CN113487496A - Image denoising method, system and device based on pixel type inference - Google Patents
Image denoising method, system and device based on pixel type inference Download PDFInfo
- Publication number
- CN113487496A CN113487496A CN202110618845.7A CN202110618845A CN113487496A CN 113487496 A CN113487496 A CN 113487496A CN 202110618845 A CN202110618845 A CN 202110618845A CN 113487496 A CN113487496 A CN 113487496A
- Authority
- CN
- China
- Prior art keywords
- pixel
- gradient
- image
- type
- denoising
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012545 processing Methods 0.000 claims abstract description 22
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 230000011218 segmentation Effects 0.000 claims abstract description 4
- 238000001914 filtration Methods 0.000 claims description 25
- 238000001514 detection method Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 5
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Facsimile Image Signal Circuits (AREA)
Abstract
The invention is suitable for the technical field of image data processing, and provides an image denoising method, a system and a device based on pixel type inference, wherein the image denoising method comprises a gradient information calculation method, a texture edge-gradient direction segmentation method, a pixel type inference method and a pixel type denoising method; the image processing system comprises a calculation module, a classification module, a denoising module and a reconstruction module; the system device includes a memory and a processor. Therefore, the method and the device can better keep the texture details while improving the denoising effect.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to an image denoising method, system and device based on pixel type inference.
Background
Due to the influence of factors such as environment and acquisition equipment, the image is inevitably polluted by noise in the acquisition, compression and transmission processes, so that image information is distorted and lost. Image noise can adversely affect processing tasks of subsequent images (such as image segmentation, target recognition, style migration, etc.), and therefore image denoising plays an important role in modern image processing systems.
The purpose of image denoising is to recover a clear image from a noisy image, which is a classical inverse problem in computer vision. The current image processing algorithms are many, and there are median filtering, gaussian filtering, ROF algorithm, BM3D algorithm, sparse representation algorithm, machine learning algorithm, deep learning algorithm, etc. in common, but these algorithms reduce the noise level to some extent, and at the same time, there are some defects, such as the problem of computational efficiency, the problem of feature loss, etc.
Most of noise of an image belongs to Gaussian noise, Gaussian filtering is linear smooth filtering and is suitable for eliminating the Gaussian noise, but the texture characteristics of the image cannot be well reserved in the Gaussian filtering, so that some scholars propose a self-adaptive Gaussian filtering algorithm, the algorithm reserves image details to a certain extent, and meanwhile, the calculation efficiency and the noise reduction effect are reduced.
In view of the above, the prior art is obviously inconvenient and disadvantageous in practical use, and needs to be improved.
Disclosure of Invention
In view of the foregoing defects, the present invention provides a method, a system, and a device for image denoising based on pixel type inference, which can better retain texture details while improving the denoising effect.
The invention provides an image denoising method based on pixel type inference, which comprises the following steps:
step-gradient information calculation
By means of a Sobel operator, gradient values of the image in the horizontal direction and the vertical direction are calculated, and gradient strength and gradient direction of the image are calculated by means of gradient values of four directions of the horizontal direction, the vertical direction, 45 degrees and 45 degrees.
Step two texture edge-gradient direction segmentation
The texture edge and the gradient direction of the image are divided into four directions of horizontal, vertical, 45 degrees and 45 degrees according to the gradient defensive line, and an inference basis is provided for the pixel type of the image.
Step three pixel type inference
And deducing the pixel type of the image by adopting methods of extremum inference, double-threshold detection and connectivity judgment.
Step four-pixel type image denoising
And according to the inferred pixel type, adopting a corresponding image denoising scheme, and outputting a final image.
According to the image denoising method based on the pixel type inference, in the first step, a 3 × 3 Sobel operator is selected to determine the gradient strength of the image.
According to the image denoising method based on the pixel type inference, in the second step, the pixel types of the image comprise three types, namely, noise pixels, texture pixels and common pixels.
