CN111932476A - Image processing method, image processing device, electronic equipment and computer readable storage medium - Google Patents

Abstract

The application relates to an image processing method, an image processing device, a computer device and a storage medium. The method comprises the following steps: acquiring images acquired aiming at the same environment under different focal lengths; determining scene images corresponding to the images, wherein each scene image comprises the same scene in the environment; and performing fusion noise reduction processing on each scene image to obtain a target noise reduction image. The method can improve the effect of image noise reduction processing.

Description

Image processing method, apparatus, electronic device, and computer-readable storage medium

technical field

The present application relates to the field of computer technology, and in particular, to an image processing method, apparatus, electronic device, and computer-readable storage medium.

Background technique

In the process of digitization and transmission, digitized images are often affected by the interference of imaging equipment and external environmental noise, that is, the image contains various noises, such as additive noise, multiplicative noise, quantization noise, “salt and pepper” noise, Gaussian noise and impact noise, etc. . The noise of the image affects the quality of the image, and it is also related to the effect of image processing, such as image segmentation, target recognition, edge extraction and so on. In order to obtain high-quality digital images, it is often necessary to perform noise reduction processing on the image, so as to maintain the integrity of the original information as much as possible, and at the same time remove the useless information in the signal.

However, traditional image noise reduction methods, such as using frequency domain, spatial domain, and the combination of frequency domain and spatial domain for noise reduction, cannot filter out image noise well, and the effect of image noise reduction is limited.

SUMMARY OF THE INVENTION

The embodiments of the present application provide an image processing method, apparatus, electronic device, and computer-readable storage medium, which can improve the effect of image noise reduction processing.

An image processing method, comprising:

Obtain images collected for the same environment at different focal lengths;

Determine the scene image corresponding to each image, and each scene image includes the same scene in the environment;

Fusion noise reduction processing is performed on each scene image to obtain the target noise reduction image.

An image processing device, comprising:

A to-be-processed image acquisition module, used to acquire images collected for the same environment under different focal lengths;

a scene image determination module, configured to determine a scene image corresponding to each image, and each scene image includes the same scene in the environment;

The noise reduction processing module is used to perform fusion noise reduction processing on each scene image to obtain the target noise reduction image.

An electronic device includes a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the following steps are implemented:

Obtain images collected for the same environment at different focal lengths;

Determine the scene image corresponding to each image, and each scene image includes the same scene in the environment;

Fusion noise reduction processing is performed on each scene image to obtain the target noise reduction image.

A computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

Obtain images collected for the same environment at different focal lengths;

Determine the scene image corresponding to each image, and each scene image includes the same scene in the environment;

Fusion noise reduction processing is performed on each scene image to obtain the target noise reduction image.

The above-mentioned image processing method, device, electronic device, and computer-readable storage medium determine scene images corresponding to each image collected for the same environment under different focal lengths, and perform fusion noise reduction on each scene image including the same scene in the environment process to obtain the target denoised image. Scene images with different focal lengths have different noise forms. By fusing and denoising each scene image, the noise form of the image can be broken, the problem of insufficient noise removal for the same noise form can be reduced, and the effect of image noise reduction can be improved.

Description of drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without any creative effort.

Fig. 1 is the application environment diagram of the image processing method in one embodiment;

2 is a flowchart of an image processing method in one embodiment;

Figure 3 is an image acquired at one focal length in one embodiment;

Figure 4 is an image acquired at another focal length in one embodiment;

5 is a schematic diagram of determining a scene image in one embodiment;

6 is a schematic flowchart of determining a scene image in another embodiment;

7 is a flowchart of fusion noise reduction processing in one embodiment;

8 is a structural block diagram of an image processing apparatus in one embodiment;

FIG. 9 is an internal structure diagram of an electronic device in one embodiment.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

It will be understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, a first client may be referred to as a second client, and similarly, a second client may be referred to as a first client, without departing from the scope of this application. Both the first client and the second client are clients, but they are not the same client.

