CN112150371B - Image noise reduction method, device, equipment and storage medium - Google Patents

Image noise reduction method, device, equipment and storage medium Download PDF

Info

Publication number
CN112150371B
CN112150371B CN201910580542.3A CN201910580542A CN112150371B CN 112150371 B CN112150371 B CN 112150371B CN 201910580542 A CN201910580542 A CN 201910580542A CN 112150371 B CN112150371 B CN 112150371B
Authority
CN
China
Prior art keywords
image
pixel
pixel point
noise reduction
edge
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910580542.3A
Other languages
Chinese (zh)
Other versions
CN112150371A (en
Inventor
李晓晖
孙岳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Uniview Technologies Co Ltd
Original Assignee
Zhejiang Uniview Technologies Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhejiang Uniview Technologies Co Ltd filed Critical Zhejiang Uniview Technologies Co Ltd
Priority to CN201910580542.3A priority Critical patent/CN112150371B/en
Publication of CN112150371A publication Critical patent/CN112150371A/en
Application granted granted Critical
Publication of CN112150371B publication Critical patent/CN112150371B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G06T5/70—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20024—Filtering details
    • G06T2207/20032—Median filtering

Abstract

The embodiment of the invention discloses an image noise reduction method, device, equipment and storage medium. The method comprises the following steps: determining the pixel type of a pixel point in an image to be processed; determining a noise reduction processing mode of the pixel points according to the pixel types of the pixel points in the image to be processed; adopting a noise reduction processing mode of the pixel points to carry out noise reduction processing on the pixel points; and synthesizing the noise reduction processing results of the pixel points in the image to be processed to obtain a final noise reduction image. According to the invention, the image is subjected to noise reduction processing by adopting different noise reduction processing modes according to the type of the pixel point, so that the image noise can be effectively reduced, the edge details of the image are protected, the calculation complexity is low, and the hardware implementation is convenient.