According to the image denoising method based on pixel type inference, in the third step, the pixel type inference process of the image comprises the following steps:
s1: initializing double thresholds TH and TL of gradient strength, and initializing and determining a noise pixel type judgment coefficient P;
s2: calculating whether f (x, y) satisfies a maximum value greater than a neighboring pixel in the gradient direction or a minimum value less than the neighboring pixel in the gradient direction according to the gradient direction decomposition diagram, if so, continuing to perform the operation of S3, otherwise, performing the operation of S4;
s3: comparing the maximum value or the minimum value of 8 pixels around f (x, y), if the following formula is satisfied, the judgment coefficient P of the determined noise type is satisfied, the type of the pixel is judged as the determined noise type, otherwise, the pixel is judged as the determined texture pixel type;
s4: calculating whether G (x, y) is larger than TH, if so, determining to determine the texture pixel, and if not, executing S5;
and 5: calculating whether G (x, y) is larger than TL, if so, judging the pixel type to be a common pixel type, and if not, executing S6;
s6: and calculating whether a determined texture pixel exists in the (x, y) neighborhood 8 pixels, if so, determining the texture pixel, and if not, determining the normal pixel type.
According to the image denoising method based on pixel type inference, in the fourth step, the processing method of each type of pixel comprises the following steps: the pixel is a determined texture pixel type, and Gaussian filtering processing is adopted; the pixel is of a common pixel type, a determined texture pixel and a determined noise pixel in a neighborhood window are replaced by a common pixel mean value of the neighborhood window, and then Gaussian filtering processing is carried out; the pixel type is determined as a texel, and no filtering process is performed.
According to the image denoising method based on the pixel type inference, the invention also provides an image processing system, which comprises: the computing module is mainly used for computing the gradient value and the gradient direction of the pixel; a classification module, which is mainly used for deducing each pixel type; the denoising module is mainly used for denoising each pixel of the noise image according to the pixel type; and the reconstruction module is mainly used for reconstructing the processed image according to all the denoised pixel values.
According to the system of the present invention, the operations executed by the computing module specifically include: solving Sobel operators in the four directions of horizontal, vertical, 45 degrees and 45 degrees; calculating gradient values of horizontal, vertical, 45 degrees and 45 degrees; solving the gradient strength of the pixel by using the gradient values in all directions; solving the gradient direction of the pixel; and forming a gradient strength and gradient direction matrix of each pixel.
According to the system of the present invention, the operations performed by the classification module specifically include: forming a texture direction exploded view according to the gradient strength and the gradient direction; determining gradient strength double thresholds TH and TL, and determining a noise pixel type judgment coefficient P; carrying out identification and judgment on the three pixel types by using extremum inference, double-threshold detection and communication method judgment; a pixel type two-dimensional matrix map is formed.
According to the system of the present invention, the operations performed by the denoising module specifically include: determining a Gaussian filter kernel according to the image information; filling related pixels according to the pixel types to form a neighborhood window to be filtered; and calculating the filtered pixel value according to the classification type denoising rule.
According to the system of the present invention, there is also provided a processing apparatus for an image processing system, the apparatus comprising a memory and a processor, the memory capable of storing a photograph to be denoised, a denoised photograph and a plurality of program codes; the processor is capable of executing the denoising method and the system.
The technical scheme of the invention has the following beneficial effects: the gradient strength expression of noise points and texture points is increased by introducing 45 DEG to 45 DEG gradient information; dividing the texture direction and the gradient direction into four directions of horizontal, vertical, 45 degrees and-45 degrees by means of the texture direction and gradient direction exploded view; and by combining gradient information with the texture direction and the gradient direction, the inference of determining three pixel types of a noise pixel, a texture pixel and a common pixel is realized by means of extremum inference, double-threshold detection and a connectivity method judgment method. By means of Gaussian filtering of the determined noise pixels, filtering output of the determined texture pixels and Gaussian filtering of neighborhood mean replacement of the common pixels (mean replacement of the determined Gaussian pixels and the determined texture pixels), image blurring is reduced, image texture details are reserved to the greatest extent, and computing processing efficiency is improved to a certain extent. In conclusion, according to the technical scheme, the denoising effect is improved, the texture details are better kept, and the method has strong application and popularization values.