FIG. 1 is a schematic diagram of an application environment of an image processing method in one embodiment. As shown in FIG. 1 , the application environment includes a terminal 102 and a server 104 . The terminal 102 communicates with the server 104 through the network. The terminal 102 sends each image collected for the same environment at different focal lengths to the server 104, and the server 104 determines the scene image corresponding to each image collected for the same environment at different focal lengths, and analyzes each image including the same scene in the environment. The scene image is fused and denoised to obtain the target denoised image. In addition, the terminal 102 may directly process the collected images, or the server 104 may obtain the images from a local database for processing. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices, and the server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

FIG. 2 is a flowchart of an image processing method in one embodiment. The image processing method in this embodiment is described by taking running on the terminal in FIG. 1 as an example. As shown in FIG. 2 , the image processing method includes steps 202 to 206 .

Step 202 , acquiring images collected for the same environment under different focal lengths.

Specifically, the focal length is a measure of the concentration or divergence of light in an optical system, and refers to the distance from the optical center of the lens to the focal point of light gathering when parallel light is incident. In image shooting, the lens of the camera is a set of lenses. When the light parallel to the main optical axis passes through the lens, the light converges to a point, which is called the focal point. The distance from the focal point to the center of the lens (ie the optical center) is called the focal length. At different focal lengths, the camera lens can collect images of different scene ranges. Generally, the larger the focal length, the smaller the lens framing range. For example, for a wide-angle lens, with a focal length below 40mm (mm), the framing range is wide, the angle of view is wide, and the depth of field is deep, which is more suitable for taking photos of larger scenes, such as buildings, landscapes, etc.; while the focal length of a telephoto lens Above 60mm, the telephoto lens has a function similar to a telescope, which can shoot distant objects, but its framing range is much smaller than the range of the naked eye (smaller point of view), which is convenient for long-distance snapshots and is suitable for shooting distant objects. object. The same environment means that lenses with different focal lengths shoot the same object, for example, the same building is shot with a wide-angle lens and a telephoto lens.

Specifically, the terminal acquires each image to be processed, each image is acquired under different focal lengths for the same environment, and the number of each image is at least two frames. For example, for a smartphone that includes multiple lenses, such as three lenses, you can By shooting 3 lenses at different focal lengths at the same time, 3 frames of images can be obtained. As shown in Figure 3 and Figure 4, in a specific application, the image to be processed obtained by the terminal is a group photo of three people in front of a building, wherein Figure 3 is obtained under the shooting condition with a small focal length, and the image range Including the whole of people and buildings; Figure 4 was collected under the shooting conditions with a large focal length, and the image range is dominated by people, including only a small part of the building. Obviously, by shooting for the same environment with different focal lengths, images including different scene ranges can be acquired.

Step 204: Determine scene images corresponding to each image, where each scene image includes the same scene in the environment.

The scene images include the same scene in the environment, and each image is collected for the same environment, that is, obtained by shooting the same object, but the focal length of each image is different, and the range of the scene in each image is different. A scene image is an image in which each image includes the same scene in the same environment. Specifically, the scene image can be obtained by comparing the images to cut out regions including the same scene from the images.

Specifically, after obtaining the images collected for the same environment under different focal lengths, the terminal further determines that each image corresponds to a scene image including the same scene in the environment. As shown in FIG. 5 , in one embodiment, the shaded portion is a scene image determined from an image including the same scene in the environment.

Step 206: Perform fusion noise reduction processing on each scene image to obtain a target noise reduction image.

The fusion noise reduction processing refers to the fusion of each scene image to achieve noise reduction, and specifically may be to perform mean value superposition of the corresponding pixels in each scene image to achieve noise reduction processing on the image to obtain a scene image.

Specifically, after determining the scene images corresponding to each image, the terminal performs fusion noise reduction processing on each scene image to obtain a target noise reduction image. In specific implementation, the terminal can directly superimpose the pixels corresponding to each scene image to obtain the target noise reduction image; the terminal can also further filter the result after superimposing the pixels corresponding to each scene image, so as to realize the secondary image of the image. Noise reduction to get the target noise reduction image.