Description

Image noise reduction method, device, equipment and storage medium
Technical Field
The embodiment of the invention relates to the technical field of image processing, in particular to an image noise reduction method, an image noise reduction device, image noise reduction equipment and a storage medium.
Background
When the image is acquired, transmitted and stored, the image quality is often reduced due to various noise interferences, and the subsequent image processing is adversely affected, so that the image noise reduction is a very widely applied technology in the field of image processing. The problem of noise reduction is how to better protect information such as edge details of an image while filtering noise.
In the related art, the image noise reduction algorithm has various kinds, and two common algorithms, namely spatial filtering and transform domain filtering, are mainly adopted. The spatial filtering algorithm is generally performed directly in a two-dimensional space of an image, and by analyzing characteristics of the image, an appropriate filter function is selected, and the filter function and the image containing noise are subjected to convolution operation to suppress noise. For example, wiener filtering, mean filtering, median filtering, etc. are proposed in the prior art. Transform domain filtering is another type of method of image noise reduction. In general, the implementation of transform domain filtering is divided into three steps: different domain transforms; processing transform domain coefficients; corresponding to the different domain inverse transforms. The purpose of noise reduction is achieved through the three steps. Common transform domain filtering methods are fourier transform filtering, wavelet transform threshold filtering, and discrete cosine filtering methods.
However, in the two image noise reduction modes, the spatial filtering algorithm is relatively simple, and has certain limitations, so that the image noise reduction effect is poor; the transform domain filtering algorithm has complex calculation process and is unfavorable for hardware realization.
Disclosure of Invention
The embodiment of the invention provides an image noise reduction method, an image noise reduction device, image noise reduction equipment and a storage medium, which can effectively reduce image noise, protect image edge details, have low calculation complexity and are convenient for hardware realization.
In a first aspect, an embodiment of the present invention provides an image noise reduction method, including: determining the pixel type of a pixel point in an image to be processed; determining a noise reduction processing mode of the pixel points according to the pixel types of the pixel points in the image to be processed; adopting a noise reduction processing mode of the pixel points to carry out noise reduction processing on the pixel points; and synthesizing the noise reduction processing results of the pixel points in the image to be processed to obtain a final noise reduction image.
In a second aspect, an embodiment of the present invention further provides an image noise reduction apparatus, including: the first determining module is used for determining the pixel type of the pixel point in the image to be processed; the second determining module is used for determining a noise reduction processing mode of the pixel points according to the pixel types of the pixel points in the image to be processed; the noise reduction processing module is used for carrying out noise reduction processing on the pixel points by adopting a noise reduction processing mode of the pixel points; and the synthesis module is used for synthesizing the noise reduction processing results of the pixel points in the image to be processed to obtain a final noise reduction image.
In a third aspect, an embodiment of the present invention further provides a computer apparatus, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the image denoising method according to the embodiment of the first aspect when executing the program.
In a fourth aspect, embodiments of the present invention further provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the image denoising method according to the embodiment of the first aspect.
The technical scheme disclosed by the embodiment of the invention has the following beneficial effects:
determining the pixel type of the pixel point in the image to be processed, determining the noise reduction processing mode of the pixel point according to the pixel type of the pixel point in the image to be processed, adopting the noise reduction processing mode of the pixel point to perform noise reduction processing on the pixel point, and then synthesizing the noise reduction processing results of the pixel point in the image to be processed to obtain a final noise reduction image. Therefore, the image is subjected to noise reduction processing by adopting different noise reduction processing modes according to the type of the pixel point, so that the image noise can be effectively reduced, the edge details of the image are protected, the calculation complexity is low, and the hardware implementation is convenient.
Drawings
Fig. 1 is a flowchart of an image denoising method according to an embodiment of the present invention;
fig. 2 is a flowchart of an image denoising method according to a second embodiment of the present invention;
fig. 3 is a schematic flow chart of edge detection of an image to be processed to obtain an edge image according to a second embodiment of the present invention;
FIG. 4 is a schematic diagram of a convolution template with different directions according to a second embodiment of the present disclosure;
fig. 5 is a schematic flow chart of determining a pixel type of a pixel point in an image to be processed according to a second embodiment of the present invention;
fig. 6 is a schematic diagram of acquiring adjacent pixel points by using an edge pixel point as a center point according to a second embodiment of the present invention;
fig. 7 is a flowchart of an image denoising method according to a third embodiment of the present invention;
fig. 8 is a schematic flow chart of a noise reduction process for continuous edge pixels in an image to be processed to obtain a noise reduction result of the continuous edge pixels according to the third embodiment of the present invention;
fig. 9 (a) -9 (c) are schematic diagrams illustrating a process of selecting a continuous edge pixel point region in a preset filtering template and adjusting the weight of the filtering template according to the pixel values of the pixels in the continuous edge point region according to the third embodiment of the present invention;
fig. 10 is a schematic flow chart of a noise reduction result of extracting isolated edge pixels according to the third embodiment of the present invention;
fig. 11 is a flowchart of a noise reduction result of extracting a background pixel point according to the third embodiment of the present invention;
FIG. 12 is a schematic diagram of a similar block shape template provided by a third embodiment of the present invention;
Fig. 13 is a schematic structural diagram of an image noise reduction device according to a fourth embodiment of the present invention;
fig. 14 is a schematic structural diagram of an image noise reduction device according to a fifth embodiment of the present invention;
fig. 15 is a schematic structural diagram of an image noise reduction device according to a sixth embodiment of the present invention;
fig. 16 is a schematic structural diagram of a computer device according to a seventh embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in further detail below with reference to the drawings and examples. It should be understood that the particular embodiments described herein are illustrative only and are not limiting of embodiments of the invention. It should be further noted that, for convenience of description, only some, but not all of the structures related to the embodiments of the present invention are shown in the drawings.
Aiming at the problems that in the related art, when the noise reduction processing is carried out on the image, the spatial filtering algorithm is relatively simple, and certain limitation exists, so that the noise reduction effect of the image is poor; the transform domain filtering algorithm has complex calculation process and is unfavorable for hardware realization, and an image noise reduction method is provided.
According to the embodiment of the invention, the pixel type of the pixel point in the image to be processed is determined, the noise reduction processing mode of the pixel point is determined according to the pixel type of the pixel point, the noise reduction processing mode of the determined pixel point is adopted to carry out noise reduction processing on the pixel point, and then the noise reduction processing results of the pixel point in the image to be processed are synthesized to obtain the final noise reduction image. Therefore, the image is subjected to noise reduction processing by adopting different noise reduction processing modes according to the type of the pixel point, so that the image noise can be effectively reduced, the edge details of the image are protected, the calculation complexity is low, and the hardware implementation is convenient.
The image noise reduction method, apparatus, device and storage medium according to the embodiments of the present invention are described in detail below with reference to the accompanying drawings.
Example 1
Fig. 1 is a schematic flow chart of an image denoising method according to an embodiment of the present invention, where the method may be applied to noise filtering of an image, and the method may be performed by an image denoising device to control an image denoising process, where the image denoising device may be composed of hardware and/or software and may be generally integrated in a computer device, and the computer device may be any hardware device having a data processing function, such as a smart phone, a computer, etc. The image noise reduction method specifically comprises the following steps:
s101, determining the pixel type of a pixel point in the image to be processed.
Wherein the image to be processed may be, but is not limited to: RGB images, YUV images, gray-scale images, and the like, the format of the image to be processed in this embodiment is not particularly limited.
In this embodiment, the pixel types of the pixel point include: continuous edge pixel points, isolated edge pixel points and background pixel points.
The continuous edge pixel points are edge points, and a plurality of adjacent edge points are adjacent to the pixel points; the isolated edge pixel point means that the pixel point is an edge point and no other edge points are nearby the pixel point or the number of adjacent edge points is smaller than a preset value, such as 2, 3, etc.; the background pixel point refers to another type of pixel point corresponding to the edge point.
Alternatively, the embodiment may obtain the edge detection result by performing edge detection on the image to be processed. And then determining the pixel type of the pixel point according to the edge detection result.
S102, determining a noise reduction processing mode of the pixel point according to the pixel type of the pixel point in the image to be processed.
In this embodiment, mapping relations between different pixel types and noise reduction modes may be preset, and then, after determining the pixel type of a pixel point in an image to be processed, the corresponding noise reduction mode is searched for and corresponding noise reduction is performed according to the pixel type in the mapping relation; alternatively, the noise reduction processing manner of the pixel point may be determined according to the pixel type characteristics of the pixel point, which is not specifically limited herein.