Drawings
FIG. 1 is a flow chart of an image denoising method according to the present invention;
FIG. 2 is an exploded view of the texture direction, gradient direction of the present invention;
FIG. 3 is a flow chart of pixel type inference of the present invention;
FIG. 4 is a flow chart of three types of pixel denoising of the present invention;
FIG. 5 is a Gaussian filter calculation for mean replacement determination of texels and determination of noisy pixels in accordance with the present invention;
FIG. 6 is a block diagram of an image denoising system according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention are described in further detail below with reference to the accompanying drawings in the embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, it is a main flowchart of an embodiment of an image denoising method based on pixel type inference according to the present invention, and the image denoising method includes the following steps:
step-gradient information calculation
Gradient values in the horizontal and vertical directions are calculated by means of a Sobel operator, and gradient strength and gradient direction are calculated by means of gradient values in four directions of horizontal, vertical, 45 DEG, -45 deg.
The texture of the image can be along different directions, therefore, the invention selects Sobel operators of 3 x 3 in four directions of horizontal, vertical, 45 degrees and-45 degrees to determine the gradient strength, and the Sobel operators in all directions are shown in the following formula.
The gradient values in the four directions of horizontal, vertical, 45 ° and-45 ° are shown by the following equations:
Gx(x,y)＝f(x,y)*Sobelx(x,y)
Gy(x,y)＝f(x,y)*Sobely(x,y)
G45°(x,y)＝f(x,y)*Sobel45°(x,y)
G-45°(x,y)＝f(x,y)*Sobel-45°(x,y)
wherein G isx(x,y)、Gy(x,y)、G45°(x,y)、G-45°(x, y) are gradient values in four directions of horizontal, vertical, 45 degrees and-45 degrees respectively; f (x, y) represents the gray value of the pixel point (x, y).
The gradient strength of the pixel point (x, y) is shown as the following formula:
the gradient direction is shown in the formula:
step two texture edge-gradient direction segmentation
The texture edge and the gradient direction are divided into four directions of horizontal, vertical, 45 degrees and 45 degrees according to the gradient defensive line, and an inference basis is provided for the pixel type.
For comparison, the present invention divides the grain direction into 4 directions, i.e., horizontal, vertical, 45 °, and-45 °, and the gradient direction also into four directions (perpendicular to the grain direction). Texture direction, gradient direction exploded view see fig. 2.
Step three pixel type inference
And deducing the pixel type by adopting methods of extremum inference, double-threshold detection and connectivity judgment.
The invention includes three pixel types, namely determining a noise pixel, determining a texture pixel and a common pixel, wherein the common pixel type represents a pixel type which has low gradient value and is difficult to judge whether the pixel type is not polluted by noise or has noise. The extreme value inference, the double-threshold detection and the connection method judgment are comprehensively used for inferring three pixel types, an inference flow chart is shown in a figure 3, and the inference flow comprises the following steps:
s1: initializing gradient strength double thresholds TH and TL (TH represents a set gradient high threshold, TL represents a set gradient low threshold), and initializing and determining a noise pixel type judgment coefficient P.
S2: calculating whether f (x, y) satisfies a maximum value greater than a neighboring pixel in the gradient direction or a minimum value less than the neighboring pixel in the gradient direction according to the gradient direction exploded view, and if so, continuing to perform the operation of S3, otherwise, performing the operation of S4.
S3: and comparing the maximum value or the minimum value of 8 pixels around f (x, y), if the following formula is satisfied, the maximum value or the minimum value represents that a determination noise type judgment coefficient P is satisfied, the type of the pixel is judged as a determination noise type, otherwise, the pixel is judged as a determination texture pixel type.
S4: whether G (x, y) is greater than TH is calculated, and if yes, it is determined to determine a texel, and if not, S5 is performed.
And 5: whether G (x, y) is greater than TL is calculated, and if yes, it is determined as a normal pixel type, and if not, S6 is performed.
S6: and calculating whether a determined texture pixel exists in the (x, y) neighborhood 8 pixels, if so, determining the texture pixel, and if not, determining the normal pixel type.
Step four-pixel type Gaussian filtering denoising
And aiming at the three inferred pixel types, adopting a corresponding Gaussian filtering scheme and outputting a final filtering image.
