CN106570843A - Adaptive wavelet threshold function image noise suppression method - Google Patents
Adaptive wavelet threshold function image noise suppression method Download PDFInfo
- Publication number
- CN106570843A CN106570843A CN201610999742.9A CN201610999742A CN106570843A CN 106570843 A CN106570843 A CN 106570843A CN 201610999742 A CN201610999742 A CN 201610999742A CN 106570843 A CN106570843 A CN 106570843A
- Authority
- CN
- China
- Prior art keywords
- wavelet
- image
- threshold
- noise
- decomposition
- 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 36
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 12
- 230000001629 suppression Effects 0.000 title abstract description 7
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 19
- 230000008569 process Effects 0.000 claims description 16
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims description 2
- 230000000717 retained effect Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 6
- 238000011002 quantification Methods 0.000 abstract 1
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 208000013021 vision distortion Diseases 0.000 description 1
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
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The present invention discloses an adaptive wavelet threshold function image noise suppression method, and belongs to the gray image noise processing technology field. The method of the present invention comprises the following realization steps of 1 importing and optionally selecting a gray image containing the Gauss noise; 2 carrying out the wavelet decomposition on a noise image, and selecting an appropriate wavelet and determining the decomposition level, and then carrying out the wavelet transform to obtain a set of wavelet coefficients; 3 carrying out the threshold quantification processing on the wavelet high frequency coefficients after the wavelet decomposition to obtain a set of wavelet coefficients after the threshold processing; 4 reconstructing the wavelet coefficients after the threshold processing, thereby obtaining a noise suppression image. The method of the present invention solves the disadvantage that a hard threshold function is not continuous at a threshold, at the same time, enables the disadvantage that an error of a soft threshold function estimation coefficient is increased, to be improved correspondingly, and enables the image peak signal to noise ratio to be improved effectively, an image mean square error to be reduced and an image restoration effect to be improved better.
Description
Technical field
The present invention relates to gray level image noise management technique field, more particularly to a kind of adaptive wavelet threshold functional image
Noise suppressing method.
Background technology
Image usually can be polluted by various noises during acquisition or transmission, segmentation hence for image,
The subsequent processes such as identification bring impact.Wavelet transformation is effective one of method in current signal processing, due to it when
Domain and frequency domain have good local character simultaneously, and the signal component in assigned frequency band and time period can be analyzed
Feature, therefore have a wide range of applications in image procossing.
In wavelet threshold denoising technology, it is crucial that how selected threshold and the quantization of threshold value how is carried out, from certain
Say in degree, it is directly connected to the quality that signal removes noise.Suppressing the classics of Gaussian noise to represent algorithm at present has hard threshold
Value method and Soft thresholding, although soft, hard threshold function has certain noise suppression effect, all there is certain lacking in them
Point.Hard threshold function is discontinuous at threshold value, therefore image occurs that the vision distortions such as ring, pseudo- Gibbs' effect are existing after processing
As；And soft-threshold function relative smooth is much, but the error of estimation coefficient is increased, thus make
Into the edge blurry of reconstructed image.
The content of the invention
The purpose of the present invention aims to solve the problem that into soft, hard threshold function there is undue smooth, edge in image denoising
Vibration and have the technological deficiencies such as constant deviation, improve wavelet threshold denoising method effect and preferably protect image edge
And detailed information.
In order to achieve the above object, the present invention proposes a kind of adaptive wavelet threshold functional image noise suppressing method,
Its concrete implementation step is as follows：
Step one, importing gray level image of the optional width containing Gaussian noise；
Step 2, wavelet decomposition is carried out to noise image, select suitable small echo and determine the level of decomposition, then carry out small echo
Conversion, obtains one group of wavelet coefficient；
Step 3, threshold value quantizing process is carried out to the small echo high frequency coefficient after wavelet decomposition, obtain that one group of threshold process crosses is little
Wave system number；
Step 4, the wavelet coefficient that threshold process is crossed is reconstructed, so as to obtain noise suppressed image.
In the step one, gray level image of the optional width containing Gaussian noise, Gaussian noise average is zero, and variance is not higher than
50。
In the step 2, wavelet decomposition is carried out to noise image, it is determined that the level for decomposing is four layers, after being decomposed
Wavelet coefficient.
In the step 3, threshold value quantizing process is carried out to the high-frequency wavelet coefficient after wavelet decomposition；
Threshold size is：
In above formula,Represent threshold value,M×NThe size of image is represented,The standard variance of noise is represented, its expression formula is：
In above formula,Thresholding coefficient of wavelet decomposition is represented, its function expression is：
In above formula, sgn (x) for sign function,,WithZero control variable is greater than, its
It act as adjustingSize, the diminution as much as possible in certain threshold rangeWithW（Original wavelet coefficients）Between it is inclined
Difference,mAnd control variable, its value size pairImpact it is very big, experiment proves thatmSpan imitate between 1 to 5
Fruit is preferably.
WhenWhen, order, in order in the case where image detail is retained, effectively filter out noise, this
Bright middle orderValue is 10,mValue is 2.
Compared with prior art, the invention has the beneficial effects as follows：The expression formula of the threshold function table of the present invention, increases small echo
The reduction amplitude of coefficient, effectively reduces the deviation between wavelet coefficient and former coefficient in certain threshold range.Solve hard
The problem of threshold function table discontinuity at the threshold value, while also improving the error increase of soft-threshold function estimation coefficient accordingly
Shortcoming.The noise suppression effect of traditional algorithm, the figure after noise suppressed are substantially better than using the noise suppression effect of the present invention
As a certain degree of improvement is obtained on Y-PSNR, mean square error and subjective effect.
Description of the drawings
In order that the object, technical solutions and advantages of the present invention are clearer, below in conjunction with accompanying drawing the present invention is made into
The detailed description of one step, wherein：
Fig. 1 is the schematic flow sheet of the present invention.
Specific embodiment
The invention will be further described with reference to the accompanying drawings and detailed description.
The present invention relates to a kind of adaptive wavelet threshold functional image noise suppressing method, as shown in figure 1, being broadly divided into
Following step：
Step one, importing gray level image of the optional width containing Gaussian noise；
Step 2, wavelet decomposition is carried out to noise image, select suitable small echo and determine the level of decomposition, then carry out small echo
Conversion, obtains one group of wavelet coefficient；
Step 3, threshold value quantizing process is carried out to the small echo high frequency coefficient after wavelet decomposition, obtain that one group of threshold process crosses is little
Wave system number；
Step 4, the wavelet coefficient that threshold process is crossed is reconstructed, so as to obtain noise suppressed image.
The present invention sets a threshold value first, for the wavelet coefficient more than threshold value, obtains after their thresholdings are processed
New estimation coefficient；And the wavelet coefficient of threshold value is less than, using the process of non-zero threshold function.This method can be by partial noise
Filter, then the estimation signal Jing after wavelet inverse transformation obtains noise suppressed.
Threshold value is chosen at during thresholding is processed has particularly important effect.Threshold size is：
In above formula, the threshold value is directly proportional to the variance of noise in theory,Represent threshold value,M×NThe size of image is represented,Table
Show the standard variance of noise, its expression formula is：
In above formula,Represent thresholding coefficient of wavelet decomposition.Thresholding transforms conventional soft-threshold function：
In above formula,WIt is original wavelet coefficients, sgn (x) for sign function：
Hard threshold function is：
。
Two kinds of threshold methods cut both ways, and after hard threshold function process, image can retain marginal information well, but make an uproar
Sound is not effectively suppressed；After soft-threshold function process, the marginal information of image is obscured, but noise suppression effect is preferable.
The present invention proposes a kind of adaptive wavelet threshold functional image noise suppressing method, and its expression formula is as follows：
In above formula, sgn (x) for sign function,WithZero control variable is greater than, which act as adjustingSize,
Diminution as much as possible in certain threshold rangeWithWBetween deviation,mAnd control variable, its value size pair's
Affect very big, experiment proves thatmSpan it is preferable in 1 to 5 effects.
Generally work asWhen,Value be 0, but useful information in image is simultaneously also filtered by this process by mistake, shadow
Ring image detail.To improve this shortcoming, whenWhen, order, by adjustingmValue, retain image it is thin
In the case of section, noise is effectively filtered out.Function is feasible to illustrate the invention, orderValue is 10,mValue is 2, it was demonstrated that as follows：WithRepresent, usexRepresentW, then：
In the same manner
In the same manner
。
A kind of adaptive wavelet threshold functional image noise suppressing method proposed by the present invention, retain traditional soft-threshold and
On the basis of hard threshold function, limit of utilization thought, by the size for adjusting two major control variate-values, changes threshold function table
Expression formula, increase the reduction amplitude of wavelet coefficient, effectively reduce in certain threshold range wavelet coefficient and former coefficient it
Between deviation.Hard threshold function discontinuity at the threshold value is solved the problems, such as, while also improving soft-threshold function accordingly
The shortcoming of the error increase of estimation coefficient.
While there has been shown and described that specific embodiment of the invention, for one of ordinary skill in the art
Speech, it is possible to understand that these contents can be carried out without departing from the principles and spirit of the present invention various changes, modification,
Replace and modification, the scope of the present invention has claims and its equivalent to limit.
Claims (4)
1. a kind of adaptive wavelet threshold functional image noise suppressing method, it is characterised in that including implemented below step：
Step one, importing gray level image of the optional width containing Gaussian noise；
Step 2, wavelet decomposition is carried out to noise image, select suitable small echo and determine the level of decomposition, then carry out small echo
Conversion, obtains one group of wavelet coefficient；
Step 3, threshold value quantizing process is carried out to the small echo high frequency coefficient after wavelet decomposition, obtain that one group of threshold process crosses is little
Wave system number；
Step 4, the wavelet coefficient that threshold process is crossed is reconstructed, so as to obtain noise suppressed image.
2. a kind of adaptive wavelet threshold functional image noise suppressing method according to claim 1, it is characterised in that institute
State in step one, gray level image of the optional width containing Gaussian noise, Gaussian noise average is zero, and variance is not higher than 50.
3. a kind of adaptive wavelet threshold functional image noise suppressing method according to claim 1, it is characterised in that institute
State in step 2, wavelet decomposition is carried out to noise image, it is determined that the level for decomposing is four layers, the wavelet coefficient after being decomposed.
4. a kind of adaptive wavelet threshold functional image noise suppressing method according to claim 1, it is characterised in that institute
State in step 3, threshold value quantizing process is carried out to the high-frequency wavelet coefficient after wavelet decomposition；
Threshold size is：
In above formula, Represent threshold value,M×NThe size of image is represented, The standard variance of noise is represented, its expression formula is：
In above formula, Thresholding coefficient of wavelet decomposition is represented, its function expression is：
In above formula, sgn (x) for sign function, , With Zero control variable is greater than, its
It act as adjusting Size, the diminution as much as possible in certain threshold range WithW（Original wavelet coefficients）Between it is inclined
Difference,mAnd control variable, its value size pair Impact it is very big, experiment proves thatmSpan imitate between 1 to 5
Fruit is preferably；
When When, order , in order in the case where image detail is retained, effectively filter out noise, make in the present invention Value is 10,mValue is 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610999742.9A CN106570843A (en) | 2016-11-14 | 2016-11-14 | Adaptive wavelet threshold function image noise suppression method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610999742.9A CN106570843A (en) | 2016-11-14 | 2016-11-14 | Adaptive wavelet threshold function image noise suppression method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106570843A true CN106570843A (en) | 2017-04-19 |
Family
ID=58542239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610999742.9A Pending CN106570843A (en) | 2016-11-14 | 2016-11-14 | Adaptive wavelet threshold function image noise suppression method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106570843A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107247875A (en) * | 2017-06-07 | 2017-10-13 | 深圳众厉电力科技有限公司 | A kind of portable intelligent medical system |
| CN108510459A (en) * | 2018-04-08 | 2018-09-07 | 哈尔滨理工大学 | One kind is based on wavelet adaptive threshold and bilateral filtering image noise reduction algorithm |
| CN108596848A (en) * | 2018-04-20 | 2018-09-28 | 西南交通大学 | A kind of image de-noising method based on improvement wavelet threshold function |
| CN109085649A (en) * | 2018-10-12 | 2018-12-25 | 西南石油大学 | A kind of seismic data denoising method based on wavelet transformation optimization |
| CN109407732A (en) * | 2018-11-16 | 2019-03-01 | 江西省农业科学院作物研究所 | A kind of data processing system and method for the device of soilless cultivation sweet potato |
| CN109557429A (en) * | 2018-11-07 | 2019-04-02 | 国网浙江省电力有限公司电力科学研究院 | Based on the GIS partial discharge fault detection method for improving wavelet threshold denoising |
| CN112348031A (en) * | 2020-11-17 | 2021-02-09 | 安徽理工大学 | Improved wavelet threshold denoising method for removing fingerprint image mixed noise |
| CN112750090A (en) * | 2020-12-28 | 2021-05-04 | 大连海事大学 | Underwater image denoising method and system for improving wavelet threshold |
| CN117745572A (en) * | 2023-12-14 | 2024-03-22 | 国网江苏省电力有限公司南通供电分公司 | Denoising method of infrared image |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015049133A (en) * | 2013-08-31 | 2015-03-16 | 新協技研株式会社 | Surface defect inspection device and surface defect inspection method |