The noise reduction processing manner of the pixel point may be, but is not limited to: bilateral filtering, guided filtering, weighted least squares filtering, non-local mean filtering, surface blurring filtering, median filtering, morphological filtering, three-dimensional block matching, double domain filtering, etc., which are not particularly limited herein.
S103, adopting a noise reduction processing mode of the pixel points to perform noise reduction processing on the pixel points.
S104, synthesizing the noise reduction processing results of the pixel points in the image to be processed to obtain a final noise reduction image.
Optionally, after determining the noise reduction processing manner of the pixel point, the image noise reduction device may perform noise reduction processing on the pixel point by using the noise reduction processing manner, to obtain a noise reduction processing result of the pixel point. And then, synthesizing the noise reduction processing results of the pixel points of different types to obtain a final noise reduction image.
For example, if the noise reduction processing method of the pixel type a is determined to be the method D1 and the noise reduction processing method of the pixel type B is determined to be the method D2, then the noise reduction processing is performed on the pixel point of the pixel type a in the image W to be processed by using the method D1 to obtain a result D1, the noise reduction processing is performed on the pixel point of the pixel type B in the image W to be processed by using the method D2 to obtain a result D2, and then the D1 and D2 are combined to obtain a final noise reduction image.
According to the image denoising method provided by the embodiment of the invention, the pixel type of the pixel in the image to be processed is determined, so that the denoising processing mode of the pixel is determined according to the pixel type of the pixel in the image to be processed, the denoising processing mode of the pixel is adopted, the pixel is subjected to denoising processing, and then the denoising processing results of the pixel in the image to be processed are synthesized, so that a final denoising image is obtained. Therefore, the image is subjected to noise reduction processing by adopting different noise reduction processing modes according to the type of the pixel point, so that the image noise can be effectively reduced, the edge details of the image are protected, the calculation complexity is low, and the hardware implementation is convenient.
Example two
As can be seen from the above analysis, according to the embodiment of the present invention, different noise reduction processing manners are determined according to pixel types of pixel points in an image to be processed, noise reduction processing is performed on the pixel points according to the different noise reduction processing manners, and noise reduction results of the different pixel points are synthesized to obtain a final noise reduction image.
In another implementation scenario of the embodiment of the present invention, when determining the pixel type of the pixel point in the image to be processed, the pixel type of the pixel point in the image to be processed may be determined by performing edge detection on the image to be processed, and according to the edge detection result. The method for image noise reduction according to the embodiment of the present invention will be described in detail with reference to fig. 2.
Fig. 2 is a flowchart of an image denoising method according to a second embodiment of the present invention.
As shown in fig. 2, the image denoising method according to the embodiment of the present invention specifically includes the following steps:
s201, edge detection is carried out on the image to be processed, and an edge image is obtained.
In this embodiment, the method of edge detection of the image to be processed may be performed in various ways. For example, a first-order or second-order derivative-based method such as Prewitt, roberts, sobel, laplacian, LOG which is common at present can be adopted; alternatively, canny, edge detection based on wavelet transform and wavelet packet, edge detection algorithm based on morphology, multi-scale edge detection technique, edge detection algorithm based on fractal geometry, and the like may be employed, which is not particularly limited in this embodiment.
As shown in fig. 3, as an alternative implementation manner, fig. 3 is a schematic flow chart of performing edge detection on an image to be processed to obtain an edge image in an embodiment of the present invention.
S301, carrying out convolution operation on the image to be processed and at least two convolution templates to obtain at least two gradient components.
In this embodiment, the convolution template may be adaptively set according to practical applications, which is not particularly limited herein. For example, the convolution template size may be 3×3, 5×5, 7×7; the number of convolution templates may be 6, 8, etc.
Alternatively, in this embodiment, the image to be processed may be convolved with at least two convolution templates to obtain at least two gradient components according to the following formula (1).
Wherein g i Representing gradient components, f representing the image to be processed, mask representing the convolution template, i representing the ith convolution template.
For example, if the image to be processed is an 8-bit (bit) gray scale image, the convolution templates are 5×5 in size and 8 in number, and the directions of the 8 convolution templates are respectively: 0 °, 22.5 °, 45 °, 67.5 °, 90 °, 112.5 °, 135 °, and 157.5 ° (as shown in fig. 4), the image noise reduction device may perform convolution operations on the gray-scale image and the 8 convolution templates according to the above formula (1), respectively, to obtain 8 gradient components. That is, i in the formula (1) takes 8.
It should be noted that, in this embodiment, a weight is set in the convolution template, and the setting of the weight is determined based on the distance between the adjacent pixel point and the center point of the template and the size of the included angle.
That is, the closer the distance from the center point, the greater the weight; the smaller the included angle with the center point, the larger the weight.
S302, determining a gradient image of the image to be processed based on the at least two gradient components.
In the present embodiment, the gradient image of the image to be processed can be determined by the following formula (2).
g(x,y)＝max i (g i (x,y))………………………………(2)
Wherein g (x, y) represents a gradient image, (x, y) represents coordinates of pixel points, max represents taking the maximum value among all gradient components, g i (x, y) represents the ith gradient component of the pixel point (x, y).
That is, the present embodiment selects the maximum gradient component from all gradient components of a pixel point in an image to be processed as a gradient image of the pixel point, and then obtains a gradient image of the image to be processed from the gradient images of all the pixel points.
S303, binarizing the gradient image to obtain an edge image.
Optionally, in this embodiment, the edge image is obtained by performing binarization processing on the gradient image to remove the weak gradient region.
In the present embodiment, the edge image can be realized by the following formula (3):
where E (x, y) represents an edge image, (x, y) represents coordinates of a pixel point, g (x, y) represents a gradient image, and 50 represents a gradient image threshold value, which may be set according to actual application conditions, and is not particularly limited herein.
That is, when the gradient image is greater than 50, the gradient image may be extracted to obtain an edge image.
For example, if the gradient image is a grayscale image, the grayscale image is binarized by the above formula (3) to obtain an edge image.
S202, determining the pixel type of the pixel point in the image to be processed according to the pixel value of the pixel point in the edge image.
In the practical application process, edge detection is carried out on the image to be processed, so that the pixel values and coordinate information of all pixel points in the edge image can be obtained while the edge image is obtained.
Therefore, when determining the pixel type of the pixel point in the image to be processed, the embodiment can determine the pixel type according to the pixel value and the coordinate information of the pixel point in the edge image.
As an alternative implementation manner, the determining the pixel type of the pixel point in the image to be processed according to this embodiment may include the following steps, referring specifically to fig. 5.
S501, determining an edge pixel point and a background pixel point according to the pixel value of each pixel point in the edge image.
Since the edge image is a binarized image and the pixel value of each pixel point in the edge image is 1 or 0 in the embodiment, the pixel points in the edge image can be classified according to the following formula (4).
Where (x, y) represents coordinates of the pixel point, and E (x, y) represents an edge image.
That is, when the pixel value of the pixel point in the edge image is 1, determining the pixel point as the edge pixel point; when the pixel value of the pixel point in the edge image is 0, determining the pixel point as a background pixel point.
Further, in this embodiment, the edge pixel further includes: a continuous edge pixel point and an isolated edge pixel point. Therefore, after determining that the pixel points in the edge image belong to the edge pixel points and the background pixel points, the embodiment can further determine the continuous edge pixel points and the isolated edge pixel points in the edge pixel points, and the specific process is referred to S502 and S503.
S502, if the pixel value of any adjacent pixel point of the edge pixel point is the same as the pixel value of the edge pixel point, and the pixel value of any adjacent pixel point of the adjacent pixel point is the same as the pixel value of the adjacent pixel point, determining the pixel type of the adjacent pixel point and the adjacent pixel point of the adjacent pixel point is the same as the pixel type of the edge pixel point.
Optionally, the determined edge pixel point may be taken as a center point, a pixel point adjacent to the edge pixel point is obtained, and the obtained pixel value of the adjacent pixel point is compared with the pixel value of the edge pixel point. If the pixel value of any adjacent pixel point is the same as the pixel value of the edge pixel point, further taking the adjacent pixel point as a center point, acquiring the pixel point adjacent to the adjacent pixel point, and comparing the acquired pixel value of the adjacent pixel point with the pixel value of the adjacent pixel point; if the pixel value of any adjacent pixel point is the same as the pixel value of the adjacent pixel point, determining the pixel types of the adjacent pixel point and the adjacent pixel point of the adjacent pixel point, wherein the pixel types of the adjacent pixel point and the edge pixel point belong to the same type; if the pixel values of all the adjacent pixel points are different from the pixel values of the adjacent pixel points, determining the pixel type of the adjacent pixel points, which are not the same type as the pixel type of the edge pixel points, and the like until the pixel types of all the edge pixel points are determined.