According to the inference process, determining that the type of the noise pixel belongs to a high-intensity noise type, possibly located in a texture region or a non-texture region, wherein the type is directly processed by Gaussian filtering; the common pixel type comprises pixels which are not polluted by noise and pixels which are polluted by noise, and in the type, the determined texture pixels and the determined noise pixels in the neighborhood window have small contribution degree to Gaussian filtering and even can bring interference, so that the determined texture pixels and the determined noise pixels are replaced by the common pixel mean value of the neighborhood window, and then filtering processing is carried out; and determining texture pixels, and reserving details without filtering.
The flow chart for three types of pixel denoising is shown in fig. 4. Mean replacement texture pixel determination and noise pixel determination gaussian filter calculations are shown in fig. 5. Window (2k +1) × (2k +1) window gaussian template (k takes value 1, 3 × 3 windows are selected in the invention), and the calculation formula of each element value in the template is as follows:
the present invention also provides a working system based on the image denoising method, referring to fig. 6, the system at least includes:
1. and the calculation module is used for calculating the horizontal, vertical, 45 degrees and 45 degrees gradient values of each pixel and calculating the gradient strength and gradient direction of each pixel according to the gradient values.
In one embodiment, the horizontal, vertical, 45 °, -45 ° gradient values for each pixel are obtained according to the Sobel operator; the gradient intensity of each pixel is calculated by adopting a square root method of the square sum of gradient values of horizontal, vertical, 45 degrees and 45 degrees; the gradient direction is obtained by adopting a horizontal gradient value and a vertical gradient value.
2. And the classification module is used for determining the inference of three pixel types including noise pixels, texture pixels and common pixels.
In one embodiment, a texture (gradient) direction exploded view is formed according to the gradient strength and the gradient direction; forming a texture (gradient) direction exploded view according to the gradient strength and the gradient direction; carrying out identification and judgment on the three pixel types by using extremum inference, double-threshold detection and communication method judgment; a pixel type two-dimensional matrix map is formed.
3. And the denoising module is used for denoising each pixel of the noise image according to the pixel type.
In one embodiment, a gaussian filter kernel is initialized according to image information; filling related pixels according to the pixel types to form a neighborhood window to be filtered; the filtered pixel values are calculated according to the classification processing rules.
4. And the reconstruction module is used for reconstructing the processed image according to all the denoised pixel values.
Further, in an embodiment of a processing apparatus of the present invention, the apparatus comprises a memory and a processor, wherein the memory can store a photo to be denoised, a de-dried photo and a plurality of program codes, and the processor can execute the image denoising method and complete the system.
In summary, the image processing method based on pixel type inference in the invention increases the gradient strength expression of noise points and texture points by introducing 45 °, -45 ° gradient information; dividing the texture direction and the gradient direction into four directions of horizontal, vertical, 45 degrees and-45 degrees by means of the texture direction and gradient direction exploded view; and by combining gradient information with the texture direction and the gradient direction, the inference of determining three pixel types of a noise pixel, a texture pixel and a common pixel is realized by means of extremum inference, double-threshold detection and a connectivity method judgment method. By means of Gaussian filtering of the determined noise pixels, filtering output of the determined texture pixels and Gaussian filtering of neighborhood mean replacement of the common pixels (mean replacement of the determined Gaussian pixels and the determined texture pixels), image blurring is reduced, image texture details are reserved to the greatest extent, and computing processing efficiency is improved to a certain extent. In conclusion, the beneficial effects of the invention are as follows: the image denoising method, the image denoising system and the image denoising device based on the pixel type inference can better retain texture details while improving the denoising effect.
The present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof, and it should be understood that various changes and modifications can be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. An image denoising method based on pixel type inference is characterized by comprising the following steps:
step-gradient information calculation
Calculating gradient values of the image in the horizontal direction and the vertical direction by means of a Sobel operator, and calculating the gradient strength and the gradient direction of the image by means of gradient values in four directions of the horizontal direction, the vertical direction, 45 degrees and 45 degrees;
step two texture edge-gradient direction segmentation
Dividing texture edges and gradient directions of the image into four directions of horizontal, vertical, 45 degrees and 45 degrees according to gradient defensive lines, and providing an inference basis for pixel types of the image;
step three-pixel type inference
Deducing the pixel type of the image by adopting a combination method of extremum inference, double-threshold detection and connectivity judgment;
denoising method for step-four pixel types
And adopting a corresponding denoising method for the inferred pixel type, and outputting a final image.
2. The method for denoising an image based on pixel type inference as claimed in claim 1, wherein in the first step, a 3 × 3 Sobel operator is selected to determine the gradient strength of the image.
3. The method as claimed in claim 1, wherein the pixel type of the image in the second step includes three types, namely, noise pixel determination, texture pixel determination and normal pixel determination.
4. The method for denoising the image based on the pixel type inference according to claim 1, wherein in the third step, the pixel type inference process of the image comprises the following steps:
s1: initializing double thresholds TH and TL of gradient strength, and initializing and determining a noise pixel type judgment coefficient P;
s2: calculating whether f (x, y) satisfies a maximum value greater than a neighboring pixel in the gradient direction or a minimum value less than the neighboring pixel in the gradient direction according to the gradient direction decomposition diagram, if so, continuing to perform the operation of S3, otherwise, performing the operation of S4;
s3: comparing the maximum value or the minimum value of 8 pixels around f (x, y), if the following formula is satisfied, the judgment coefficient P of the determined noise type is satisfied, the type of the pixel is judged as the determined noise type, otherwise, the pixel is judged as the determined texture pixel type;
s4: calculating whether G (x, y) is larger than TH, if so, determining to determine the texture pixel, and if not, executing S5;
and 5: calculating whether G (x, y) is larger than TL, if so, judging the pixel type to be a common pixel type, and if not, executing S6;
s6: and calculating whether a determined texture pixel exists in the (x, y) neighborhood 8 pixels, if so, determining the texture pixel, and if not, determining the normal pixel type.
5. The method for denoising an image based on pixel type inference according to claim 1, wherein in the fourth step, the method for processing each type of pixel comprises:
the pixel is a determined texture pixel type, and Gaussian filtering processing is adopted;
the pixel is of a common pixel type, a determined texture pixel and a determined noise pixel in a neighborhood window are replaced by a common pixel mean value of the neighborhood window, and then Gaussian filtering processing is carried out;
the pixel type is determined as a texel, and no filtering process is performed.
6. An image processing system for the image denoising method according to claim 1, comprising:
the computing module is mainly used for computing the gradient value and the gradient direction of the pixel;
a classification module, which is mainly used for deducing each pixel type;
the denoising module is mainly used for denoising each pixel of the noise image according to the pixel type;
and the reconstruction module is mainly used for reconstructing the processed image according to all the denoised pixel values.
7. The system according to claim 6, wherein the operations performed by the computing module specifically include:
solving Sobel operators in the four directions of horizontal, vertical, 45 degrees and 45 degrees;
calculating gradient values of horizontal, vertical, 45 degrees and 45 degrees;
solving the gradient strength of the pixel by using the gradient values in all directions;
solving the gradient direction of the pixel;
and forming a gradient strength and gradient direction matrix of each pixel.
8. The system according to claim 6, characterized in that the operations performed by the classification module comprise in particular:
forming a texture direction exploded view according to the gradient strength and the gradient direction;
determining gradient strength double thresholds TH and TL, and determining a noise pixel type judgment coefficient P;
carrying out identification and judgment on the three pixel types by using extremum inference, double-threshold detection and communication method judgment;
a pixel type two-dimensional matrix map is formed.
9. The system according to claim 6, wherein the denoising module performs operations comprising:
determining a Gaussian filter kernel according to the image information;
filling related pixels according to the pixel types to form a neighborhood window to be filtered;
and calculating the filtered pixel value according to the classification type denoising rule.
10. A processing apparatus for use in the image processing system of claim 6, characterized by:
the device comprises a memory and a processor, wherein the memory can store a photo to be denoised, a denoised photo and a plurality of program codes; the processor is capable of executing the denoising method of any one of claims 1-5 and the system of any one of claims 6-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110618845.7A CN113487496B (en) | 2021-06-03 | 2021-06-03 | Image denoising method, system and device based on pixel type inference |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110618845.7A CN113487496B (en) | 2021-06-03 | 2021-06-03 | Image denoising method, system and device based on pixel type inference |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113487496A true CN113487496A (en) | 2021-10-08 |
| CN113487496B CN113487496B (en) | 2023-09-08 |
Family
ID=77934497
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110618845.7A Active CN113487496B (en) | 2021-06-03 | 2021-06-03 | Image denoising method, system and device based on pixel type inference |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113487496B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160132995A1 (en) * | 2014-11-12 | 2016-05-12 | Adobe Systems Incorporated | Structure Aware Image Denoising and Noise Variance Estimation |
| CN109064418A (en) * | 2018-07-11 | 2018-12-21 | 成都信息工程大学 | A kind of Images Corrupted by Non-uniform Noise denoising method based on non-local mean |
| CN111179291A (en) * | 2019-12-27 | 2020-05-19 | 凌云光技术集团有限责任公司 | Edge pixel point extraction method and device based on neighborhood relationship |
| CN112150474A (en) * | 2020-10-12 | 2020-12-29 | 山东省科学院海洋仪器仪表研究所 | Underwater bubble image feature segmentation and extraction method |
-
2021
- 2021-06-03 CN CN202110618845.7A patent/CN113487496B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160132995A1 (en) * | 2014-11-12 | 2016-05-12 | Adobe Systems Incorporated | Structure Aware Image Denoising and Noise Variance Estimation |
| CN109064418A (en) * | 2018-07-11 | 2018-12-21 | 成都信息工程大学 | A kind of Images Corrupted by Non-uniform Noise denoising method based on non-local mean |
| CN111179291A (en) * | 2019-12-27 | 2020-05-19 | 凌云光技术集团有限责任公司 | Edge pixel point extraction method and device based on neighborhood relationship |
| CN112150474A (en) * | 2020-10-12 | 2020-12-29 | 山东省科学院海洋仪器仪表研究所 | Underwater bubble image feature segmentation and extraction method |
Non-Patent Citations (2)
| Title |
|---|
| LINWEI FAN, ET AL: "Brief review of image denoising techniques", 《IEEE ACCESS》, pages 1 - 6 * |
| 岑红: "计算机视觉技术的图像识别与复原研究", 《哈尔滨理工大学学报》, pages 142 - 146 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113487496B (en) | 2023-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108921800B (en) | Non-local mean denoising method based on shape self-adaptive search window | |
| CN110866924B (en) | Line structured light center line extraction method and storage medium | |
| US20170365046A1 (en) | Algorithm and device for image processing | |
| CN112819772B (en) | High-precision rapid pattern detection and recognition method | |
| CN108510451B (en) | Method for reconstructing license plate based on double-layer convolutional neural network | |
| Xu et al. | Structure-texture aware network for low-light image enhancement | |
| CN110136075B (en) | Remote sensing image defogging method for generating countermeasure network based on edge sharpening cycle | |
| CN112150371B (en) | Image noise reduction method, device, equipment and storage medium | |
| CN111681198A (en) | Morphological attribute filtering multimode fusion imaging method, system and medium | |
| CN111105452A (en) | High-low resolution fusion stereo matching method based on binocular vision | |
| CN113421210B (en) | Surface point Yun Chong construction method based on binocular stereoscopic vision | |
| CN110827209A (en) | Self-adaptive depth image restoration method combining color and depth information | |
| Zou et al. | Image haze removal algorithm using a logarithmic guide filtering and multi-channel prior | |
| CN116862809A (en) | Image enhancement method under low exposure condition | |
| CN116912115A (en) | Underwater image self-adaptive enhancement method, system, equipment and storage medium | |
| Htet et al. | The edges detection in images using the clustering algorithm | |
| CN113487496B (en) | Image denoising method, system and device based on pixel type inference | |
| CN113362338B (en) | Rail segmentation method, device, computer equipment and rail segmentation processing system | |
| Lee et al. | A 4K-capable hardware accelerator of haze removal algorithm using haze-relevant features | |
| CN109242797B (en) | Image denoising method, system and medium based on homogeneous and heterogeneous region fusion | |
| CN111626966A (en) | Sonar image denoising model training method and device and readable storage medium thereof | |
| Xu et al. | Quaternion Quasi-Chebyshev Non-local Means for Color Image Denoising | |
| CN110648341B (en) | Target boundary detection method based on scale space and subgraph | |
| CN112581411B (en) | Image defogging method and terminal | |
| Li et al. | A novel fusion method for infrared and visible images under poor illumination conditions |
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 |