At present, most of the image noise reduction methods use the frequency domain, the spatial domain, and the combination of the frequency domain and the spatial domain for noise reduction. Spatial domain noise reduction is to filter a single frame image at the current resolution to reduce Gaussian noise, salt and pepper noise, etc.; spatial domain noise reduction is to superimpose filtering with multiple frames of images before and after at the current resolution to reduce noise; some Combining the two methods can achieve better results. At the same resolution, the noise patterns of multiple frames before and after are relatively fixed. However, the image noise model is ever-changing, and different noise forms will appear at different times, and limited image algorithms cannot cover all noise forms. Therefore, no matter it is pure spatial domain noise reduction, pure time domain noise reduction, or a noise reduction method that combines spatial domain and time domain, it cannot be guaranteed that image noise can be well filtered.

This embodiment aims at the problem of limited noise reduction effect in traditional image noise reduction processing. Considering that scene images with different focal lengths have different noise forms, by performing fusion noise reduction processing on each scene image, the noise form of the image can be broken. Reduce the problem of insufficient noise removal for the same noise form, and improve the effect of image noise reduction.

The image processing method in this embodiment determines the scene images corresponding to the images collected for the same environment under different focal lengths, and performs fusion noise reduction processing on the scene images including the same scene in the environment to obtain the target noise reduction image . Scene images with different focal lengths have different noise forms. By fusing and denoising each scene image, the noise form of the image can be broken, the problem of insufficient noise removal for the same noise form can be reduced, and the effect of image noise reduction can be improved.

In one embodiment, the scene image includes a first scene image and a second scene image; determining the scene image corresponding to each image includes: determining a first image from each image, and determining the first image as the first scene image; The focal length corresponding to the first image is not less than the focal length corresponding to the second image in each image except the first image; the second scene image is determined from the second image.

In this embodiment, the scene image includes a first scene image and a second scene image, the first scene image is obtained according to the first image with the largest corresponding focal length among the images, and the second scene image is obtained according to the first image among the images except the first image. The second image is obtained.

Specifically, the terminal determines the first image from each image, and determines the first image as the first scene image, and the focal length corresponding to the first image is not less than the focal length corresponding to the second image in each image except the first image. In specific applications, the terminal may determine the focal length corresponding to each image, determine the image with the largest focal length as the first image according to the focal length corresponding to each image, and determine other images in each image as the second image. Further, the terminal determines the first image as the first scene image, and determines the second scene image from the second image, for example, an image area in the second image that includes the same scene as the first scene image can be intercepted as the second scene image. .

In a specific application, multiple lenses equipped with an electronic device can be used to shoot at the same environment at the same time to obtain images with different focal lengths. At this time, when the number of second images exceeds 1, each second image can be sequentially combined with The first image is subjected to iterative fusion noise reduction processing, that is, the target noise reduction image obtained by the fusion noise reduction processing of each second image and the first image is taken as the first image in the next iteration, and iterative fusion is performed with the next second image. The noise reduction process is performed until the fusion noise reduction process is performed on all the second images to obtain the target noise reduction image.

In this embodiment, the scene image is determined according to the focal length corresponding to each image, which can effectively determine the scene image corresponding to each image, thereby improving the accuracy and processing efficiency of image processing.

In one embodiment, before determining the second scene image from the second image, the method further includes: scaling the first image to obtain a scaled image corresponding to the first image.

In this embodiment, after the determined first image is zoomed, the second scene image is determined from the second image according to the pixel difference between the zoomed image obtained by zooming and the second image. Specifically, before determining the second scene image from the second image, the terminal zooms the determined first image to obtain a zoomed image corresponding to the first image.

Further, determining the second scene image from the second image includes: determining a pixel difference between the zoomed image and the second image; and determining the second scene image from the second image according to the pixel difference.

After obtaining the zoomed image corresponding to the first image, the terminal determines the pixel difference between the zoomed image and the second image. Specifically, the terminal may traverse the zoomed image in the second image to calculate the pixel difference, and calculate the pixel difference according to the pixel difference. The second scene image is determined from the two images. For example, the image area corresponding to the smallest pixel difference value can be cut out as the second scene image corresponding to the second image.