In this embodiment, when the pixel points adjacent to the edge pixel point are acquired and the pixel points adjacent to the adjacent pixel point are acquired, the implementation may be based on eight communication areas. The eight-connected region is a pixel point in 8 directions, which takes the pixel point as the center and takes the upper, lower, left, right, upper left, upper right, lower left and lower right of the center position to be adjacent to the pixel point position and the obliquely adjacent pixel point position.
For example, as shown in fig. 6, the edge pixel point (e.g., the pixel point marked 61 in the figure) is taken as the center point, and the pixel point of the eight connected regions of the edge pixel point (e.g., the pixel point marked 62 in the figure) is obtained.
For another example, an edge pixel point is taken as a center point, a neighborhood pixel block with a preset surrounding size is selected, eight connectivity analysis is carried out on each pixel point in the neighborhood pixel block, and the pixel point types with the same pixel value in the eight connection directions are determined to be the same pixel type. The preset neighborhood blocks may be 3×3, 5×5, and 7×7, which are not specifically limited herein.
In this embodiment, eight connectivity is defined as equation (5) below:
N 8 (x,y)＝(x,y)∪(x-1,y-1)∪(x-1,y)∪(x-1,y+1)∪(x,y-1)∪(x+1，y-1)∪(x+1,y)∪(x+1,y+1)…………………………………(5)
where (x, y) represents the coordinates of the edge pixel point.
It should be noted that, in this embodiment, when determining the pixel type of the edge pixel point by selecting the field pixel block with the preset size, the pixel value of each pixel point in the whole to-be-processed image can be prevented from being compared with the pixel value of the edge pixel point, so that the processing cost can be saved, and the implementation is easier.
Furthermore, in order to facilitate the subsequent determination of whether the edge pixel points belong to the continuous edge pixel points, the embodiment may further count the number of the pixel points with the same pixel type, compare the number of the pixel points with the threshold value of the number of the pixel points with the same pixel type, and determine whether the pixel points with the same pixel type are continuous edge pixel points.
S503, if the number of the pixel points of any pixel type is greater than or equal to the threshold value of the number of the pixel points, determining that the pixel type is a continuous edge pixel point; otherwise, it is determined that the pixel type is an isolated edge pixel point.
In this embodiment, the threshold value of the number of pixel points may be adaptively set according to the actual application scenario, which is not specifically limited herein. For example 3, 8, 25, etc.
For example, if the number of pixels is 25 and the number of pixels of the pixel type a is 30, it is determined that the pixel type a belongs to the continuous edge pixels.
For another example, if the threshold of the number of pixel points is 8 and the number of pixel points of the pixel point type a is 3, it is determined that the pixel point type a belongs to an isolated edge pixel point.
S203, determining a noise reduction processing mode of the pixel point according to the pixel type of the pixel point in the image to be processed.
S204, adopting a noise reduction processing mode of the pixel points to perform noise reduction processing on the pixel points.
S205, synthesizing the noise reduction processing results of the pixel points in the image to be processed to obtain a final noise reduction image.
According to the image noise reduction method provided by the embodiment of the invention, the edge detection is carried out on the image to be processed to obtain the edge image, the pixel type of the pixel point in the image to be processed is determined according to the pixel value of the pixel point in the edge image, and then the noise reduction processing mode is determined according to the pixel type of the pixel point, so that the image can be subjected to noise reduction processing in different noise reduction processing modes according to the pixel type of the pixel point, the edge information of the image can be protected to the maximum extent, the noise level is reduced, and the image noise reduction effect is improved.
Example III
As can be seen from the above analysis, the embodiment of the present invention determines the pixel type of the pixel point in the image to be processed according to the pixel value of the pixel point in the edge image.
In the specific implementation process, after the pixel type of the pixel point in the image to be processed is determined, the noise reduction processing mode of the pixel point can be determined according to the pixel type, and the noise reduction processing is performed according to the determined noise reduction processing mode. In the image denoising method according to the embodiment of the present invention, a denoising method of a pixel point is determined according to a pixel type, and a denoising process is specifically described according to the determined denoising method, with reference to fig. 7.
Fig. 7 is a flowchart of an image denoising method according to a third embodiment of the present invention.
As shown in fig. 7, the image denoising method specifically includes the following steps:
s701, determining the pixel type of the pixel point in the image to be processed.
S702, if the pixel type is a continuous edge pixel point, performing noise reduction processing on the continuous edge pixel point in the image to be processed to obtain a noise reduction result of the continuous edge pixel point.
Optionally, when the pixel type of the pixel point in the image to be processed is a continuous edge pixel point, the noise reduction result of the continuous edge pixel point is obtained by performing noise reduction processing on the continuous edge pixel point in the image to be processed.
As an optional implementation manner, as shown in fig. 8, the noise reduction processing is performed on the continuous edge pixel points in the image to be processed to obtain a noise reduction result of the continuous edge pixel points, which specifically includes the following steps:
s801, selecting an area with the same shape as the continuous edge pixel point area in a preset filtering template.
The preset filtering template can be set according to actual application requirements, and is not particularly limited herein.
It should be noted that, each pixel point of the preset filtering template has a weight, and the weight is determined by calculating the distance between the center pixel point of the preset filtering template and other pixel points. That is, the closer the distance between the other pixel and the center pixel is, the larger the weight is, whereas the smaller the distance is, the same distance has the same weight. In this embodiment, the weights of the pixels in the preset filtering template may also be preset according to actual needs. For example, in order to realize protection of the image edge information, the weights of the pixel points in the preset filtering template may be set to [36,10,5,3,2,1], and so on.
In practical application, since the continuous edge pixel area may be larger than the size of the preset filtering template, the embodiment may firstly divide the continuous edge pixel area into blocks according to the size of the preset filtering template to obtain a plurality of continuous edge pixel area blocks. And then selecting an area with the same shape as the area block of the continuous edge pixel points from a preset filtering template. For example, if the size of the preset filtering template is 5×5, the continuous edge pixel area may be divided into 5×5 blocks to obtain a plurality of continuous edge pixel area blocks.
For example, as shown in fig. 9 (a), if the preset filtering template size is 5×5 and the filtering weight of each pixel is composed of the median value in [36,10,5,3,2,1], the image noise reduction device may select the region with the same shape as the continuous edge pixel in the preset filtering template according to the continuous edge pixel region (as shown in fig. 9 (b)).
S802, according to pixel values of pixel points in the continuous edge pixel points, adjusting the filtering weight of the preset filtering template, and carrying out filtering processing on the continuous edge pixel point area by utilizing the adjusted filtering template.
Continuing with the description of the example in S801, after selecting an area with the same shape as the continuous edge pixel area from the preset filtering templates, the image noise reduction device may adjust the filtering weights of the corresponding pixels in the 5×5 filtering templates according to the pixel values of the pixels in the selected continuous edge pixel area, so as to obtain an adjusted filtering template (as shown in fig. 9 (c)), and perform filtering processing on the continuous edge pixel area by using the adjusted filtering template. As shown in fig. 9 (c), the filtering weight of each pixel point in the adjusted filtering template is composed of values in [36,10,0,5,2,1 ].
S703, if the pixel type is an isolated edge pixel point or a background pixel point, performing noise reduction processing on the image to be processed, and extracting a noise reduction result of the isolated edge pixel point or the background pixel point from the noise reduction result according to the position information of the isolated edge pixel point or the background pixel point.
In practical application, the number of the isolated edge pixel points is relatively small, so that noise reduction processing on the isolated edge pixel points is relatively complex and difficult. Therefore, in order to reduce the computational complexity, the present embodiment may perform noise reduction processing on the image to be processed, and then extract a corresponding noise reduction result from the noise reduction result of the image to be processed according to the position information of the isolated edge pixel points.
That is, in this embodiment, when the pixel type is an isolated edge pixel or a background pixel, the corresponding noise reduction result may be extracted from the noise reduction result of the image to be processed according to the position information of the isolated edge pixel or the background pixel after the noise reduction process is performed on the image to be processed.
Next, a detailed description will be given of a specific implementation procedure of extracting the noise reduction result of the isolated edge pixel point from the noise reduction result of the image to be processed when the pixel type is the isolated edge pixel point and extracting the noise reduction result of the background pixel point from the noise reduction result of the image to be processed when the pixel type is the background pixel point in this embodiment, with reference to fig. 10 and 11.
First, as shown in fig. 10, when the pixel type is an isolated edge pixel, the noise reduction result of extracting the isolated edge pixel from the noise reduction result of the image to be processed specifically includes the following:
s1001, median filtering processing is carried out on the image to be processed, and a median filtering result of the image to be processed is obtained.
S1002, extracting a corresponding median filtering result from the median filtering result of the image to be processed according to the position information of the isolated edge pixel points.
Alternatively, in this embodiment, the median filtering process may be performed on the image to be processed through the following formula (6), so as to obtain a median filtering result of the image to be processed.
f med (x,y)＝median(f(s,t))，(s,t)∈S x,y ………………………(6)
Wherein f med (x, y) represents the median filtering result of the pixel point (x, y) in the image to be processed, f (S, t) represents the original information of the pixel point (S, t) in the image to be processed, and (S, t) represents the coordinates of the pixel point in the image to be processed, S x,y A certain size neighborhood with (x, y) as the center point is represented.