| CN105913393A (en) * | 2016-04-08 | 2016-08-31 | 暨南大学 | Self-adaptive wavelet threshold image de-noising algorithm and device |
-
2016
- 2016-11-14 CN CN201610999742.9A patent/CN106570843A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015049133A (en) * | 2013-08-31 | 2015-03-16 | 新協技研株式会社 | Surface defect inspection device and surface defect inspection method |
| CN105913393A (en) * | 2016-04-08 | 2016-08-31 | 暨南大学 | Self-adaptive wavelet threshold image de-noising algorithm and device |
Non-Patent Citations (1)
| Title |
|---|
| 田流芳: "基于中值滤波和小波变换的图像去噪算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107247875A (en) * | 2017-06-07 | 2017-10-13 | 深圳众厉电力科技有限公司 | A kind of portable intelligent medical system |
| CN108510459A (en) * | 2018-04-08 | 2018-09-07 | 哈尔滨理工大学 | One kind is based on wavelet adaptive threshold and bilateral filtering image noise reduction algorithm |
| CN108596848A (en) * | 2018-04-20 | 2018-09-28 | 西南交通大学 | A kind of image de-noising method based on improvement wavelet threshold function |
| CN108596848B (en) * | 2018-04-20 | 2020-06-30 | 西南交通大学 | Image denoising method based on improved wavelet threshold function |
| CN109085649A (en) * | 2018-10-12 | 2018-12-25 | 西南石油大学 | A kind of seismic data denoising method based on wavelet transformation optimization |
| CN109085649B (en) * | 2018-10-12 | 2020-02-28 | 西南石油大学 | Seismic data denoising method based on wavelet transformation optimization |
| CN109557429A (en) * | 2018-11-07 | 2019-04-02 | 国网浙江省电力有限公司电力科学研究院 | Based on the GIS partial discharge fault detection method for improving wavelet threshold denoising |
| CN109557429B (en) * | 2018-11-07 | 2021-08-27 | 国网浙江省电力有限公司电力科学研究院 | GIS partial discharge fault detection method based on improved wavelet threshold denoising |
| CN109407732A (en) * | 2018-11-16 | 2019-03-01 | 江西省农业科学院作物研究所 | A kind of data processing system and method for the device of soilless cultivation sweet potato |
| CN112348031A (en) * | 2020-11-17 | 2021-02-09 | 安徽理工大学 | Improved wavelet threshold denoising method for removing fingerprint image mixed noise |
| CN112750090A (en) * | 2020-12-28 | 2021-05-04 | 大连海事大学 | Underwater image denoising method and system for improving wavelet threshold |
| CN117745572A (en) * | 2023-12-14 | 2024-03-22 | 国网江苏省电力有限公司南通供电分公司 | Denoising method of infrared image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106570843A (en) | Adaptive wavelet threshold function image noise suppression method | |
| CN105303532B (en) | A kind of wavelet field Retinex image defogging methods | |
| CN108985179B (en) | Electric energy quality signal denoising method based on improved wavelet threshold function | |
| CN100550978C (en) | A kind of self-adapting method for filtering image that keeps the edge | |
| CN109242799B (en) | Variable-threshold wavelet denoising method | |
| CN108596848B (en) | Image denoising method based on improved wavelet threshold function | |
| Bijalwan et al. | Wavelet transform based image denoise using threshold approaches | |
| Abe et al. | Iterative Edge-Preserving adaptive Wiener filter for image denoising | |
| Deng et al. | A wavelet image denoising based on the new threshold function | |
| CN106067164B (en) | Color image contrast enhancement algorithms based on the processing of adaptive wavelet domain | |
| CN109409281A (en) | A kind of noise-reduction method based on improved wavelet threshold function | |
| CN105719658B (en) | Wavelet packet voice de-noising method based on new threshold function table and adaptive threshold | |
| uddin Khan et al. | An efficient image noise removal and enhancement method | |
| Wu et al. | Low-Light image enhancement algorithm based on HSI color space | |
| Thriveni | Satellite image enhancement using discrete wavelet transform and threshold decomposition driven morphological filter | |
| Lin et al. | Comparative analysis of image denoising methods based on wavelet transform and threshold functions | |
| Shetter et al. | Image de-noising algorithm based on filtering and histogram equalization | |
| Kumari et al. | A wavelet based denoising of speech signal | |
| Lasmika et al. | Improving Quality of Satellite Image by Wavelet Transforming & Morphological Filtering | |
| Joshi et al. | Comparative analysis of thresholding techniques using discrete wavelet transform | |
| Dhiman et al. | An improved threshold estimation technique for image denoising using wavelet thresholding techniques | |
| CN108665419B (en) | Image denoising method and device | |
| Jain et al. | Performance comparison of two image denoising algorithm at different noises | |
| Venkatachalam | A novel algorithm for image denoising using modified adaptive median filter | |
| WANG et al. | An improved wavelet threshold function and its application in image edge detection |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170419 |