reduction amount for denoising an image to be processed according to each of N noise reduction intensities, and determining N noise reduction amounts, wherein N is a natural number greater than or equal to 1; determining a target noise reduction interval based on the N noise reduction amounts, wherein the target noise reduction interval includes noise reduction amounts within a preset range; and performing noise reduction processing on the image to be processed according to the target noise reduction interval to obtain a target image.

[0006] According to another embodiment of the present invention, an image processing apparatus is provided, comprising: a first determining module, configured to determine a noise reduction amount for denoising an image to be processed according to each of N noise reduction intensities, and to determine N noise reduction amounts, wherein N is a natural number greater than or equal to 1; a second determining module, configured to determine a target noise reduction interval based on the N noise reduction amounts, wherein the target noise reduction interval includes noise reduction amounts within a preset range; and a first processing module, configured to perform noise reduction processing on the image to be processed according to the target noise reduction interval to obtain a target image.

[0007] In an exemplary embodiment, the first determining module includes: a first determining unit, configured to determine the weight value of each noise reduction intensity in each pixel of the image to be processed; a first processing unit, configured to perform noise reduction processing on each pixel using the weight value of each noise reduction intensity in each pixel of the image to be processed, to obtain each pixel after noise reduction; and a determining unit, configured to determine the N noise reduction amounts based on each pixel after noise reduction.

[0008] In an exemplary embodiment, the first determining module includes: a second determining unit, configured to determine pixels in the image to be processed that are in a preset frequency band; a third determining unit, configured to perform denoising processing on the pixels in the preset frequency band according to each denoising intensity, and determine the amount of change of the pixels in the preset frequency band; and a second processing unit, configured to determine N denoising amounts using the amount of change of the pixels in the preset frequency band.

[0009] In an exemplary embodiment, the second determining module includes: a first dividing unit, configured to divide the N noise reduction values ​​into M noise reduction intervals according to a preset order, wherein M is a natural number greater than or equal to 1; and a fourth determining unit, configured to determine the noise reduction interval that matches the preset noise reduction value among the M noise reduction intervals as the target noise reduction interval.

[0010] In an exemplary embodiment, the first processing module includes a first noise reduction unit, configured to perform noise reduction processing on each corresponding pixel in the image to be processed using the noise reduction amount in the target noise reduction interval and a preset noise reduction value to obtain the target image, wherein the preset noise reduction value is used to perform noise reduction on each corresponding pixel.

[0011] In an exemplary embodiment, the first noise reduction unit includes: a first determining subunit, configured to determine the difference between the preset noise reduction value and the noise reduction amount in the target noise reduction interval; a first conversion subunit, configured to convert the difference into a weight value using a preset function; and a first noise reduction subunit, configured to perform noise reduction processing on each corresponding pixel in the image to be processed based on the weight value to obtain the target image.

[0012] In one exemplary embodiment, the apparatus further includes one of the following: a first splitting module, configured to split the image to be processed into a single-channel image when the image to be processed includes a multi-channel image; and a first conversion module, configured to convert the image to be processed into an image including a luminance channel and a color channel when the image to be processed includes a multi-channel image.

[0013] According to yet another embodiment of the present invention, a computer-readable storage medium is also provided, wherein a computer program is stored therein, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.

[0014] According to yet another embodiment of the present invention, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0015] This invention determines a target noise reduction interval by defining N noise reduction amounts, where the target noise reduction interval includes noise reduction amounts within a preset range. Noise reduction processing is then performed on the image to be processed according to the target noise reduction interval to obtain the target image. This allows for the use of multiple noise reduction intensities to perform noise reduction processing on images. It solves the problem of image denoising in related technologies, achieving effective noise removal while maintaining image clarity. Attached Figure Description

[0016] Figure 1 This is a hardware structure block diagram of a mobile terminal for an image processing method according to an embodiment of the present invention.