As shown in fig. 11, when the pixel type is a background pixel point, the noise reduction result of extracting the background pixel point from the noise reduction result of the image to be processed specifically includes the following steps:
s1101, matching the pixel points in the image to be processed with at least two similar block shape templates, and selecting a target similar block shape template matched with the pixel points from the at least two similar block shape templates according to a matching result.
Wherein, at least two similar block shape templates are custom set by a technician according to actual needs.
Optionally, in this embodiment, a pixel point in the image to be processed may be used as a center point, and is respectively matched with at least two similar block shape templates, and a pixel average value of other pixel points except the pixel point is calculated. And then, the pixel mean value is differenced with the pixel value of the pixel point to obtain a difference absolute value, and the smallest value is selected from the difference absolute values, so that the similar block shape template corresponding to the smallest value is determined as the target similar block shape template.
For example, as shown in fig. 12, at least two similar block shape templates are 10, where 121 is a pixel in the image to be processed and 122 is a pixel adjacent to the pixel of the image to be processed. Taking the first similar block shape template as an example, if the pixel point in the image to be processed is f (i, j), the corresponding absolute value of the difference value can be calculated as follows:similarly, the absolute value d of the difference of the 10 similar block shape templates can be calculated x X=1, 2, 3, … 10. If the absolute value of the difference value of the 3 rd similar block shape template is the smallest in the 10 absolute values of the difference values, the 3 rd similar block shape template can be determined as the target similar block template.
S1102, determining an image area with the same shape as the target similar block shape template in the image to be processed.
The embodiment can determine the image area with the same shape as the target similar block shape template in a preset search window. The number of the preset search windows can be determined according to the number of the pixel points in the image to be processed, and the preset search windows are larger than the similar block shape template and smaller than the image to be processed.
That is, the embodiment determines the image area with the same shape as the target similar block shape template through the preset search window, so that the image processing speed and efficiency can be effectively improved.
S1103, determining the filtering weight of the image to be processed according to the distance between the image area and the target similar block shape template.
In this embodiment, the distance refers to a euclidean distance.
Alternatively, the embodiment may first calculate the euclidean distance between the image region and the target similar block shape template, and then determine the filtering weight of the image to be processed according to the euclidean distance.
For example, if m is the center pixel point of the image region, n is the target similar block shape templateCenter pixel point N of (1) m N is the image area centered on the pixel point m n For the target similar block shape template with the pixel point n as the center, the euclidean distance between the image region and the target similar block shape template can be calculated by the following formula (7).
Wherein σ represents the standard deviation of the gaussian kernel.
Further, the euclidean distance calculated according to the formula (7) is used to determine the filter weight of the image to be processed using the following formula (8).
Wherein w (m, n) is a filtering weight,for the normalization constant, the parameter h is a smoothing parameter, the decay rate of the exponential function is controlled, and d (m, n) represents the Euclidean distance between the image region and the target similar block shape template.
S1104, carrying out filtering processing on the image to be processed based on the determined filtering weight, and extracting a corresponding filtering result from the filtering result of the image to be processed according to the position information of the background pixel point.
According to the embodiment, the pixel points in the image to be processed can be subjected to weighted average processing according to the determined filtering weights, so that a filtering result of the image to be processed is obtained, and then the corresponding filtering result is extracted from the filtering result of the image to be processed according to the position information of the background pixel points.
The execution sequence of S702 and S703 may be that S702 is executed first and then S703 is executed; alternatively, S703 may be executed first, and S702 may be executed later; alternatively, S702 and S703 may be performed simultaneously, which is not particularly limited herein.
S704, synthesizing the noise reduction processing results of the pixel points in the image to be processed to obtain a final noise reduction image.
According to the image denoising method provided by the embodiment of the invention, after the pixel type of the pixel point in the image to be processed is determined, the denoising processing mode of the pixel point is determined according to the pixel type, then the denoising processing is carried out according to the pixel points of different pixel types by adopting different denoising processing modes, and the denoising processing results of the pixel points corresponding to different pixel types in the image to be processed are synthesized to obtain the final denoising image. Therefore, the noise reduction processing mode is adopted in a targeted mode according to the pixel type of the pixel point, the image noise can be effectively filtered, the image edge detail information can be protected, the overall calculation complexity in the image noise reduction process is low, and the hardware implementation is facilitated.
Example IV
In order to achieve the above object, a fourth embodiment of the present invention further provides an image noise reduction device.
Fig. 13 is a schematic structural diagram of an image noise reduction device according to a fourth embodiment of the present invention.
As shown in fig. 13, the image noise reduction device according to the embodiment of the present invention includes: the device comprises a first determining module 11, a second determining module 12, a noise reduction processing module 13 and a synthesizing module 14.
The first determining module 11 is configured to determine a pixel type of a pixel point in the image to be processed;
the second determining module 12 is configured to determine a noise reduction processing manner of a pixel point according to a pixel type of the pixel point in the image to be processed;
the noise reduction processing module 13 is configured to perform noise reduction processing on the pixel point by adopting a noise reduction processing manner of the pixel point;
the synthesis module 14 is configured to synthesize the noise reduction processing result of the pixel points in the image to be processed, so as to obtain a final noise reduction image.
It should be noted that the foregoing explanation of the embodiment of the image noise reduction method is also applicable to the image noise reduction device of this embodiment, and the implementation principle is similar, and will not be repeated here.
According to the image noise reduction device provided by the embodiment of the invention, the pixel type of the pixel point in the image to be processed is determined, so that the noise reduction processing mode of the pixel point is determined according to the pixel type of the pixel point in the image to be processed, the noise reduction processing mode of the pixel point is adopted, the noise reduction processing is carried out on the pixel point, and then the noise reduction processing results of the pixel point in the image to be processed are synthesized, so that the final noise reduction image is obtained. Therefore, the image is subjected to noise reduction processing by adopting different noise reduction processing modes according to the type of the pixel point, so that the image noise can be effectively reduced, the edge details of the image are protected, the calculation complexity is low, and the hardware implementation is convenient.
Example five
Fig. 14 is a schematic structural diagram of an image noise reduction device according to a fifth embodiment of the present invention.
As shown in fig. 14, the image noise reduction device according to the embodiment of the present invention includes: the device comprises a first determining module 11, a second determining module 12, a noise reduction processing module 13 and a synthesizing module 14.
The first determining module 11 is configured to determine a pixel type of a pixel point in the image to be processed;
the second determining module 12 is configured to determine a noise reduction processing manner of a pixel point according to a pixel type of the pixel point in the image to be processed;
the noise reduction processing module 13 is configured to perform noise reduction processing on the pixel point by adopting a noise reduction processing manner of the pixel point;
the synthesis module 14 is configured to synthesize the noise reduction processing result of the pixel points in the image to be processed, so as to obtain a final noise reduction image.
As an optional implementation manner of the embodiment of the present invention, the image noise reduction device further includes: an edge detection module 15.
The edge detection module 15 is configured to perform edge detection on the image to be processed to obtain an edge image;
the first determining module 11 is specifically configured to determine a pixel type of a pixel point in the image to be processed according to a pixel value of the pixel point in the edge image.
As an alternative implementation manner of the embodiment of the present invention, the edge detection module 15 is specifically configured to:
performing convolution operation on the image to be processed and at least two convolution templates to obtain at least two gradient components;
determining a gradient image of the image to be processed based on the at least two gradient components;
and performing binarization processing on the gradient image to obtain an edge image.
As an alternative implementation manner of the embodiment of the present invention, the first determining module 11 is further configured to:
determining an edge pixel point and a background pixel point according to the pixel value of each pixel point in the edge image;
if the pixel value of any adjacent pixel point of the edge pixel point is the same as the pixel value of the edge pixel point and the pixel value of any adjacent pixel point of the adjacent pixel point is the same as the pixel value of the adjacent pixel point, determining the pixel types of the adjacent pixel point and the adjacent pixel point of the adjacent pixel point and the pixel type of the edge pixel point;
if the number of the pixel points of any pixel type is greater than or equal to the threshold value of the number of the pixel points, determining that the pixel type is a continuous edge pixel point; otherwise, it is determined that the pixel type is an isolated edge pixel point.
