CN108510459A - One kind is based on wavelet adaptive threshold and bilateral filtering image noise reduction algorithm - Google Patents
One kind is based on wavelet adaptive threshold and bilateral filtering image noise reduction algorithm Download PDFInfo
- Publication number
- CN108510459A CN108510459A CN201810305631.2A CN201810305631A CN108510459A CN 108510459 A CN108510459 A CN 108510459A CN 201810305631 A CN201810305631 A CN 201810305631A CN 108510459 A CN108510459 A CN 108510459A
- Authority
- CN
- China
- Prior art keywords
- image
- wavelet
- noise reduction
- threshold
- bilateral filtering
- 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
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 19
- 238000001914 filtration Methods 0.000 title claims abstract description 16
- 230000002146 bilateral effect Effects 0.000 title claims abstract description 14
- 238000011002 quantification Methods 0.000 claims abstract description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 7
- 238000002474 experimental method Methods 0.000 abstract description 2
- 230000003247 decreasing effect Effects 0.000 abstract 1
- 230000009466 transformation Effects 0.000 description 5
- 238000000034 method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000013519 translation Methods 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
- 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
- G06T2207/20024—Filtering details
- G06T2207/20028—Bilateral filtering
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses one kind based on wavelet adaptive threshold and bilateral filtering image noise reduction algorithm, including：The first step is to convert original image to gray level image, carries out small echo MALLAT and decomposes at many levels, obtains high fdrequency component on horizontal, vertical and diagonal three directions and with a low frequency component on scale；Second step is will to decompose obtained noise-containing three high fdrequency components using improved wavelet threshold function and improve adaptive thresholding algorithm progress quantification treatment；Third step is to recover original image using the high fdrequency component and a low frequency component progress wavelet reconstruction on three directions；4th step to obtain third step in imagery exploitation improve gray scale kernel function two-sided filter carry out image secondary filtering, just obtain the image after noise reduction；Y-PSNR is not only increased by above-mentioned image noise reduction algorithm known to emulation experiment, also so that mean square error has and is decreased obviously, it was demonstrated that validity of the algorithm to image noise reduction.
Description
Technical field
It is specifically a kind of to be based on wavelet adaptive threshold and bilateral filtering image noise reduction the present invention relates to image noise reduction field
Algorithm.
Background technology
The wavelet transformation of the title of " school microscop " is to be formed and be applied to rapidly in last century the eighties very much
One branch of mathematics of engineering field, it by a series of flexible and shift operations, realize to signal carry out part, appoint
Anticipate scale refinement analysis, be truly realized effectively handle non-stationary signal local feature, solve Fourier transformation without
The problem of method signal Analysis local feature.
Digital picture is in acquisition, transmission and transfer process, due to the mechanical movement of equipment, internal system circuit and device
The reasons such as material material itself make image be infected with noise, to seriously reduce the quality of image, while can also be further to image
Successive depths processing causes centainly to perplex；In image pre-processing phase, noise reduction process is vital, it is pictures subsequent
Segmentation, matching and identification even depth processing establish solid foundation and provide strong guarantee；Currently, being widely used in letter
Number, the wavelet transformation in image noise reduction field can pass through flexible translation transformation because it can do partial transformation in time domain and frequency domain
The good characteristics such as multiscale analysis are carried out to signal, are received more and more attention.
Invention content
The technical problem to be solved by the present invention is to propose one kind based on wavelet adaptive threshold and bilateral filtering image noise reduction
Algorithm has good image noise reduction effect, and to the edge-protected good of target image.
One kind is based on wavelet adaptive threshold and bilateral filtering image noise reduction algorithm, specific steps：
1, it converts original image to gray level image, carries out small echo MALLAT and decompose at many levels, obtain horizontal, vertical and right
High fdrequency component on the direction of three, angle and with a low frequency component on scale；
2, obtained noise-containing three high fdrequency components will be decomposed using improved wavelet threshold function and improved adaptive
Thresholding algorithm is answered to carry out quantification treatment；
3, using the high fdrequency component and a low frequency component progress wavelet reconstruction on three directions, original image is recovered；
4, the secondary filter of image is carried out using the two-sided filter for improving gray scale kernel function to the reconstructed image in 3 steps
Wave just obtains the image after noise reduction.
Preferably, the improved wavelet threshold function is
P is adjustable parameter in formula, and p takes 1,2,3 ... positive integer, ωi,jFor former wavelet coefficient, λ is threshold value,For threshold value
Estimation wavelet coefficient after quantization.
Preferably, the improved adaptive thresholding value expression is
J is decomposition scale in formula, and M and N are picture size size, σnoiseIt is poor for noise criteria.
