CN112037151A - Image denoising method based on wavelet analysis - Google Patents
Image denoising method based on wavelet analysis Download PDFInfo
- Publication number
- CN112037151A CN112037151A CN202010932813.XA CN202010932813A CN112037151A CN 112037151 A CN112037151 A CN 112037151A CN 202010932813 A CN202010932813 A CN 202010932813A CN 112037151 A CN112037151 A CN 112037151A
- Authority
- CN
- China
- Prior art keywords
- wavelet
- image
- decomposition
- image denoising
- analysis
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 30
- 230000009466 transformation Effects 0.000 claims abstract description 27
- 230000006870 function Effects 0.000 claims description 22
- 238000001914 filtration Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 235000002566 Capsicum Nutrition 0.000 description 2
- 239000006002 Pepper Substances 0.000 description 2
- 241000722363 Piper Species 0.000 description 2
- 235000016761 Piper aduncum Nutrition 0.000 description 2
- 235000017804 Piper guineense Nutrition 0.000 description 2
- 235000008184 Piper nigrum Nutrition 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06T5/00—Image enhancement or restoration
- G06T5/10—Image enhancement or restoration using non-spatial domain filtering
-
- 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
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an image denoising method based on wavelet analysis, and relates to the technical field of image processing; according to a signal source, wavelet transformation is carried out, a wavelet basis function is selected, wavelet decomposition is carried out by utilizing the wavelet basis function, the number of decomposition layers is determined, a proper threshold value of a wavelet coefficient is selected, thresholding processing is carried out on each layer coefficient after decomposition, and an image is reconstructed by utilizing the processed wavelet coefficient through wavelet inverse transformation to obtain a denoised image.
Description
Technical Field
The invention discloses an image denoising method, relates to the technical field of image processing, and particularly relates to an image denoising method based on wavelet analysis.
Background
With the development of technology and social progress, image information gradually becomes one of important information sources in work, study and life of people, but digital images are often influenced by interference of imaging equipment and external environment noise and the like in the digitization and transmission processes, so that the information of the images is damaged, and the image quality is influenced. The median filtering in the current image denoising method has an obvious effect on removing salt and pepper noise because the salt and pepper noise only appears randomly at partial points on a picture, and the median filtering has a high probability of replacing the value of a noise point with a point which is not polluted according to data sorting, so that the suppression effect is good. However, median filtering is not suitable for images with more points, lines and peaks because some minutiae points may be regarded as noise points; the Wiener filtering algorithm has an obvious effect on removing Gaussian noise, but has no obvious effect on removing other noises.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an image denoising method based on wavelet analysis, which can provide more accurate time domain positioning and more accurate frequency domain positioning for images. The images after wavelet transformation have the characteristics of frequency spectrum division, direction selection, multi-resolution analysis and natural tower data structure.
The specific scheme provided by the invention is as follows:
the image denoising method based on wavelet analysis comprises the steps of performing wavelet transformation according to a signal source, selecting a wavelet basis function, performing wavelet decomposition by using the wavelet basis function, determining the number of decomposition layers, selecting a proper threshold value of a wavelet coefficient, performing thresholding processing on each decomposed layer coefficient, and reconstructing an image by using the processed wavelet coefficient through wavelet inverse transformation to obtain a denoised image.
Preferably, in the image denoising method based on wavelet analysis, the wavelet sequence is obtained after the basic wavelet is subjected to expansion and translation, and the wavelet sequence is utilized to perform continuous wavelet transformation.
Preferably, the wavelet basis function selection is performed according to the support length, the vanishing moment, the symmetry, the regularity and the similarity in the image denoising method based on the wavelet analysis.
Preferably, the wavelet analysis-based image denoising method selects the threshold of the wavelet coefficient according to a fixed threshold estimation method, an extremum threshold estimation method, an unbiased likelihood estimation method or a heuristic estimation method.
The image denoising system based on wavelet analysis comprises a transformation module, a decomposition module, a processing module and a denoising module,
the transformation module carries out wavelet transformation according to a signal source, the decomposition module selects a wavelet basis function, wavelet decomposition is carried out by utilizing the wavelet basis function to determine the decomposition layer number, the processing module selects a proper threshold value of a wavelet coefficient, thresholding processing is carried out on each decomposed layer coefficient, and the denoising module reconstructs an image by utilizing the processed wavelet coefficient through wavelet inverse transformation to obtain a denoised image.
Preferably, in the image denoising system based on wavelet analysis, the transform module uses a basic wavelet to obtain a wavelet sequence after expansion and translation, and uses the wavelet sequence to perform continuous wavelet transform.
Preferably, in the image denoising system based on wavelet analysis, the decomposition module performs wavelet basis function selection according to the support length, the vanishing moment, the symmetry, the regularity and the similarity.