It should be noted that the foregoing explanation of the embodiment of the image noise reduction method is also applicable to the image noise reduction device of this embodiment, and the implementation principle is similar, and will not be repeated here.
According to the image noise reduction device provided by the embodiment of the invention, the edge detection is carried out on the image to be processed to obtain the edge image, the pixel type of the pixel point in the image to be processed is determined according to the pixel value of the pixel point in the edge image, and then the noise reduction processing mode is determined according to the pixel type of the pixel point, so that the image can be subjected to noise reduction processing in different noise reduction processing modes according to the pixel type of the pixel point, the edge information of the image can be protected to the maximum extent, the noise level is reduced, and the image noise reduction effect is improved.
Example six
Fig. 15 is a schematic structural diagram of an image noise reduction device according to a sixth embodiment of the present invention.
As shown in fig. 15, the image noise reduction device according to the embodiment of the present invention includes: the device comprises a first determining module 11, a second determining module 12, a noise reduction processing module 13 and a synthesizing module 14.
The first determining module 11 is configured to determine a pixel type of a pixel point in the image to be processed;
the second determining module 12 is configured to determine a noise reduction processing manner of a pixel point according to a pixel type of the pixel point in the image to be processed;
The noise reduction processing module 13 is configured to perform noise reduction processing on the pixel point by adopting a noise reduction processing manner of the pixel point;
the synthesis module 14 is configured to synthesize the noise reduction processing result of the pixel points in the image to be processed, so as to obtain a final noise reduction image.
As an alternative implementation of the embodiment of the present invention, the second determining module 12 includes: a first noise reduction processing unit 1202 and a second noise reduction processing unit 1204.
The first noise reduction processing unit 1202 is configured to perform noise reduction processing on continuous edge pixel points in the image to be processed, so as to obtain a noise reduction result of the continuous edge pixel points;
the second noise reduction processing unit 1204 is configured to perform noise reduction processing on the image to be processed, and extract a noise reduction result of the isolated edge pixel point or the background pixel point from the noise reduction result according to the position information of the isolated edge pixel point or the background pixel point.
As an optional implementation manner of the embodiment of the present invention, the first noise reduction processing unit 1202 is specifically configured to:
selecting an area with the same shape as the continuous edge pixel point area in a preset filtering template;
and adjusting the filtering weight of the preset filtering template according to the pixel values of the pixels in the continuous edge pixel area, and filtering the continuous edge pixel area by utilizing the adjusted filtering template.
As an optional implementation manner of the embodiment of the present invention, the second noise reduction processing unit 1204 is specifically configured to: performing median filtering treatment on the image to be treated to obtain a median filtering result of the image to be treated;
and extracting a corresponding median filtering result from the median filtering result of the image to be processed according to the position information of the isolated edge pixel points.
As an optional implementation manner of the embodiment of the present invention, the second noise reduction processing unit 1204 is further configured to:
matching the pixel points in the image to be processed with at least two similar block shape templates, and selecting a target similar block shape template matched with the pixel points from the at least two similar block shape templates according to a matching result;
determining an image area with the same shape as the target similar block shape template in the image to be processed;
determining the filtering weight of the image to be processed according to the distance between the image area and the target similar block shape template;
and carrying out filtering processing on the image to be processed based on the determined filtering weight, and extracting a corresponding filtering result from the filtering result of the image to be processed according to the position information of the background pixel point.
It should be noted that the foregoing explanation of the embodiment of the image noise reduction method is also applicable to the image noise reduction device of this embodiment, and the implementation principle is similar, and will not be repeated here.
After determining the pixel type of the pixel point in the image to be processed, the image denoising device provided by the embodiment of the invention determines the denoising processing mode of the pixel point according to the pixel type, then performs denoising processing according to the pixel point of different pixel types by adopting different denoising processing modes, and synthesizes denoising processing results of the pixel points corresponding to different pixel types in the image to be processed to obtain a final denoising image. Therefore, the noise reduction processing mode is adopted in a targeted mode according to the pixel type of the pixel point, the image noise can be effectively filtered, the image edge detail information can be protected, the overall calculation complexity in the image noise reduction process is low, and the hardware implementation is facilitated.
Example seven
In order to achieve the above object, a seventh embodiment of the present invention further provides a computer device.
Fig. 16 is a schematic structural view of a computer device according to a seventh embodiment of the present invention, and as shown in fig. 16, the computer device includes a processor 70, a memory 71, an input device 72, and an output device 73; the number of processors 70 in the computer device may be one or more, one processor 70 being taken as an example in fig. 16; the processor 70, memory 71, input means 72 and output means 73 in the computer device may be connected by a bus or other means, in fig. 16 by way of example.
The memory 71 is a computer-readable storage medium that can be used to store a software program, a computer-executable program, and modules, such as program instructions/modules corresponding to the image denoising method in the embodiment of the present invention (for example, the first determination module 11, the second determination module 12, the denoising process module 13, and the synthesis module 14 in the image denoising apparatus). The processor 70 executes various functional applications of the computer device and data processing, i.e., implements the image noise reduction method described above, by running software programs, instructions, and modules stored in the memory 71.
The memory 71 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for functions; the storage data area may store data created according to the use of the terminal, etc. In addition, memory 71 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some examples, memory 71 may further include memory remotely located with respect to processor 70, which may be connected to the device/terminal/server via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 72 may be used to receive entered numeric or character information and to generate key signal inputs related to user settings and function control of the computer device. The output means 73 may comprise a display device such as a display screen.
It should be noted that the foregoing explanation of the image noise reduction method embodiment is also applicable to the computer device of the embodiment, and the implementation principle is similar, and will not be repeated here.
According to the computer equipment provided by the embodiment of the invention, the pixel type of the pixel point in the image to be processed is determined, so that the noise reduction processing mode of the pixel point is determined according to the pixel type of the pixel point in the image to be processed, the noise reduction processing mode of the pixel point is adopted, the noise reduction processing is carried out on the pixel point, and then the noise reduction processing results of the pixel point in the image to be processed are synthesized, so that the final noise reduction image is obtained. Therefore, the image is subjected to noise reduction processing by adopting different noise reduction processing modes according to the type of the pixel point, so that the image noise can be effectively reduced, the edge details of the image are protected, the calculation complexity is low, and the hardware implementation is convenient.
Example eight
To achieve the above object, an eighth embodiment of the present invention also proposes a computer-readable storage medium.
A computer readable storage medium provided by an embodiment of the present invention has stored thereon a computer program which, when executed by a processor, implements an image noise reduction method according to the embodiment of the first aspect, the method comprising:
determining the pixel type of a pixel point in an image to be processed;
determining a noise reduction processing mode of the pixel points according to the pixel types of the pixel points in the image to be processed;
adopting a noise reduction processing mode of the pixel points to carry out noise reduction processing on the pixel points;
and synthesizing the noise reduction processing results of the pixel points in the image to be processed to obtain a final noise reduction image.
Of course, the computer-readable storage medium provided in the embodiments of the present invention is not limited to the above-described method operations, and may also perform the related operations in the image denoising method provided in any of the embodiments of the present invention.
From the above description of embodiments, it will be apparent to those skilled in the art that the embodiments of the present invention may be implemented by software and necessary general purpose hardware, and of course may be implemented by hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the embodiments of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a FLASH Memory (FLASH), a hard disk, or an optical disk of a computer, where the instructions include a number of instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the embodiments of the present invention.
It should be noted that, in the above-mentioned embodiments of the search apparatus, each unit and module included are only divided according to the functional logic, but not limited to the above-mentioned division, as long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the embodiments of the present invention.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the embodiments of the present invention are not limited to the particular embodiments described herein, but are capable of numerous obvious changes, rearrangements and substitutions without departing from the scope of the embodiments of the present invention. Therefore, while the embodiments of the present invention have been described in connection with the above embodiments, the embodiments of the present invention are not limited to the above embodiments, but may include many other equivalent embodiments without departing from the spirit of the embodiments of the present invention, and the scope of the embodiments of the present invention is determined by the scope of the appended claims.