In this embodiment, after the first image is zoomed, an image area including information in the first image is selected in the second image according to the pixel difference value, so as to determine from the second image the first scene image that includes the same scene as the first scene image. Two scene images.

In one embodiment, scaling the first image to obtain a scaled image corresponding to the first image includes: scaling the first image according to different scaling parameters to obtain scaled images corresponding to different scaling parameters of the first image.

In this embodiment, multi-level scaling is performed on the first image, that is, scaling is performed according to different scaling parameters, so as to obtain multiple scaled images, so as to improve the accuracy of determining the second scene image. Specifically, when scaling the first image, the terminal scales the first image according to different scaling parameters to obtain each scaled image corresponding to different scaling parameters of the first image. The scaling parameters can be flexibly set according to actual needs, such as enlarging or reducing the image by a certain ratio.

As shown in FIG. 6 , in a specific application, the first image is a first group photo image 601 , the second image includes a second group photo image 602 , and the first group photo image 601 is used as the first scene image. The first group photo image 601 is scaled according to the three scaling parameters to obtain scaled images 601A, 601B and 601C corresponding to the first group photo image 601; The pixel difference value is used to obtain an image area of the second group photo image 602 that includes the same scene as the first group photo image 601 , and the image area is extracted to obtain a second scene image 602X corresponding to the second group photo image 602 .

In one embodiment, determining the pixel difference value between the zoomed image and the second image includes: traversing and calculating the pixel difference value between each zoomed image and the second image respectively.

In this embodiment, the second scene image in the second image is determined according to the image area corresponding to the smallest pixel difference between the zoomed image and the second image. Specifically, when the terminal determines the pixel difference between the zoomed image and the second image, the terminal traverses and calculates the pixel difference between each zoomed image and the second image. Specifically, the terminal can translate the zoomed image in each image area of the second image and calculate the pixel difference between the zoomed image and the second image, thereby traversing and calculating the pixel difference between the zoomed image and each image area in the second image.

Further, determining the second scene image from the second image according to the pixel difference value includes: determining an image area in the second image corresponding to the smallest pixel difference value; and intercepting the image area from the second image to obtain the second scene image.

After obtaining the pixel difference value between each zoomed image and the second image, the terminal determines the image area in the second image corresponding to the smallest pixel difference value, and intercepts the image area from the second image to obtain the second scene image, thereby obtaining a second scene image from The second image accurately determines a second scene image that includes the same scene as the first image.

In specific implementation, if multiple zoomed images are included, for each zoomed image, the pixel difference value can be calculated by traversing the second image, and the minimum pixel difference value can be determined, and then the minimum pixel difference corresponding to each zoomed image can be compared. value, determine the minimum pixel difference value of each zoomed image, and obtain the second scene image according to the image area in the second image corresponding to the minimum pixel difference value.

In one embodiment, before performing fusion noise reduction processing on each scene image to obtain a target noise reduction image, the method includes: performing image registration processing on each scene image to obtain each registered scene image.

In this embodiment, before performing fusion noise reduction processing on the obtained scene images, the terminal performs image registration processing on each scene image to obtain each registered scene image. Among them, the image registration processing can be realized by an image alignment algorithm based on feature point detection. By performing image registration processing on each scene image, it can be ensured that the size of each scene image is consistent and can be overlapped.

Further, performing fusion noise reduction processing on each scene image to obtain a target noise reduction image includes: performing fusion noise reduction processing on each registered scene image to obtain a target noise reduction image.

After performing image registration processing on each scene image, the terminal performs fusion noise reduction processing on each registered scene image to obtain a target noise reduction image. Specifically, each registered scene image can be directly superimposed according to the corresponding pixel mean value, so that each image of different noise forms is fused and denoised to obtain a target denoised image.

In this embodiment, by performing image registration processing on each scene image, it can be ensured that the size of each scene image is consistent and can be overlapped, so that each image with different noise forms can be fused and denoised, and the efficiency of image denoising processing can be improved. Effect.

As shown in FIG. 7 , in one embodiment, performing fusion noise reduction processing on each registered scene image to obtain a noise reduction image, including steps 702 to 704 .

Step 702 , superimpose the pixels corresponding to each registered scene image to obtain a superimposed noise reduction image.

In this embodiment, the pixels corresponding to each registered scene image are superimposed, and the target noise reduction image is obtained according to the obtained superimposed noise reduction image. Specifically, after obtaining each registered scene image, the terminal superimposes the pixels corresponding to each registered scene image, so that each image with different noise forms is fused and denoised to obtain a superimposed denoised image.

Step 704, obtaining a target noise reduction image according to the superimposed noise reduction image.

After obtaining the superimposed noise reduction image, the terminal obtains the target noise reduction image according to the superimposed noise reduction image. Specifically, the terminal can directly use the superimposed noise reduction image as the target noise reduction image; the terminal can also perform secondary noise reduction processing on the superimposed noise reduction image. noisy image.

In this embodiment, the pixels corresponding to each registered scene image are superimposed, and the target denoised image is obtained according to the obtained superimposed denoised image, so that the images of different noise forms can be fused and denoised, and the image reduction is improved. Noise processing effect.

In one embodiment, obtaining the denoised image according to the superimposed denoised image includes: filtering the superimposed denoised image to obtain the filtered denoised image, and using the filtered denoised image as the target denoised image.

In this embodiment, filtering processing is performed on the superimposed noise reduction image, so that secondary noise reduction is performed on the obtained superimposed noise reduction image, which further improves the effect of the image noise reduction processing. Specifically, after obtaining the superimposed noise reduction image, the terminal further performs filtering processing on the superimposed noise reduction image to obtain the filtered noise reduction image, and uses the filtered noise reduction image as the target noise reduction image. The specific implementation is that the superimposed noise reduction image can be filtered through spatial filtering methods, such as bilateral filtering algorithm, median filtering algorithm, edge-preserving filtering algorithm, Beeps skin grinding algorithm, Smartblur algorithm in PS (Adobe Photoshop) 2018, Nlm (Non-local-mean, non-localized filter noise reduction algorithm) algorithm, BM3D (Block-Matching and 3D filtering, block matching and 3D filter noise reduction algorithm) noise reduction algorithm, etc.

In one embodiment, the image processing method is applied to the image denoising processing obtained by the wide-angle lens and the telephoto lens. Specifically, cameras using different focal lengths are acquired, specifically, a standard wide-angle focal length lens and a telephoto lens simultaneously collect image information to obtain two noisy YUV format wide-angle images and telephoto images. The telephoto image is zoomed at different levels, and then the pixel difference value of the reduced image in the wide-angle image is calculated, and the part of the wide-angle image corresponding to the smallest pixel difference is selected as the corresponding scene image in the wide-angle image. The selected scene image and telephoto image are registered through the image alignment algorithm based on feature point detection, so that the two images can be overlapped. The scene image and the telephoto image are averaged pixel by pixel, so that the two images with different noise forms are fused and denoised. Further, perform spatial filtering processing on the superimposed image, specifically through bilateral filtering algorithm, median filtering algorithm, edge-preserving filtering algorithm, Beeps microdermabrasion algorithm, Smartblur algorithm in PS2018, Nlm algorithm, BM3D noise reduction algorithm, etc. , for example, BM3D can be selected for noise reduction to obtain the target noise reduction image after noise reduction.

Traditional noise reduction algorithms use images of the same resolution and size, resulting in the same image noise shape in the same period of time. Neither spatial filtering nor temporal filtering can completely break the noise shape.

In this embodiment, the images with different focal lengths have different noise patterns, and the noise patterns of the images are broken through the superposition operation, reducing the insufficient superposition and elimination caused by the same noise pattern. Combined with the spatial filtering algorithm, more It further filters out image noise and improves the effect of image noise reduction.

It should be understood that although the various steps in the flowcharts of FIG. 2 and FIG. 7 are shown in sequence according to the arrows, these steps are not necessarily executed in the sequence shown by the arrows. Unless explicitly stated herein, the execution of these steps is not strictly limited to the order, and these steps may be performed in other orders. Furthermore, at least a part of the steps in FIG. 2 and FIG. 7 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but may be executed at different times. These sub-steps or The order of execution of the stages is also not necessarily sequential, but may be performed alternately or alternately with other steps or sub-steps of other steps or at least a portion of a stage.

FIG. 8 is a structural block diagram of an image processing apparatus according to an embodiment. As shown in FIG. 8 , the image processing apparatus includes: a to-be-processed image acquisition module 802, a scene image determination module 804 and a noise reduction processing module 806, wherein:

A to-be-processed image acquisition module 802, configured to acquire images collected for the same environment under different focal lengths;

a scene image determination module 804, configured to determine a scene image corresponding to each image, and each scene image includes the same scene in the environment;

The noise reduction processing module 806 is configured to perform fusion noise reduction processing on each scene image to obtain a target noise reduction image.

In one embodiment, the scene image includes a first scene image and a second scene image; the scene image determination module 804 includes a first image determination module and a second scene image module; wherein: the first image determination module is used to determine from each image The first image is determined in the first image, and the first image is determined as the first scene image; the focal length corresponding to the first image is not less than the focal length corresponding to the second image in each image except the first image; the second scene image module is used for A second scene image is determined from the second image.

In one embodiment, it further includes a scaling module for scaling the first image to obtain a scaled image corresponding to the first image; the second scene image module includes a pixel difference value determination module and a pixel difference value processing module; wherein: the pixel The difference value determination module is used to determine the pixel difference value between the zoomed image and the second image; the pixel difference value processing module is used to determine the second scene image from the second image according to the pixel difference value.

In one embodiment, the scaling module is further configured to scale the first image according to different scaling parameters to obtain each scaled image corresponding to different scaling parameters of the first image.

In one embodiment, the pixel difference value determination module is further configured to traverse and calculate the pixel difference value between each zoomed image and the second image respectively; the pixel difference value processing module is further configured to determine the second image corresponding to the smallest pixel difference value The image area in ; intercept the image area from the second image to obtain the second scene image.

In one embodiment, a registration module is further included for performing image registration processing on each scene image to obtain each registered scene image; the noise reduction processing module 806 is also used for performing image registration processing on each registered scene image. Integrate the noise reduction processing to obtain the target noise reduction image.

In one embodiment, the noise reduction processing module 806 includes an image superposition module and a superposition result processing module; wherein: the image superposition module is used to superimpose the pixels corresponding to each registered scene image to obtain a superimposed noise reduction image; superimpose; The result processing module is used to obtain the target noise reduction image according to the superimposed noise reduction image.

In one embodiment, the superposition result processing module is further configured to perform filtering processing on the superimposed noise reduction image to obtain a filtered noise reduction image, and use the filtered noise reduction image as a target noise reduction image.

The division of each module in the above image processing apparatus is only for illustration. In other embodiments, the image processing apparatus may be divided into different modules as required to complete all or part of the functions of the above image processing apparatus.

For the specific limitation of the image processing apparatus, reference may be made to the limitation of the image processing method above, which will not be repeated here. Each module in the above-mentioned image processing apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

FIG. 9 is a schematic diagram of the internal structure of an electronic device in one embodiment. As shown in FIG. 9, the electronic device includes a processor and a memory connected by a system bus. Among them, the processor is used to provide computing and control capabilities to support the operation of the entire electronic device. The memory may include non-volatile storage media and internal memory. The nonvolatile storage medium stores an operating system and a computer program. The computer program can be executed by the processor to implement an image processing method provided by the following embodiments. Internal memory provides a cached execution environment for operating system computer programs in non-volatile storage media. The electronic device may be any terminal device such as a mobile phone, a tablet computer, a PDA (Personal Digital Assistant, personal digital assistant), a POS (Point of Sales, a sales terminal), a vehicle-mounted computer, a wearable device, and the like.