[0017] Figure 2 This is a flowchart of an image processing method according to an embodiment of the present invention;

[0018] Figure 3 This is a flowchart based on a specific embodiment of the present invention;

[0019] Figure 4 This is a structural block diagram of an image processing apparatus according to an embodiment of the present invention;

[0020] Figure 5 This is a schematic diagram of the noise reduction range according to an embodiment of the present invention. Detailed Implementation

[0021] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings and examples.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0023] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for an image processing method according to an embodiment of the present invention. For example... Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0024] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the image processing method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0025] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0026] This embodiment provides an image processing method. Figure 2 This is a flowchart of an image processing method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0027] Step S202: Determine the noise reduction amount for each of the N noise reduction intensities to be processed on the image to be processed, and determine the N noise reduction amounts, where N is a natural number greater than or equal to 1.

[0028] In this embodiment, the image to be processed includes, but is not limited to, single-channel and multi-channel images. For example, RGB images with three primary colors, multispectral images, etc.

[0029] The N noise reduction values ​​can be determined by applying N noise reduction methods to the image to be processed. These methods include, but are not limited to, spatial domain image noise reduction, frequency domain image noise reduction, hybrid spatial and frequency domain image noise reduction, and learning-based image noise reduction. The N noise reduction intensities are arranged in ascending order, for example, noise reduction intensity 1 < noise reduction intensity 2 < ... < noise reduction intensity N. Here, the noise reduction value represents the intensity of noise removal for a single pixel.

[0030] Step S204: Determine the target noise reduction range based on N noise reduction amounts, wherein the target noise reduction range includes noise reduction amounts within a preset range;

[0031] In this embodiment, the stronger the noise reduction intensity, the greater the noise reduction amount; therefore, the order of noise reduction intensity is consistent with the noise reduction amount. The target noise reduction range can be determined based on a preset noise reduction amount value, satisfying noise reduction amount x < noise reduction value < noise reduction amount x+1. Noise reduction amount x and noise reduction amount x+1 are the noise reduction amounts corresponding to two adjacent noise reduction intensities. For example, as... Figure 5 As shown, the noise reduction range is 0, which is less than the noise reduction amount 1; the range between the noise reduction amount 1 and the noise reduction amount 2 is the noise reduction range 1; and so on. The range is N, which is greater than the noise reduction amount N.

[0032] Step S206: Denoise the image to be processed according to the target denoising range to obtain the target image.

[0033] The entity performing the above steps may be a terminal, a server, a specific processor set in the terminal or server, or a processor or processing device set up relatively independently of the terminal or server, but is not limited to these.

[0034] Through the above steps, a target denoising interval is determined by N denoising amounts, which includes denoising amounts within a preset range. The image to be processed is then denoised according to the target denoising interval to obtain the target image. This method achieves the goal of denoising images using denoising amounts determined by multiple denoising intensities. It can solve the problem of image denoising in related technologies, effectively removing noise while maintaining image clarity.

[0035] In one exemplary embodiment, determining the noise reduction amount for denoising the image to be processed according to each of N noise reduction intensities, and determining the N noise reduction amounts includes:

[0036] S11, Determine the weight value of each noise reduction intensity for each pixel in the image to be processed;

[0037] S12, using the weight value of each noise reduction intensity in each pixel of the image to be processed, perform noise reduction on each pixel to obtain each pixel after noise reduction;

[0038] S13, determine N noise reduction amounts based on each pixel after noise reduction.

[0039] In this embodiment, after calculating the weight value of each noise reduction intensity at each pixel, the most suitable noise reduction intensity for each pixel is determined, and noise reduction is performed accordingly. This allows for accurate determination of the noise reduction amount for each pixel.

[0040] In one exemplary embodiment, determining the noise reduction amount for denoising the image to be processed according to each of N noise reduction intensities, and determining the N noise reduction amounts includes:

[0041] S21, Determine the pixels in the image to be processed that are in the preset frequency band;

[0042] S22, perform noise reduction processing on the pixels of the preset frequency band according to each noise reduction intensity, and determine the amount of change of the pixels of the preset frequency band;

[0043] S23, determine N noise reduction values ​​by using the change in pixel values ​​in the preset frequency band.