Preferably, the processing module in the image denoising system based on wavelet analysis selects the threshold of the wavelet coefficient according to a fixed threshold estimation method, an extremum threshold estimation method, an unbiased likelihood estimation method or a heuristic estimation method.
Image denoising device based on wavelet analysis includes: at least one memory and at least one processor;
the at least one memory to store a machine readable program;
the at least one processor is used for calling the machine readable program to execute the image denoising method based on the wavelet analysis.
The invention has the advantages that:
the invention provides an image denoising method based on wavelet analysis, which is good at analyzing non-stationary signals, selects a wavelet basis function by performing wavelet transformation under the condition that an image has edges or a signal has a mutation, performs wavelet decomposition by using the wavelet basis function, determines the number of decomposition layers, selects a threshold value of a proper wavelet coefficient, performs thresholding processing on each layer of the decomposed coefficient, reconstructs the image by using the processed wavelet coefficient through inverse wavelet transformation to obtain a denoised image, decomposes image signals to different resolutions (scales) for respective processing, and can remove noise and simultaneously keep the details of the image as much as possible after wavelet denoising.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention.
Detailed Description
The present invention is further described below in conjunction with the following figures and specific examples so that those skilled in the art may better understand the present invention and practice it, but the examples are not intended to limit the present invention.
The invention provides an image denoising method based on wavelet analysis, which comprises the steps of performing wavelet transformation according to a signal source, selecting a wavelet basis function, performing wavelet decomposition by using the wavelet basis function, determining the number of decomposition layers, selecting a threshold value of a proper wavelet coefficient, performing thresholding treatment on each layer coefficient after decomposition, and reconstructing an image by using the wavelet coefficient after treatment through inverse wavelet transformation to obtain a denoised image.
Because the noise information is mostly concentrated in the sub-low frequency, sub-high frequency and high frequency sub-bands, especially the high frequency sub-bands are basically the noise information, the wavelet noise is distributed in the high frequency part after the wavelet decomposition by the method of the invention, the wavelet coefficient of the high frequency sub-band containing much noise information is set to zero, and the coefficient of the sub-high frequency sub-band and the sub-low frequency sub-band is subjected to the suppression, thereby achieving the purpose of removing the noise.
In some embodiments of the invention, the process of wavelet transform is specified:
let Ψ (t) be L2(R) Fourier transform thereof
When in use
Satisfying the allowable conditions (complete reconstruction conditions or constant resolution conditions) is as follows
When we call Ψ (t) as a basic wavelet or mother wavelet, the mother wavelet Ψ (t) is scaled and translated to obtain:
it is referred to as a wavelet series. Wherein a isScale factor, b is a translation factor, for an arbitrary function Ψ (t) ∈ L2(R) continuous wavelet transform:
the reconstruction formula (inverse transformation) is:
after wavelet transformation, the energy is concentrated on a few wavelet coefficients, while Gaussian white noise is still white noise after orthogonal basis transformation, so that the energy becomes dispersed and the amplitude is smaller, the method selects a proper threshold, performs threshold quantization processing on the wavelet coefficients, removes noise parts, retains and enhances signal parts, and can achieve the filtering effect.
Wherein the wavelet basis functions are selected to be comprehensively considered from the support length, vanishing moment, symmetry, regularity, similarity and the like. The wavelet basis functions have characteristics when processing signals, and no wavelet basis function can achieve the optimal denoising effect on all types of signals. For example, db wavelet system and sym wavelet system can be selected as wavelet base in speech denoising;
in wavelet decomposition, selecting the decomposition layer number according to different characteristics of noise and signal expression and the balance condition between reconstructed signal distortion;
the threshold value is selected, the threshold value selection rule is based on the model y ═ f (t) + e, e is white gaussian noise N (0,1), and N is the signal length, so the threshold value capable of eliminating noise in the wavelet domain can be evaluated through wavelet coefficients or original signals.
The current common methods for selecting the threshold value are as follows: fixed threshold estimation, extremum threshold estimation, unbiased likelihood estimation, heuristic estimation, and the like,
and after threshold processing, reconstructing an image through inverse wavelet transform by using the processed wavelet coefficient to obtain a denoised image.
The invention also provides an image denoising system based on wavelet analysis, which comprises a transformation module, a decomposition module, a processing module and a denoising module,
the transformation module carries out wavelet transformation according to a signal source, the decomposition module selects a wavelet basis function, wavelet decomposition is carried out by utilizing the wavelet basis function to determine the decomposition layer number, the processing module selects a proper threshold value of a wavelet coefficient, thresholding processing is carried out on each decomposed layer coefficient, and the denoising module reconstructs an image by utilizing the processed wavelet coefficient through wavelet inverse transformation to obtain a denoised image.
The information interaction, execution process and other contents between the modules in the system are based on the same concept as the method embodiment of the present invention, and specific contents can be referred to the description in the method embodiment of the present invention, and are not described herein again.
Meanwhile, the invention also provides an image denoising device based on wavelet analysis, which comprises: at least one memory and at least one processor;
the at least one memory to store a machine readable program;
the at least one processor is used for calling the machine readable program to execute the image denoising method based on the wavelet analysis.
The processor in the device performs information interaction, executes readable program process, and the like, and the specific content can be referred to the description in the embodiment of the method of the present invention because the processor is based on the same concept as the embodiment of the method of the present invention, and is not described herein again.
It should be noted that not all steps and modules in the above flows and system and device structures are necessary, and some steps or modules may be omitted according to actual needs. The execution order of the steps is not fixed and can be adjusted as required. The system structure described in the above embodiments may be a physical structure or a logical structure, that is, some modules may be implemented by the same physical entity, or some modules may be implemented by a plurality of physical entities, or some components in a plurality of independent devices may be implemented together.
The above-mentioned embodiments are merely preferred embodiments for fully illustrating the present invention, and the scope of the present invention is not limited thereto. The equivalent substitution or change made by the technical personnel in the technical field on the basis of the invention is all within the protection scope of the invention. The protection scope of the invention is subject to the claims.
Claims (9)
1. The image denoising method based on wavelet analysis is characterized in that wavelet transformation is carried out according to a signal source, a wavelet basis function is selected, wavelet decomposition is carried out by utilizing the wavelet basis function, the number of decomposition layers is determined, a proper threshold value of a wavelet coefficient is selected, thresholding processing is carried out on each layer coefficient after decomposition, and an image is reconstructed by utilizing the processed wavelet coefficient through wavelet inverse transformation to obtain a denoised image.
2. The image denoising method based on wavelet analysis as claimed in claim 1, wherein the wavelet sequence is obtained by using the basic wavelet through expansion and translation, and the continuous wavelet transform is performed by using the wavelet sequence.
3. The image denoising method based on wavelet analysis according to claim 1 or 2, wherein wavelet basis function selection is performed according to support length, vanishing moment, symmetry, regularization and similarity.
4. The image denoising method based on wavelet analysis of claim 3, wherein the threshold selection of wavelet coefficients is performed according to a fixed threshold estimation method, an extreme value threshold estimation method, an unbiased likelihood estimation method, or a heuristic estimation method.
5. The image denoising system based on wavelet analysis is characterized by comprising a transformation module, a decomposition module, a processing module and a denoising module,
the transformation module carries out wavelet transformation according to a signal source, the decomposition module selects a wavelet basis function, wavelet decomposition is carried out by utilizing the wavelet basis function to determine the decomposition layer number, the processing module selects a proper threshold value of a wavelet coefficient, thresholding processing is carried out on each decomposed layer coefficient, and the denoising module reconstructs an image by utilizing the processed wavelet coefficient through wavelet inverse transformation to obtain a denoised image.
6. The image denoising system based on wavelet analysis of claim 5, wherein the transform module uses the basic wavelet to obtain a wavelet sequence after expansion and translation, and uses the wavelet sequence to perform continuous wavelet transform.
7. The image denoising system based on wavelet analysis of claim 5 or 6, wherein the decomposition module performs wavelet basis function selection according to support length, vanishing moment, symmetry, regularization and similarity.
8. The wavelet analysis-based image denoising system of claim 7, wherein the processing module performs threshold selection of wavelet coefficients according to a fixed threshold estimation method, an extreme value threshold estimation method, an unbiased likelihood estimation method, or a heuristic estimation method.
9. Image denoising device based on wavelet analysis, characterized by, includes: at least one memory and at least one processor;
the at least one memory to store a machine readable program;
the at least one processor, configured to invoke the machine readable program to execute the wavelet analysis based image denoising method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010932813.XA CN112037151A (en) | 2020-09-08 | 2020-09-08 | Image denoising method based on wavelet analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010932813.XA CN112037151A (en) | 2020-09-08 | 2020-09-08 | Image denoising method based on wavelet analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112037151A true CN112037151A (en) | 2020-12-04 |
Family
ID=73584194
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010932813.XA Pending CN112037151A (en) | 2020-09-08 | 2020-09-08 | Image denoising method based on wavelet analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112037151A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113074807A (en) * | 2021-03-18 | 2021-07-06 | 中国水产科学研究院黄海水产研究所 | Real-time monitoring system for vibration and deformation of cultivation fence facility structure |
| CN113808042A (en) * | 2021-09-16 | 2021-12-17 | 沈阳工业大学 | A SAR Image Denoising Method Based on Wavelet Transform and Generative Adversarial Network |
| CN113947121A (en) * | 2021-10-19 | 2022-01-18 | 山东农业大学 | Wavelet basis function selection method and system based on modular maximum denoising evaluation |
| CN113962891A (en) * | 2021-10-22 | 2022-01-21 | 深圳前海环融联易信息科技服务有限公司 | Image denoising method based on multi-resolution wavelet transform |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103617630A (en) * | 2013-12-18 | 2014-03-05 | 国网重庆潼南县供电有限责任公司 | Infrared image dividing method and system for power system equipment based on wavelet analysis |
| CN103854264A (en) * | 2014-03-28 | 2014-06-11 | 中国石油大学(华东) | Improved threshold function-based wavelet transformation image denoising method |
| CN107977944A (en) * | 2017-12-12 | 2018-05-01 | 华南农业大学 | One kind estimation NPP remote sensing image data generation methods |
-
2020
- 2020-09-08 CN CN202010932813.XA patent/CN112037151A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103617630A (en) * | 2013-12-18 | 2014-03-05 | 国网重庆潼南县供电有限责任公司 | Infrared image dividing method and system for power system equipment based on wavelet analysis |
| CN103854264A (en) * | 2014-03-28 | 2014-06-11 | 中国石油大学(华东) | Improved threshold function-based wavelet transformation image denoising method |
| CN107977944A (en) * | 2017-12-12 | 2018-05-01 | 华南农业大学 | One kind estimation NPP remote sensing image data generation methods |
Non-Patent Citations (1)
| Title |
|---|
| 张国伟: "基于小波变换的图像去噪方法研究", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113074807A (en) * | 2021-03-18 | 2021-07-06 | 中国水产科学研究院黄海水产研究所 | Real-time monitoring system for vibration and deformation of cultivation fence facility structure |
| CN113808042A (en) * | 2021-09-16 | 2021-12-17 | 沈阳工业大学 | A SAR Image Denoising Method Based on Wavelet Transform and Generative Adversarial Network |
| CN113808042B (en) * | 2021-09-16 | 2024-04-05 | 沈阳工业大学 | SAR image denoising method based on wavelet transformation and generation countermeasure network |
| CN113947121A (en) * | 2021-10-19 | 2022-01-18 | 山东农业大学 | Wavelet basis function selection method and system based on modular maximum denoising evaluation |
| CN113962891A (en) * | 2021-10-22 | 2022-01-21 | 深圳前海环融联易信息科技服务有限公司 | Image denoising method based on multi-resolution wavelet transform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112037151A (en) | Image denoising method based on wavelet analysis | |
| CN105913393B (en) | A kind of adaptive wavelet threshold image de-noising method and device | |
| Liu et al. | A medical image enhancement method using adaptive thresholding in NSCT domain combined unsharp masking | |
| Ismael et al. | Digital Image Denoising Techniques Based on Multi-Resolution Wavelet Domain with Spatial Filters: A Review. | |
| CN112991199B (en) | Image high-low frequency decomposition noise removal method based on residual dense network | |
| Patel et al. | Separated component-based restoration of speckled SAR images | |
| Lyakhov et al. | A new method for adaptive median filtering of images | |
| CN111192204A (en) | Image enhancement method, system and computer readable storage medium | |
| Anilet Bala et al. | Retinal image enhancement using adaptive histogram equalization tuned with nonsimilar grouping curvelet | |
| CN116612032A (en) | Sonar image denoising method and device based on self-adaptive wiener filtering and 2D-VMD | |
| CN110136086A (en) | Image denoising method with interval threshold based on BEMD | |
| Liu et al. | The Translation Invariant Wavelet-based Contourlet Transform for Image Denoising. | |
| CN117692074A (en) | Low-frequency aliasing noise suppression method suitable for unsteady-state underwater sound target signal | |
| Das et al. | Design of RAMF for impulsive noise cancelation from chest X-Ray image | |
| Hussain et al. | An efficient implementation of neighborhood based wavelet thresholding for image denoising | |
| CN106780398A (en) | A kind of image de-noising method based on noise prediction | |
| Zhang et al. | Improved dual-domain filtering and threshold function denoising method for ultrasound images based on non-subsampled contourlet transform | |
| Wang et al. | Comparative Study of Tongue Image Denoising Methods. | |
| Hoˇst’álková et al. | Wavelet signal and image denoising | |
| Wu et al. | The contourlet transform with multiple Cycles spinning for catenary image denoising | |
| Kiani et al. | Two new methods based on contourlet transform for despeckling synthetic aperture radar images | |
| CN116400337B (en) | Ship noise modulation line spectrum extraction and axial frequency estimation method based on line segment detection | |
| CN113160080B (en) | CR image noise reduction method, device, equipment and medium | |
| Kar et al. | An intelligent approach for noise elimination from brain image | |
| Lu et al. | Noise removal for medical x-ray images in multiwavelet domain |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201204 |
|
| RJ01 | Rejection of invention patent application after publication |