The implementation of each module in the image processing apparatus provided in the embodiments of the present application may be in the form of a computer program. The computer program can be run on a terminal or server. The program modules constituted by the computer program can be stored on the memory of the electronic device. When the computer program is executed by the processor, the steps of the methods described in the embodiments of the present application are implemented.

Embodiments of the present application also provide a computer-readable storage medium. One or more non-volatile computer-readable storage media containing computer-executable instructions, when executed by one or more processors, cause the processors to perform the steps of an image processing method.

A computer program product containing instructions, when run on a computer, causes the computer to perform an image processing method.

Any reference to a memory, storage, database, or other medium as used herein may include non-volatile and/or volatile memory. Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which acts as external cache memory. By way of illustration and not limitation, RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous Link (Synchlink) DRAM (SLDRAM), Memory Bus (Rambus) Direct RAM (RDRAM), Direct Memory Bus Dynamic RAM (DRDRAM), and Memory Bus Dynamic RAM (RDRAM).

The above-mentioned embodiments only represent several embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but should not be construed as a limitation on the scope of the patent of the present application. It should be noted that, for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the scope of protection of the patent of the present application shall be subject to the appended claims.

Claims (11)

1. an image processing method, is characterized in that, comprises: Obtain images collected for the same environment at different focal lengths; determining a scene image corresponding to each of the images, and each of the scene images includes the same scene in the environment; Perform fusion noise reduction processing on each of the scene images to obtain a target noise reduction image. 2. The method according to claim 1, wherein the scene image comprises a first scene image and a second scene image; and the determining the scene image corresponding to each of the images comprises: A first image is determined from each of the images, and the first image is determined as the first scene image; the focal length corresponding to the first image is not less than the focal length of each of the images except the first image the focal length corresponding to the second image; The second scene image is determined from the second image. 3. The method according to claim 2, wherein before the determining the second scene image from the second image, the method further comprises: zooming the first image to obtain a zoomed image corresponding to the first image; The determining the second scene image from the second image includes: determining a pixel difference between the scaled image and the second image; The second scene image is determined from the second image according to the pixel difference values. 4. The method according to claim 3, wherein the scaling the first image to obtain a scaled image corresponding to the first image comprises: The first image is scaled according to different scaling parameters, and each scaled image corresponding to different scaling parameters of the first image is obtained. 5. The method according to claim 4, wherein the determining a pixel difference between the zoomed image and the second image comprises: traversing and calculating the pixel difference between each of the zoomed images and the second image respectively; The determining of the second scene image from the second image according to the pixel difference value includes: determining the image area in the second image corresponding to the smallest pixel difference; The image area is intercepted from the second image to obtain the second scene image. 6. The method according to any one of claims 1 to 5, wherein, before performing fusion noise reduction processing on each of the scene images to obtain a target noise reduction image, the method comprises: Perform image registration processing on each of the scene images to obtain each registered scene image; Performing fusion noise reduction processing on each of the scene images to obtain a target noise reduction image, including: Perform fusion noise reduction processing on each of the registered scene images to obtain a target noise reduction image. 7. The method according to claim 6, wherein the performing fusion noise reduction processing on each of the registered scene images to obtain a noise reduction image, comprising: superimposing the pixels corresponding to each of the registered scene images to obtain a superimposed noise reduction image; The target noise reduction image is obtained according to the superimposed noise reduction image. 8. The method according to claim 7, wherein the obtaining a denoised image according to the superimposed denoised image comprises: Perform filtering processing on the superimposed noise reduction image to obtain a filtered noise reduction image, and use the filtered noise reduction image as the target noise reduction image. 9. An image processing device, comprising: A to-be-processed image acquisition module, used to acquire images collected for the same environment under different focal lengths; a scene image determination module, configured to determine a scene image corresponding to each of the images, and each of the scene images includes the same scene in the environment; The noise reduction processing module is used to perform fusion noise reduction processing on each of the scene images to obtain a target noise reduction image. 10. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, characterized in that, when the computer program is executed by the processor, the processor is made to execute the process as claimed in claims 1 to 8 The steps of any one of the image noise reduction methods. 11. A computer-readable storage medium on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images