Claims (9)

1. A method of image denoising, the method comprising:
Determining the pixel type of a pixel point in an image to be processed;
determining a noise reduction processing mode of the pixel points according to the pixel types of the pixel points in the image to be processed;
adopting a noise reduction processing mode of the pixel points to carry out noise reduction processing on the pixel points;
synthesizing the noise reduction processing results of the pixel points in the image to be processed to obtain a final noise reduction image;
the determining the pixel type of the pixel point in the image to be processed comprises the following steps:
performing edge detection on the image to be processed to obtain an edge image;
determining the pixel type of the pixel point in the image to be processed according to the pixel value of the pixel point in the edge image;
wherein the determining the pixel type of the pixel point in the image to be processed according to the pixel value of the pixel point in the edge image includes:
determining an edge pixel point and a background pixel point according to the pixel value of each pixel point in the edge image;
if the pixel value of any adjacent pixel point of the edge pixel point is the same as the pixel value of the edge pixel point and the pixel value of any adjacent pixel point of the adjacent pixel point is the same as the pixel value of the adjacent pixel point, determining the pixel types of the adjacent pixel point and the adjacent pixel point of the adjacent pixel point and the pixel type of the edge pixel point;
If the number of the pixel points of any pixel type is greater than or equal to the threshold value of the number of the pixel points, determining that the pixel type is a continuous edge pixel point; otherwise, it is determined that the pixel type is an isolated edge pixel point.
2. The method according to claim 1, wherein performing edge detection on the image to be processed to obtain an edge image comprises:
carrying out convolution operation on the image to be processed and at least two convolution templates respectively to obtain at least two gradient components;
determining a gradient image of the image to be processed based on the at least two gradient components;
and performing binarization processing on the gradient image to obtain an edge image.
3. The method according to claim 1, wherein the determining the noise reduction processing manner of the pixel point according to the pixel type of the pixel point in the image to be processed includes:
carrying out noise reduction treatment on the continuous edge pixel points in the image to be treated to obtain a noise reduction result of the continuous edge pixel points;
and carrying out noise reduction processing on the image to be processed, and extracting the noise reduction result of the isolated edge pixel point or the background pixel point from the noise reduction result according to the position information of the isolated edge pixel point or the background pixel point.
4. A method according to claim 3, wherein performing noise reduction processing on consecutive edge pixels in the image to be processed to obtain a noise reduction result of the consecutive edge pixels comprises:
selecting an area with the same shape as the continuous edge pixel point area in a preset filtering template;
and adjusting the filtering weight of the preset filtering template according to the pixel values of the pixels in the continuous edge pixel area, and filtering the continuous edge pixel area by utilizing the adjusted filtering template.
5. A method according to claim 3, wherein the denoising processing is performed on the image to be processed, and the denoising result of the isolated edge pixel point is extracted from the denoising result according to the position information of the isolated edge pixel point, and the method comprises:
performing median filtering treatment on the image to be treated to obtain a median filtering result of the image to be treated;
and extracting a corresponding median filtering result from the median filtering result of the image to be processed according to the position information of the isolated edge pixel points.
6. A method according to claim 3, wherein the denoising processing is performed on the image to be processed, and the denoising result of the background pixel point is extracted from the denoising result according to the position information of the background pixel point, and the method comprises:
Matching the pixel points in the image to be processed with at least two similar block shape templates, and selecting a target similar block shape template matched with the pixel points from the at least two similar block shape templates according to a matching result;
determining an image area with the same shape as the target similar block shape template in the image to be processed;
determining the filtering weight of the image to be processed according to the distance between the image area and the target similar block shape template;
and carrying out filtering processing on the image to be processed based on the determined filtering weight, and extracting a corresponding filtering result from the filtering result of the image to be processed according to the position information of the background pixel point.
7. An image noise reduction apparatus, comprising:
the first determining module is used for determining the pixel type of the pixel point in the image to be processed;
the second determining module is used for determining a noise reduction processing mode of the pixel points according to the pixel types of the pixel points in the image to be processed;
the noise reduction processing module is used for carrying out noise reduction processing on the pixel points by adopting a noise reduction processing mode of the pixel points;
the synthesis module is used for synthesizing the noise reduction processing results of the pixel points in the image to be processed to obtain a final noise reduction image;
Wherein, the image noise reduction device further includes: the edge detection module is used for carrying out edge detection on the image to be processed to obtain an edge image;
the first determining module is specifically configured to determine a pixel type of a pixel point in the image to be processed according to a pixel value of the pixel point in the edge image;
wherein the first determining module is further configured to: determining an edge pixel point and a background pixel point according to the pixel value of each pixel point in the edge image;
if the pixel value of any adjacent pixel point of the edge pixel point is the same as the pixel value of the edge pixel point and the pixel value of any adjacent pixel point of the adjacent pixel point is the same as the pixel value of the adjacent pixel point, determining the pixel types of the adjacent pixel point and the adjacent pixel point of the adjacent pixel point and the pixel type of the edge pixel point;
if the number of the pixel points of any pixel type is greater than or equal to the threshold value of the number of the pixel points, determining that the pixel type is a continuous edge pixel point; otherwise, it is determined that the pixel type is an isolated edge pixel point.
8. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the image noise reduction method of any of claims 1-6 when the program is executed.
9. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the image denoising method as claimed in any one of claims 1-6.
CN201910580542.3A 2019-06-28 2019-06-28 Image noise reduction method, device, equipment and storage medium Active CN112150371B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910580542.3A CN112150371B (en) 2019-06-28 2019-06-28 Image noise reduction method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910580542.3A CN112150371B (en) 2019-06-28 2019-06-28 Image noise reduction method, device, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN112150371A CN112150371A (en) 2020-12-29
CN112150371B true CN112150371B (en) 2024-02-06