Preferably, the improved gray scale kernel function expression formula is
L is image gray levels in formula, the gray value of pixel (i, j) centered on f (i, j), pixel centered on f (k, l)
The gray value of (i, j) neighborhood territory pixel point (k, l), Δ be normalized central pixel point and its neighborhood territory pixel point gray value it
Difference, T are bilateral filtering threshold value, and the standard deviation that T=exp (- σ), σ are pending image.
The present invention is compared with existing image noise reduction algorithm, improved wavelet threshold function and adaptive thresholding algorithm solution
It has determined between wavelet coefficient and former wavelet coefficient and has haveed the shortcomings that constant deviation and reconstruction accuracy are poor；Improved two-sided filter with
The mode that wavelet threshold combines, can protect image target edge and minutia to the maximum extent；For traditional hard threshold function
Discontinuously, cause Pseudo-Gibbs phenomenons occur after image reconstruction also all well to be solved；It is verified, is changed by emulation experiment
Into algorithm improve Y-PSNR, obtain good image noise reduction effect.
Description of the drawings
Fig. 1 is the image noise reduction flow chart of the present invention；
Fig. 2 is two layers of wavelet decomposition structural schematic diagram of gray level image of the present invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments；It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
As shown in Figure 1, a kind of based on wavelet adaptive threshold and bilateral filtering image noise reduction algorithm, image noise reduction it is specific
Steps are as follows：
1, it converts original image to gray level image, carries out small echo MALLAT and decompose at many levels, obtain horizontal, vertical and right
High fdrequency component on the direction of three, angle and with a low frequency component on scale；Double-layer structure schematic diagram such as Fig. 2 of wavelet decomposition
It is shown；
2, obtained noise-containing three high fdrequency components will be decomposed using improved wavelet threshold function and improved adaptive
Thresholding algorithm is answered to carry out quantification treatment；The improved wavelet threshold function expression of use is as follows
P is adjustable parameter in formula, and p takes 1,2,3 ... positive integer, ωi,jFor former wavelet coefficient, λ is threshold value,For threshold value
Estimation wavelet coefficient after quantization；The expression formula for improving adaptive threshold is as follows
J is decomposition scale in formula, and M and N are picture size size, σnoiseIt is poor for noise criteria；The decomposition scale J profits of use
It determines with the following method：
Enable cj,kAnd dj,kRespectively wavelet decomposition jth layer approaches wavelet coefficient and detail wavelet coefficients, and dj,kMean value
It is respectively formula (7) and (8) with mean variance,
Wherein NjIt is the detail wavelet coefficients d of jth layerj,kNumber；The then detail wavelet coefficients of the purified signal of jth layer
For
Purified signal wavelet coefficient is in jth layer
It enables
Threshold value η=0.9196 is set, when occurring ξ ＞ η for the first time, the number of plies decomposed at this time is exactly final small wavelength-division
Solve the number of plies.
3, using the high fdrequency component and a low frequency component progress wavelet reconstruction on three directions, original image is recovered；
4, the secondary filter of image is carried out using the two-sided filter for improving gray scale kernel function to the reconstructed image in 3 steps
Wave just obtains the image after noise reduction；The improved gray scale kernel function expression formula used is as follows
L is image gray levels in formula, the gray value of pixel (i, j) centered on f (i, j), pixel centered on f (k, l)
The gray value of (i, j) neighborhood territory pixel point (k, l), Δ be normalized central pixel point and its neighborhood territory pixel point gray value it
Difference, T are bilateral filtering threshold value, and the standard deviation that T=exp (- σ), σ are pending image.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms；Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Profit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent requirements of the claims
Variation is included within the present invention, and any reference signs in the claims should not be construed as limiting the involved claims.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiment being appreciated that.
Claims (4)
1. one kind is based on wavelet adaptive threshold and bilateral filtering image noise reduction algorithm, its step are as follows：
The first step converts original image to gray level image, carries out small echo MALLAT and decomposes at many levels, obtains horizontal, vertical and right
High fdrequency component on the direction of three, angle and with a low frequency component on scale；
Second step will decompose obtained noise-containing three high fdrequency components using improved wavelet threshold function and improve adaptive
Thresholding algorithm is answered to carry out quantification treatment；
Third step recovers original image using high fdrequency component and a low frequency component progress wavelet reconstruction on three directions；
4th step carries out the secondary of image to the reconstructed image in third step using the two-sided filter for improving gray scale kernel function
Filtering, just obtains the image after noise reduction.
2. one kind according to claim 1 is based on wavelet adaptive threshold and bilateral filtering image noise reduction algorithm, feature
It is：Improved wavelet threshold function is
P is adjustable parameter in formula, and p takes 1,2,3 ... positive integer, ωi,jFor former wavelet coefficient, λ is threshold value,For threshold value quantizing
Estimation wavelet coefficient afterwards.
3. one kind according to claim 1 is based on wavelet adaptive threshold and bilateral filtering image noise reduction algorithm, feature
It is：Improved adaptive thresholding value expression is
J is decomposition scale in formula, and M and N are picture size size, σnoiseIt is poor for noise criteria.
4. one kind according to claim 1 is based on wavelet adaptive threshold and bilateral filtering image noise reduction algorithm, feature
It is：Improved gray scale kernel function expression formula is
L is image gray levels in formula, the gray value of pixel (i, j) centered on f (i, j), pixel (i, j) centered on f (k, l)
The gray value of neighborhood territory pixel point (k, l), Δ are the difference of normalized central pixel point and the gray value of its neighborhood territory pixel point, and T is
Bilateral filtering threshold value, and the standard deviation that T=exp (- σ), σ are pending image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810305631.2A CN108510459A (en) | 2018-04-08 | 2018-04-08 | One kind is based on wavelet adaptive threshold and bilateral filtering image noise reduction algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810305631.2A CN108510459A (en) | 2018-04-08 | 2018-04-08 | One kind is based on wavelet adaptive threshold and bilateral filtering image noise reduction algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108510459A true CN108510459A (en) | 2018-09-07 |
Family
ID=63380668
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810305631.2A Pending CN108510459A (en) | 2018-04-08 | 2018-04-08 | One kind is based on wavelet adaptive threshold and bilateral filtering image noise reduction algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108510459A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109345475A (en) * | 2018-09-19 | 2019-02-15 | 长安大学 | A kind of unmanned aerial vehicle remote sensing mountain highway Image Fusion Filtering method |
| CN109447935A (en) * | 2018-11-16 | 2019-03-08 | 哈工大机器人（山东）智能装备研究院 | Infrared Image Processing Method, device, computer equipment and readable storage medium storing program for executing |
| CN110691229A (en) * | 2019-08-23 | 2020-01-14 | 昆明理工大学 | Hologram compression method, encoder and reproduced image output system |
| CN112750090A (en) * | 2020-12-28 | 2021-05-04 | 大连海事大学 | Underwater image denoising method and system for improving wavelet threshold |
| CN113034400A (en) * | 2021-04-07 | 2021-06-25 | 深圳鱼亮科技有限公司 | Image noise reduction method based on wireless image sensor array |
| CN113160080A (en) * | 2021-04-16 | 2021-07-23 | 桂林市啄木鸟医疗器械有限公司 | CR image noise reduction method, device, equipment and medium |
| CN114549353A (en) * | 2022-02-22 | 2022-05-27 | 中科微影(浙江)医疗科技有限公司 | Denoising method and system for nuclear magnetic resonance image |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101639938A (en) * | 2009-08-28 | 2010-02-03 | 浙江大学 | Image restoration method based on double-edge wave filter and margin deconvolution |
| CN102393423A (en) * | 2011-09-28 | 2012-03-28 | 南京信息工程大学 | Lamb wave denoising method based on adaptive threshold value orthogonal wavelet transform |
| CN103700072A (en) * | 2013-12-17 | 2014-04-02 | 北京工业大学 | Image denoising method based on self-adaptive wavelet threshold and two-sided filter |
| CN105787910A (en) * | 2015-12-24 | 2016-07-20 | 武汉鸿瑞达信息技术有限公司 | Method for optimizing calculation based on heterogeneous platform for human face area filtering method |
| CN105844601A (en) * | 2016-05-20 | 2016-08-10 | 中国矿业大学(北京) | Mine image enhancement method based on bilateral filtering and multi-scale Retinex algorithm |
| US20160330347A1 (en) * | 2007-06-26 | 2016-11-10 | Google Inc. | Method for noise-robust color changes in digital images |
| CN106570843A (en) * | 2016-11-14 | 2017-04-19 | 山东理工大学 | Adaptive wavelet threshold function image noise suppression method |
-
2018
- 2018-04-08 CN CN201810305631.2A patent/CN108510459A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160330347A1 (en) * | 2007-06-26 | 2016-11-10 | Google Inc. | Method for noise-robust color changes in digital images |
| CN101639938A (en) * | 2009-08-28 | 2010-02-03 | 浙江大学 | Image restoration method based on double-edge wave filter and margin deconvolution |
| CN102393423A (en) * | 2011-09-28 | 2012-03-28 | 南京信息工程大学 | Lamb wave denoising method based on adaptive threshold value orthogonal wavelet transform |
| CN103700072A (en) * | 2013-12-17 | 2014-04-02 | 北京工业大学 | Image denoising method based on self-adaptive wavelet threshold and two-sided filter |
| CN105787910A (en) * | 2015-12-24 | 2016-07-20 | 武汉鸿瑞达信息技术有限公司 | Method for optimizing calculation based on heterogeneous platform for human face area filtering method |
| CN105844601A (en) * | 2016-05-20 | 2016-08-10 | 中国矿业大学(北京) | Mine image enhancement method based on bilateral filtering and multi-scale Retinex algorithm |
| CN106570843A (en) * | 2016-11-14 | 2017-04-19 | 山东理工大学 | Adaptive wavelet threshold function image noise suppression method |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109345475A (en) * | 2018-09-19 | 2019-02-15 | 长安大学 | A kind of unmanned aerial vehicle remote sensing mountain highway Image Fusion Filtering method |
| CN109345475B (en) * | 2018-09-19 | 2021-07-23 | 长安大学 | Unmanned aerial vehicle remote sensing mountain road image fusion filtering method |
| CN109447935A (en) * | 2018-11-16 | 2019-03-08 | 哈工大机器人（山东）智能装备研究院 | Infrared Image Processing Method, device, computer equipment and readable storage medium storing program for executing |
| CN110691229A (en) * | 2019-08-23 | 2020-01-14 | 昆明理工大学 | Hologram compression method, encoder and reproduced image output system |
| CN110691229B (en) * | 2019-08-23 | 2021-10-22 | 昆明理工大学 | Hologram compression method, encoder and reproduced image output system |
| CN112750090A (en) * | 2020-12-28 | 2021-05-04 | 大连海事大学 | Underwater image denoising method and system for improving wavelet threshold |
| CN113034400A (en) * | 2021-04-07 | 2021-06-25 | 深圳鱼亮科技有限公司 | Image noise reduction method based on wireless image sensor array |
| CN113160080A (en) * | 2021-04-16 | 2021-07-23 | 桂林市啄木鸟医疗器械有限公司 | CR image noise reduction method, device, equipment and medium |
| CN113160080B (en) * | 2021-04-16 | 2023-09-22 | 桂林市啄木鸟医疗器械有限公司 | CR image noise reduction method, device, equipment and medium |
| CN114549353A (en) * | 2022-02-22 | 2022-05-27 | 中科微影(浙江)医疗科技有限公司 | Denoising method and system for nuclear magnetic resonance image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108510459A (en) | One kind is based on wavelet adaptive threshold and bilateral filtering image noise reduction algorithm | |
| CN100550978C (en) | A kind of self-adapting method for filtering image that keeps the edge | |
| CN105913393B (en) | A kind of adaptive wavelet threshold image de-noising method and device | |
| CN109242799A (en) | A kind of Wavelet noise-eliminating method of variable threshold value | |
| CN102663695A (en) | DR image denoising method based on wavelet transformation and system thereof | |
| Wang et al. | Hybrid image denoising method based on non‐subsampled contourlet transform and bandelet transform | |
| Routray et al. | Improving performance of K-SVD based image denoising using curvelet transform | |
| Jia et al. | Dual-complementary convolution network for remote-sensing image denoising | |
| CN109409281A (en) | A kind of noise-reduction method based on improved wavelet threshold function | |
| CN104809714A (en) | Image fusion method based on multi-morphological sparse representation | |
| CN107346532A (en) | A kind of porcelain shell for cable terminal Infrared Image Denoising method of correlation between consideration yardstick | |
| CN103310423A (en) | Mine image intensification method | |
| Yu et al. | An efficient edge-based bilateral filter for restoring real noisy image | |
| CN116884426A (en) | Voice enhancement method, device and equipment based on DFSMN model | |
| CN104462800B (en) | A kind of signal de-noising method based on wavelet frame | |
| CN102509268B (en) | Immune-clonal-selection-based nonsubsampled contourlet domain image denoising method | |
| CN109727200A (en) | Similar block based on Bayes's tensor resolution piles up Denoising method of images and system | |
| Ning et al. | Study on image compression and fusion based on the wavelet transform technology | |
| CN107563982A (en) | A kind of Enhancement Methods about Satellite Images | |
| CN103077503A (en) | Discrete cosine transform (DCT) dictionary synchronous sparse representation-based synthetic aperture radar (SAR) image speckle reduction method | |
| Zhang et al. | Image denoising based on the bivariate model of dual tree complex wavelet transform | |
| Qiaoman et al. | Application of adaptive median filter and wavelet transform to dongba manuscript images denoising | |
| Li et al. | Dictionary learning based image enhancement for rarity detection | |
| Geng et al. | Image compressed sensing recovery based on multi-scale group sparse representation | |
| CN103839235B (en) | Method for denoising global Bandelet transformation domain based on non-local directional correction |
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: 20180907 |