[0044] In this embodiment, the noise reduction method corresponding to the noise reduction intensity can be either frequency domain noise reduction or spatial domain noise reduction. For example, frequency domain noise reduction can decompose the image to be processed into various frequency bands. The pixels corresponding to the high-frequency bands are then identified. Noise reduction is then applied to the pixels in the high-frequency bands. For example, the noise reduction amount for each pixel can be calculated by statistically analyzing the reduction in high-frequency values.

[0045] In one exemplary embodiment, determining the target noise reduction range based on N noise reduction values ​​includes:

[0046] S31, divide the N noise reduction values ​​into M noise reduction intervals according to a preset order, where M is a natural number greater than or equal to 1;

[0047] S32, determine the noise reduction interval that matches the preset noise reduction value among the M noise reduction intervals as the target noise reduction interval.

[0048] In this embodiment, the noise reduction interval can be determined according to a preset noise reduction value. For example, the interval less than the noise reduction value 1 is the noise reduction interval 0, the interval between the noise reduction value 1 and the noise reduction value 2 is the noise reduction interval 1, and so on, while the interval greater than the noise reduction value N is the noise reduction interval N.

[0049] In one exemplary embodiment, the image to be processed is denoised using a target denoising region to obtain a target image, including:

[0050] S41, using the noise reduction amount in the target noise reduction range and the preset noise reduction value to perform noise reduction processing on each corresponding pixel in the image to be processed, to obtain the target image, wherein the preset noise reduction value is used to perform noise reduction on each corresponding pixel.

[0051] In this embodiment, the preset noise reduction value can satisfy: noise reduction x < preset noise reduction value < noise reduction x+1, where noise reduction x and noise reduction x+1 are the noise reduction values ​​corresponding to two adjacent noise reduction intensities.

[0052] In one exemplary embodiment, the noise reduction process is performed on each pixel in the image to be processed using the noise reduction amount in the target noise reduction interval and a preset noise reduction value to obtain the target image, including:

[0053] S51, determine the difference between the preset noise reduction value and the noise reduction amount in the target noise reduction range;

[0054] S52, use a preset function to convert the difference into a weight value;

[0055] S53, based on the weight value, performs noise reduction processing on each corresponding pixel in the image to be processed to obtain the target image.

[0056] In this embodiment, the difference between the preset noise reduction value and the noise reduction value corresponding to the noise reduction intensity can be fused. The difference between the preset noise reduction value and the noise reduction value corresponding to the noise reduction intensity is converted into a weight value.

[0057] In one exemplary embodiment, the method further includes one of the following:

[0058] S61, if the image to be processed includes a multi-channel image, split the image to be processed into a single-channel image;

[0059] S62, if the image to be processed includes a multi-channel image, convert the image to be processed into an image including a luminance channel and a color channel.

[0060] In this embodiment, the noise reduction method for grayscale images can be applied separately to each channel of a color image or each channel of a multi-channel image. Alternatively, all three channels of a color image or each channel of a multi-channel image can be processed together. Or, it can be converted to a luma and chroma multi-channel image for simultaneous processing. After conversion to luma and chroma multi-channel, the noise reduction intensity of the luma and chroma channels can be set separately. This allows for more effective filtering of color noise while preserving noise reduction details.

[0061] The present invention will now be described in conjunction with specific embodiments:

[0062] This embodiment uses the noise reduction amount generated by various noise reduction methods to perform noise reduction processing on the image. These various noise reduction methods include:

[0063] Spatial domain image denoising methods include algorithms such as mean filtering, Gaussian filtering, and median filtering.

[0064] Frequency domain image denoising methods include wavelet denoising algorithms and Discrete Cosine Transform (DCT). These algorithms determine the frequency domain of the image transformation and then perform denoising on the image in the frequency domain.

[0065] Image denoising methods that combine spatial and frequency domains mainly include algorithms such as Block Matching 3D (BM3D) and Weighted Nuclear Norm Minimization (WNNM). These algorithms combine spatial and frequency domain denoising of images to improve the denoising capability of images.

[0066] Image denoising methods based on learning, including deep learning and dictionary learning-based denoising algorithms.

[0067] In this embodiment, as Figure 3 As shown, region-based noise reduction of an image includes the following steps:

[0068] S301, Denoise the image at different intensities and count the amount of noise reduction;

[0069] S302, obtains the optimal noise reduction range based on the amount of noise reduction;

[0070] S303 performs zone noise reduction.

[0071] The image denoising method described in this embodiment is applicable to grayscale images, color images, and any other multi-channel images, such as RGB images, multispectral images, etc.

[0072] For example, when the image is a multi-channel image, the noise reduction method for grayscale images can be applied separately to each channel of the color image or each channel of the multi-channel image. Alternatively, all three channels of the color image or each channel of the multi-channel image can be processed together, or the image can be converted to a luma / chroma multi-channel image for simultaneous processing. After conversion to luma / chroma multi-channel, the noise reduction intensity for the luma and chroma channels can be set separately. This preserves detail while more effectively filtering out color noise.

[0073] The detailed steps of this embodiment include:

[0074] S401 performs noise reduction at different intensities and calculates the noise reduction amount:

[0075] This embodiment applies to all existing spatial and frequency domain denoising algorithms, as well as two combined denoising algorithms, and is not specific to any particular denoising algorithm. The denoising intensities are sorted in ascending order, for example, denoising intensity 1 < denoising intensity 2 < ... < denoising intensity N.

[0076] In this embodiment, the noise reduction statistics of the spatial domain noise reduction algorithm include the following:

[0077] Spatial domain denoising algorithms set a denoising intensity, then calculate the weights within the neighborhood of that intensity, and finally perform a weighted average of the pixels using these weights to obtain the denoised signal. Methods for calculating these weights include: ;or, ;or, ,in, This is used to represent configuration parameters, which can be configured. The Diff is calculated from the difference between image patches or the difference between pixels. The more similar the pixels are, the smaller the Diff and the larger the weight.

[0078] For example, weight ,or, .

[0079] The method for calculating the noise reduction amount derived in this embodiment can include the following formula: .

[0080] In this embodiment, the noise reduction statistics of the frequency domain noise reduction algorithm include the following:

[0081] Frequency domain denoising algorithms process the high frequencies of an image. Here, the reduction in high frequencies is calculated to determine the amount of denoising.

[0082] In this embodiment, a frequency domain noise reduction algorithm is used. First, the image is decomposed into various frequency bands, where high frequency is represented as: .

[0083] After noise reduction using frequency domain denoising, the high frequencies become: High-frequency changes include: The noise reduction amount can be expressed as: .

[0084] In this embodiment, a noise reduction algorithm combining spatial and frequency domains is used:

[0085] These algorithms employ spatial domain matching strategies and frequency domain noise reduction methods. Essentially, they are still frequency domain noise reduction methods, so the methods used to statistically analyze the noise reduction amount of frequency domain noise reduction algorithms can still be applied.

[0086] S402, determining the optimal noise reduction range based on the amount of noise reduction:

[0087] In this embodiment, the stronger the noise reduction intensity, the greater the noise reduction amount. Therefore, the order of noise reduction intensity is consistent with the noise reduction amount. The noise reduction interval can be defined as follows: the interval less than the noise reduction amount 1 is the noise reduction interval 0, the interval between the noise reduction amount 1 and the noise reduction amount 2 is the noise reduction interval 1, and so on, while the interval greater than the noise reduction amount N is the noise reduction interval N.

[0088] In this embodiment, the optimal noise reduction range is selected based on a pre-set noise reduction value, where noise reduction amount x < noise reduction value < noise reduction amount x+1. Noise reduction amount x and noise reduction amount x+1 are the noise reduction amounts corresponding to two adjacent noise reduction intensities.

[0089] S403, zone noise reduction includes the following:

[0090] Based on the noise reduction amount and value of the noise reduction range, as well as the preset noise reduction amount, the final noise reduction result is interpolated.

[0091] If the noise reduction region is between 1 and N-1, the final noise reduction result can be interpolated using the following methods: .

[0092] If it is in the 0 noise reduction region, the final noise reduction result includes: .

[0093] If it is within the N noise reduction region, the final noise reduction result includes: .

[0094] S404, the interval noise reduction method includes the following:

[0095] The fusion is performed based on the difference between a pre-set noise reduction value and the statistical noise reduction value corresponding to the noise reduction intensity. The difference between the pre-set noise reduction value and the statistical noise reduction value corresponding to the noise reduction intensity can be expressed by the formula: .

[0096] Convert the gap into weights: Here, f represents a function that maps the gaps to the weights, such as an exponential function or a linear function. T represents an externally configured parameter used to adjust the intensity of the interval noise reduction, i.e., the size of WeiNoisSta.

[0097] The final representation of interval denoising is as follows: .

[0098] The S405 multi-channel image noise reduction methods include the following:

[0099] In this embodiment, when the image to be processed is a color image or a multi-channel image, a color image is also referred to as a multi-channel image. Any image with more than one channel is called a multi-channel image. Multi-channel images can be processed simply by splitting them into individual channels for processing, or by converting them into luminance and chrominance multi-channel images for processing together. After conversion to luminance and chrominance multi-channel images, the noise reduction intensity of the luminance and chrominance channels can be set separately. This preserves detail while more effectively filtering out color noise.

[0100] In summary, this embodiment achieves noise reduction across all regions by setting a suitable noise reduction value, while maximizing signal protection in each region. This represents an improvement over the original noise reduction algorithm. Furthermore, it is implemented in hardware with virtually no increase in line memory consumption.

[0101] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0102] This embodiment also provides an image processing apparatus for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0103] Figure 4 This is a structural block diagram of an image processing apparatus according to an embodiment of the present invention, such as... Figure 4 As shown, the device includes:

[0104] The first determining module 42 is used to determine the noise reduction amount of the image to be processed according to each of the N noise reduction intensities, and to determine the N noise reduction amounts, where N is a natural number greater than or equal to 1.

[0105] The second determining module 44 is used to determine the target noise reduction interval based on N noise reduction amounts, wherein the target noise reduction interval includes noise reduction amounts within a preset range;

[0106] The first processing module 46 is used to perform noise reduction processing on the image to be processed according to the target noise reduction range to obtain the target image.

[0107] In one exemplary embodiment, the first determining module described above includes:

[0108] The first determining unit is used to determine the weight value of each noise reduction intensity in each pixel of the above image to be processed;

[0109] The first processing unit is used to perform noise reduction processing on each pixel using the weight value of each noise reduction intensity in each pixel of the image to be processed, so as to obtain each pixel after noise reduction.

[0110] The second determining unit is used to determine the above N noise reduction amounts based on each pixel after the above noise reduction.

[0111] In one exemplary embodiment, the first determining module described above includes:

[0112] The second determining unit is used to determine the pixels in the image to be processed that are in a preset frequency band;

[0113] The third determining unit is used to perform noise reduction processing on the pixels of the preset frequency band according to each of the above noise reduction intensities, and to determine the amount of change of the pixels of the preset frequency band.

[0114] The second processing unit is used to determine N noise reduction amounts using the changes in pixel points in the aforementioned preset frequency band.

[0115] In one exemplary embodiment, the second determining module described above includes:

[0116] The first division unit is used to divide the above N noise reduction amounts into M noise reduction intervals according to a preset order, where M is a natural number greater than or equal to 1.

[0117] The fourth determining unit is used to determine the noise reduction interval that matches the preset noise reduction value among the above M noise reduction intervals as the above target noise reduction interval.

[0118] In one exemplary embodiment, the first processing module described above includes:

[0119] The first noise reduction unit is used to perform noise reduction processing on each corresponding pixel in the image to be processed using the noise reduction amount in the target noise reduction interval and the preset noise reduction value to obtain the target image, wherein the preset noise reduction value is used to perform noise reduction on each corresponding pixel.

[0120] In one exemplary embodiment, the first noise reduction unit includes:

[0121] The first determining subunit is used to determine the difference between the preset noise reduction value and the noise reduction amount in the target noise reduction range.

[0122] The first conversion subunit is used to convert the above difference into a weight value using a preset function;

[0123] The first noise reduction subunit is used to perform noise reduction processing on each corresponding pixel in the image to be processed based on the above weight values ​​to obtain the above target image.

[0124] In one exemplary embodiment, the above-described apparatus further includes one of the following:

[0125] The first splitting module is used to split the image to be processed into a single-channel image when the image to be processed includes a multi-channel image.

[0126] The first conversion module is used to convert the image to be processed into an image including a luminance channel and a color channel, when the image to be processed includes a multi-channel image.

[0127] According to yet another embodiment of the present invention, a computer-readable storage medium is also provided, wherein a computer program is stored therein, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.

[0128] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0129] Embodiments of the present invention also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.

[0130] In this embodiment, the computer-readable storage medium described above may be configured to store a computer program for performing the above steps.

[0131] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0132] Embodiments of the present invention also provide an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0133] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0134] In one exemplary embodiment, the processor described above may be configured to perform the above steps via a computer program.

[0135] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0136] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0137] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An image processing method, characterized in that, include: The noise reduction amount is determined for each of the N noise reduction intensities of the image to be processed. N noise reduction amounts are determined, where N is a natural number greater than or equal to 1. The noise reduction amount is calculated as follows: when the image to be processed is denoised using a frequency domain noise reduction algorithm, the absolute difference between the target high frequency of the image to be processed before noise reduction and the target high frequency after noise reduction is calculated to obtain multiple high frequency change amounts. The target high frequency is any high frequency of the image to be processed. The multiple high frequency change amounts are summed to obtain the noise reduction amount. The target noise reduction range is determined based on the N noise reduction amounts, wherein the target noise reduction range includes noise reduction amounts within a preset range; The image to be processed is denoised according to the target denoising range to obtain the target image; The determination of the target noise reduction interval based on the N noise reduction values ​​includes: dividing the N noise reduction values ​​into M noise reduction intervals according to a preset order, where M is a natural number greater than or equal to 1; and determining the noise reduction interval that matches the preset noise reduction value among the M noise reduction intervals as the target noise reduction interval.

2. The method according to claim 1, characterized in that, The image to be processed is denoised according to the target denoising range to obtain the target image, including: The target image is obtained by denoising each pixel in the image to be processed using the denoising amount in the target denoising range and the preset denoising value, wherein the preset denoising value is used to denoise each corresponding pixel.

3. The method according to claim 2, characterized in that, The target image is obtained by performing noise reduction processing on each corresponding pixel in the image to be processed using the noise reduction amount in the target noise reduction interval and the preset noise reduction value, including: Determine the difference between the preset noise reduction value and the noise reduction amount in the target noise reduction range; The difference is converted into a weight value using a preset function; Based on the weight values, noise reduction is performed on each corresponding pixel in the image to be processed to obtain the target image.

4. The method according to claim 1, characterized in that, The method also includes one of the following: In the case where the image to be processed includes a multi-channel image, the image to be processed is split into a single-channel image; In the case where the image to be processed includes a multi-channel image, the image to be processed is converted into an image including a luminance channel and a color channel.

5. An image processing apparatus, characterized in that, include: The first determining module is used to determine the noise reduction amount of the image to be processed according to each of the N noise reduction intensities, and to determine the N noise reduction amounts, where N is a natural number greater than or equal to 1. The noise reduction amount is calculated as follows: when the image to be processed is denoised using a frequency domain noise reduction algorithm, the absolute difference between the target high frequency of the image to be processed before noise reduction and the target high frequency after noise reduction is calculated to obtain multiple high frequency change amounts, where the target high frequency is any high frequency of the image to be processed, and the multiple high frequency change amounts are summed to obtain the noise reduction amount. The second determining module is used to determine a target noise reduction interval based on the N noise reduction amounts, wherein the target noise reduction interval includes noise reduction amounts within a preset range; The first processing module is used to perform noise reduction processing on the image to be processed according to the target noise reduction range to obtain the target image; The second determining module is further configured to divide the N noise reduction values ​​into M noise reduction intervals according to a preset order, wherein M is a natural number greater than or equal to 1; and to determine the noise reduction interval that matches the preset noise reduction value among the M noise reduction intervals as the target noise reduction interval.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the method described in any one of claims 1 to 4.

7. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the method described in any one of claims 1 to 4.

Images