Family

ID=73892136

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910580542.3A Active CN112150371B (en) 2019-06-28 2019-06-28 Image noise reduction method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112150371B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112946232A (en) * 2021-02-04 2021-06-11 成都秦川物联网科技股份有限公司 Natural gas energy metering data acquisition method and system
CN114088658A (en) * 2021-10-09 2022-02-25 池明旻 Noise reduction treatment method for nondestructive cleaning analysis of near-infrared fabric fiber components
CN113689373B (en) * 2021-10-21 2022-02-11 深圳市慧鲤科技有限公司 Image processing method, device, equipment and computer readable storage medium
CN114693543B (en) * 2021-12-07 2024-04-05 珠海市杰理科技股份有限公司 Image noise reduction method and device, image processing chip and image acquisition equipment
CN115358951B (en) * 2022-10-19 2023-01-24 广东电网有限责任公司佛山供电局 Intelligent ring main unit monitoring system based on image recognition

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101316321A (en) * 2007-05-30 2008-12-03 展讯通信（上海）有限公司 Pattern noise removal method and device based on median filter
CN102494675A (en) * 2011-11-30 2012-06-13 哈尔滨工业大学 High-speed visual capturing method of moving target features
CN102761683A (en) * 2011-04-28 2012-10-31 华晶科技股份有限公司 Multi-picture image noise reduction method
CN103888638A (en) * 2014-03-15 2014-06-25 浙江大学 Time-space domain self-adaption denoising method based on guide filtering and non-local average filtering
JP2017188024A (en) * 2016-04-08 2017-10-12 キヤノン株式会社 Image processing device, image processing method and program

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101316321A (en) * 2007-05-30 2008-12-03 展讯通信（上海）有限公司 Pattern noise removal method and device based on median filter
CN102761683A (en) * 2011-04-28 2012-10-31 华晶科技股份有限公司 Multi-picture image noise reduction method
CN102494675A (en) * 2011-11-30 2012-06-13 哈尔滨工业大学 High-speed visual capturing method of moving target features
CN103888638A (en) * 2014-03-15 2014-06-25 浙江大学 Time-space domain self-adaption denoising method based on guide filtering and non-local average filtering
JP2017188024A (en) * 2016-04-08 2017-10-12 キヤノン株式会社 Image processing device, image processing method and program

Also Published As

Publication number Publication date
CN112150371A (en) 2020-12-29

Similar Documents

Publication Publication Date Title
CN112150371B (en) Image noise reduction method, device, equipment and storage medium
Wang et al. Infrared small target detection via nonnegativity-constrained variational mode decomposition
Li et al. Haze and thin cloud removal via sphere model improved dark channel prior
US20180122051A1 (en) Method and device for image haze removal
WO2013168618A1 (en) Image processing device and image processing method
Salmon et al. From patches to pixels in non-local methods: Weighted-average reprojection
CN109064504B (en) Image processing method, apparatus and computer storage medium
CN109214996B (en) Image processing method and device
CN107563974B (en) Image denoising method and device, electronic equipment and storage medium
CN111402170A (en) Image enhancement method, device, terminal and computer readable storage medium
WO2020232910A1 (en) Target counting method and apparatus based on image processing, device, and storage medium
CN113421206B (en) Image enhancement method based on infrared polarization imaging
CN111861938B (en) Image denoising method and device, electronic equipment and readable storage medium
CN112634301A (en) Equipment area image extraction method and device
CN111179186A (en) Image denoising system for protecting image details
CN111563517A (en) Image processing method, image processing device, electronic equipment and storage medium
CN112561919A (en) Image segmentation method, device and computer readable storage medium
CN113744294A (en) Image processing method and related device
CN106663317B (en) Morphological processing method and digital image processing device for digital image
CN112435182A (en) Image noise reduction method and device
CN116739943A (en) Image smoothing method and target contour extraction method
CN111476801A (en) Image segmentation method, electronic equipment and related product
CN111986095B (en) Image processing method and image processing device based on edge extraction
Satti et al. Intensity bound limit filter for high density impulse noise removal
Kim et al. Separable bilateral nonlocal means

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant