CN104616259B - A kind of adaptive non-local mean image de-noising method of noise intensity - Google Patents
A kind of adaptive non-local mean image de-noising method of noise intensity Download PDFInfo
- Publication number
- CN104616259B CN104616259B CN201510057999.8A CN201510057999A CN104616259B CN 104616259 B CN104616259 B CN 104616259B CN 201510057999 A CN201510057999 A CN 201510057999A CN 104616259 B CN104616259 B CN 104616259B
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- image
- denoising
- brightness
- 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.)
- Expired - Fee Related
Links
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a kind of adaptive non-local mean image de-noising method of noise intensity, GTG bar image is gathered first, different removing-noise strength parameter denoisings are used for using non-local mean method, the optimal removing-noise strength parameter under different brightness is obtained；The method for reusing linear interpolation, calculates the optimal removing-noise strength parameter corresponding to other brightness；Finally use under different brightness corresponding optimal removing-noise strength parameter in log-domain to image denoising, the image after log-domain denoising is subjected to exponential transform and obtains the image after final denoising.Instant invention overcomes the shortcoming that removing-noise strength parameter in existing method is fixed, the denoising effect of image is improved；Contribute to increase the difference of dark areas pixel intensity in log-domain processing simultaneously, reduce the difference of bright area, be more beneficial for improving the denoising effect of image.
Description
Technical field
The invention belongs to digital image processing techniques field, it is related to a kind of adaptive non-local mean image of noise intensity
Denoising method.
Background technology
Digital picture is inevitably disturbed during acquisition by various noise signals so that image matter
Amount is degenerated, so as to influence the image characteristics extraction in later stage, Target Segmentation and target identification, thus image denoising have it is important
Actual application value.
Image de-noising method can be divided into the method based on spatial domain and the major class of the method based on transform domain two.Based on spatial domain
Method has the methods such as the bilateral filtering based on single pixel grey similarity, gaussian filtering, and the method based on transform domain is for example various
Image de-noising method based on wavelet transformation etc..Traditional spatial domain denoising method is handled based on single pixel information,
Weak edge and grain details can not be retained well, and the non-local mean denoising method proposed by Buades is then using local
The information of image block, can preferably express the structural information of image, therefore its performance is better than other classical Denoising Algorithms, such as bilateral
Filtering, PDE, method based on small echo etc..
The characteristics of having succinct algorithm, superior performance due to non-local mean method, be easily modified with extension, is current reality
A kind of main stream approach in the application of border.But this method in practical application, to entire image use identical removing-noise strength parameter,
Cause the denoising effect of different luminance areas in image not ideal enough.It is contemplated that strong according to the different luminance area noises of image
The inconsistent feature of degree distribution, by testing the denoising effect in grayscale bar under different brightness, the denoising ginseng of selection varying strength
Number, can preferably adapt to the uneven situation of noise profile, thus can obtain better image denoising effect.
The content of the invention
It is existing to solve it is an object of the invention to provide a kind of adaptive non-local mean image de-noising method of noise intensity
The undesirable technology of image denoising effect that some non-local mean denoising methods are caused using identical removing-noise strength parameter is asked
Topic.
The technical solution adopted by the present invention is that a kind of adaptive non-local mean image de-noising method of noise intensity has
Body includes following methods step：
Step 1：GTG bar image is gathered, computer is inputted, GTG bar image is designated as z (i), wherein i represents picture
Vegetarian refreshments, z represents the brightness value of the pixel, and the different luminance area of GTG bar is designated as into Xm；
Step 2：Obtain the optimal removing-noise strength parameter under different brightness；
2.1, denoising is carried out to GTG bar image z (i) under different removing-noise strength parameters using non-local mean method, with
Obtain different brightness YmCorresponding optimal removing-noise strength parameter gm, it is designated as (gm,Ym), YmFor luminance area XmAverage brightness；
2.2, obtained using linear interpolation method and be different from brightness YmBrightness PnCorresponding optimal removing-noise strength parameter qn；
Step 3：It is different bright that the corresponding optimal denoising parameter of different brightness obtained according to step 2 treats the progress of denoising image
Noise intensity self-adaptive solution under degree.
The features of the present invention is also resided in,
The detailed process of step 2.1 is：
2.1.1, using denoising formula to GTG bar image z (i) denoisings：
By removing-noise strength parameter h since 1, change value successively from small to large, to going for GTG bar image z (i)
Make an uproar, obtain a series of image after denoisings, wherein, removing-noise strength parameter h value is：h1=1, hk=10 (k-1), 2≤k≤
101, k be integer, hkK-th of removing-noise strength parameter is represented, denoising formula is as follows：
NLM (i)=∑ ω (i, j) z (j)
Wherein, NLM (i) is that, using the image after non-local mean method denoising, ω (i, j) is represented by gray scale image z (i)
Weight between pixel i and j, and meet 0≤ω (i, j)≤1 andJ is 21 × 21 regions centered on i
Pixel；C (i) is normalization factor, NiRepresent 7 × 7 image block centered on pixel i, NjRepresent centered on pixel j
7 × 7 image block；
Step 2.1.2, calculates each luminance area X of GTG bar image z (i)mUsing different removing-noise strength parameter hiDenoising
The Y-PSNR PSNR of a series of images obtained afterwards, chooses each luminance area XmIn a series of images obtained after denoising
Removing-noise strength parameter h corresponding to image maximum Y-PSNR PSNRiIt is used as corresponding bright region XmOptimal removing-noise strength
Parameter, is designated as gm, and calculate each luminance area XmAverage brightness Ym, by each luminance area XmUnder optimal removing-noise strength
Parameter and average brightness are expressed as (gm,Ym)；
Y-PSNR PSNR calculation formula is：
Wherein, M represents luminance area XmSum of all pixels；
The average brightness Y of each luminance areamCalculation formula is：
The detailed process of step 2.2 is：
If brightness PnNot in (gm,Ym) among, then from (gm,Ym) among find most close two neighboring bright with its numerical value
Average value is spent, Y is designated as respectivelyjAnd Yj+1, wherein YjLess than Pn, Yj+1More than Pn, YjAnd Yj+1In (gm,Ym) in corresponding denoising it is strong
It is respectively g to spend parameterjAnd gj+1, then brightness PnCorresponding optimal removing-noise strength parameter qnCalculated and tried to achieve by linear interpolation formula,
Linear interpolation formula is：
The detailed process of step 3 is：
3.1, it will treat that the graphical representation of denoising, for g (x, y), natural logrithm conversion is carried out to it, transformation results are g1(x,y)
=lng (x, y)；
3.2, in log-domain to g1(x, y) carries out denoising using non-local mean method, is specially：
To g1Each pixel (x, y) of (x, y), using the corresponding optimal denoising of its original image g (x, y) brightness value
Intensive parameter h, according to denoising formula to g1(x, y) denoising, obtains the image after denoising, is designated as g2(x,y)；
3.3, to g2(x, y) carry out exponential transform, obtain the image h (x, y) after final denoising, as a result for h (x, y)=
exp(g2(x,y)。
The beneficial effects of the invention are as follows the present invention is non-by being carried out to GTG bar image using different removing-noise strength parameters
Then local mean value denoising, the optimal removing-noise strength parameter sought under different brightness is joined to image using different removing-noise strengths
Number denoising, overcomes the defect that removing-noise strength parameter is fixed in existing non-local mean denoising method, improves image difference bright
Spend the denoising effect in region.Meanwhile, contribute to increase the difference of dark areas pixel intensity in log-domain processing, reduce bright area
Difference, further improves the denoising effect of image.
Brief description of the drawings
Fig. 1 is a kind of flow chart of the adaptive non-local mean image de-noising method of noise intensity of the invention；
Fig. 2 is the image for treating denoising；
Fig. 3 is using the later image of the inventive method denoising.
Embodiment
Below by the drawings and specific embodiments, the present invention is described in detail.
The invention provides a kind of adaptive non-local mean image de-noising method of noise intensity, specifically according to following step
It is rapid to implement：
Step 1：The GTG bar image on KODAK Gray Scale GTG cards is gathered, computer is inputted, the GTG
Bar image is included from black to the region of totally 20 different brightness in vain, GTG bar image is designated as into z (i), wherein i represents pixel, z
The brightness value of the pixel is represented, luminance area is designated as Xm, 1≤m≤20；
Step 2：The optimal removing-noise strength parameter under different brightness is obtained, detailed process is as follows：
Step 2.1, using non-local mean algorithm, gray scale image z (i) is gone using different removing-noise strength parameters
Make an uproar, to obtain different brightness YmCorresponding optimal removing-noise strength parameter gm, it is designated as (gm,Ym| m=1,2......20), YmFor brightness
Region XmAverage brightness：
Step 2.1.1, using denoising formula to GTG bar image z (i) denoisings：
By removing-noise strength parameter h since 1, change value successively from small to large, to going for GTG bar image z (i)
Make an uproar, obtain a series of image after denoisings, wherein, removing-noise strength parameter h value is：h1=1, hk=10 (k-1), 2≤k≤
101, k be integer, hkK-th of removing-noise strength parameter is represented, denoising formula is as follows：
NLM (i)=∑ ω (i, j) z (j) (1)
Wherein, NLM (i) is that, using the image after non-local mean method denoising, ω (i, j) is represented by gray scale image z (i)
Weight between pixel i and j, and meet 0≤ω (i, j)≤1 andJ is 21 × 21 regions centered on i
Pixel；C (i) is normalization factor, NiRepresent 7 × 7 image block centered on pixel i, NjRepresent centered on pixel j
7 × 7 image block；
Step 2.1.2, calculates each luminance area X of GTG bar image z (i)mUsing different removing-noise strength parameter hiDenoising
The Y-PSNR PSNR of a series of images obtained afterwards, chooses each luminance area XmIn a series of images obtained after denoising
Removing-noise strength parameter h corresponding to image maximum Y-PSNR PSNRiIt is used as corresponding bright region XmOptimal removing-noise strength
Parameter, is expressed as gm, and calculate each luminance area XmAverage brightness Ym, by each luminance area XmUnder optimal denoising it is strong
Degree parameter and average brightness are expressed as (gm,Ym| m=1,2......20)；
Y-PSNR PSNR calculation formula is：
Wherein, M represents luminance area XmSum of all pixels；
The average brightness calculation formula of each luminance area is：
Wherein, M represents luminance area XmSum of all pixels；
Step 2.2, obtained using linear interpolation method and be different from brightness YmBrightness PnCorresponding optimal removing-noise strength parameter
qn, it is specially：
If brightness PnNot in (gm,Ym| m=1,2......20) among, then from (gm,Ym| m=1,2......20) among
Find with its numerical value most close two neighboring average brightness, Y is designated as respectivelyjAnd Yj+1, wherein YjLess than Pn, Yj+1More than Pn,
YjAnd Yj+1In (gm,Ym| m=1,2......20) in corresponding removing-noise strength parameter be respectively gjAnd gj+1, then brightness PnIt is corresponding
Optimal removing-noise strength parameter qnCalculated and tried to achieve by linear interpolation formula, linear interpolation formula is：
Step 3, it is different bright that the corresponding optimal denoising parameter of different brightness obtained according to step 2 treats the progress of denoising image
Noise intensity self-adaptive solution under degree, detailed process is：
Step 3.1, it will treat that the graphical representation of denoising, for g (x, y), natural logrithm conversion is carried out to it, transformation results are g1
(x, y)=lng (x, y)；
Step 3.2, in log-domain to g1(x, y) carries out denoising using non-local mean method, is specially：
To g1Each pixel (x, y) of (x, y), using the corresponding optimal denoising of its original image g (x, y) brightness value
Intensive parameter h, according to the denoising formula in step 2 to g1(x, y) denoising, obtains the image after denoising, is designated as g2(x,y)；
Step 3.3), to g2(x, y) carry out exponential transform, obtain the image h (x, y) after final denoising, as a result for h (x,
Y)=exp (g2(x,y))。
The different brightness cases in sign natural image from black to white can be very good using GTG bar image in the present invention,
By using different removing-noise strength parameters to the GTG bar image denoising, the suitable strength denoising ginseng under each brightness can be found
Optimal removing-noise strength parameter under number, and all brightness of method acquisition for passing through interpolation, goes so as to be applied to real image
Make an uproar, the denoising parameter of varying strength can be used to the pixel of the different brightness of each in real image, acquisition is preferably gone
Make an uproar effect.
Fig. 3 is to use the design sketch after the final denoising of the inventive method to the image of Fig. 2 Noises, as can be seen from Figure 3
Obtain that the image denoising effect after denoising is good using the inventive method, edge details of image etc. have obtained preferable reservation.
Claims (4)
1. the adaptive non-local mean image de-noising method of a kind of noise intensity, it is characterised in that specifically include following steps：
Step 1：GTG bar image is gathered, computer is inputted, GTG bar image is designated as z (i), wherein i represents pixel,
Z represents the brightness value of the pixel, and the different luminance area of GTG bar is designated as into Xm；
Step 2：Obtain the optimal removing-noise strength parameter under different brightness；
2.1, denoising is carried out to GTG bar image z (i) under different removing-noise strength parameters using non-local mean method, to obtain
Different brightness YmCorresponding optimal removing-noise strength parameter gm, it is designated as (gm,Ym), YmFor luminance area XmAverage brightness；
2.2, obtained using linear interpolation method and be different from brightness YmBrightness PnCorresponding optimal removing-noise strength parameter qn；
Step 3：The corresponding optimal denoising parameter of different brightness obtained according to step 2 is treated denoising image and carried out under different brightness
Noise intensity self-adaptive solution.
2. a kind of adaptive non-local mean image de-noising method of noise intensity according to claim 1, its feature exists
In the detailed process of the step 2.1 is：
2.1.1, using denoising formula to GTG bar image z (i) denoisings：
By removing-noise strength parameter h since 1, change value successively from small to large, the carry out denoising to GTG bar image z (i) is obtained
A series of image to after denoisings, wherein, removing-noise strength parameter h value is：h1=1, hk=10 (k-1), 2≤k≤101, k
For integer, hkK-th of removing-noise strength parameter is represented, denoising formula is as follows：
NLM (i)=∑ ω (i, j) z (j)
<mrow>
<mi>&omega;</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mi>C</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<mo>-</mo>
<mfrac>
<mrow>
<mo>|</mo>
<mo>|</mo>
<mi>z</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>N</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mi>z</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>N</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>|</mo>
<msubsup>
<mo>|</mo>
<mn>2</mn>
<mn>2</mn>
</msubsup>
</mrow>
<msup>
<mi>h</mi>
<mn>2</mn>
</msup>
</mfrac>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mi>C</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munder>
<mi>&Sigma;</mi>
<mi>j</mi>
</munder>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<mo>-</mo>
<mfrac>
<mrow>
<mo>|</mo>
<mo>|</mo>
<mi>z</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>N</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mi>z</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>N</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>|</mo>
<msubsup>
<mo>|</mo>
<mn>2</mn>
<mn>2</mn>
</msubsup>
</mrow>
<msup>
<mi>h</mi>
<mn>2</mn>
</msup>
</mfrac>
<mo>)</mo>
</mrow>
<mo>;</mo>
</mrow>
Wherein, NLM (i) is that, using the image after non-local mean method denoising, ω (i, j) represents pixel by gray scale image z (i)
Weight between i and j, and meet 0≤ω (i, j)≤1 andJ is the picture in 21 × 21 regions centered on i
Element；C (i) is normalization factor, NiRepresent 7 × 7 image block centered on pixel i, NjRepresent centered on pixel j 7 ×
7 image block；
2.1.2, each luminance area X of GTG bar image z (i) are calculatedmUsing different removing-noise strength parameter hiObtained after denoising
The Y-PSNR PSNR of a series of images, chooses each luminance area XmPeak value noise in a series of images obtained after denoising
Removing-noise strength parameter h than PSNR corresponding to maximum imageiIt is used as corresponding bright region XmOptimal removing-noise strength parameter, note
For gm, and calculate each luminance area XmAverage brightness Ym, by each luminance area XmUnder optimal removing-noise strength parameter and bright
Degree average value is expressed as (gm,Ym)；
Y-PSNR PSNR calculation formula is：
<mrow>
<mi>P</mi>
<mi>S</mi>
<mi>N</mi>
<mi>R</mi>
<mo>=</mo>
<mn>10</mn>
<mi>l</mi>
<mi>o</mi>
<mi>g</mi>
<mrow>
<mo>(</mo>
<mfrac>
<msup>
<mn>255</mn>
<mn>2</mn>
</msup>
<mrow>
<mfrac>
<mn>1</mn>
<mi>M</mi>
</mfrac>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>M</mi>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<mi>N</mi>
<mi>L</mi>
<mi>M</mi>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
<mo>-</mo>
<mi>z</mi>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</mfrac>
<mo>)</mo>
</mrow>
<mo>;</mo>
</mrow>
Wherein, M represents luminance area XmSum of all pixels；
The average brightness Y of each luminance areamCalculation formula is：
<mrow>
<msub>
<mi>Y</mi>
<mi>m</mi>
</msub>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mi>M</mi>
</mfrac>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>M</mi>
</munderover>
<mi>z</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>.</mo>
</mrow>
3. a kind of adaptive non-local mean image de-noising method of noise intensity according to claim 1, its feature exists
In the detailed process of the step 2.2 is：
If brightness PnNot in (gm,Ym) among, then from (gm,Ym) among find and put down with the most close two neighboring brightness of its numerical value
Average, is designated as Y respectivelyjAnd Yj+1, wherein YjLess than Pn, Yj+1More than Pn, YjAnd Yj+1In (gm,Ym) in corresponding removing-noise strength ginseng
Number is respectively gjAnd gj+1, then brightness PnCorresponding optimal removing-noise strength parameter qnCalculated and tried to achieve by linear interpolation formula, linearly
Interpolation formula is：
<mrow>
<msub>
<mi>q</mi>
<mi>n</mi>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<mo>|</mo>
<mrow>
<msub>
<mi>P</mi>
<mi>n</mi>
</msub>
<mo>-</mo>
<msub>
<mi>Y</mi>
<mi>j</mi>
</msub>
</mrow>
<mo>|</mo>
</mrow>
<mrow>
<mo>|</mo>
<mrow>
<msub>
<mi>Y</mi>
<mrow>
<mi>j</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>Y</mi>
<mi>j</mi>
</msub>
</mrow>
<mo>|</mo>
</mrow>
</mfrac>
<mo>&times;</mo>
<msub>
<mi>g</mi>
<mi>j</mi>
</msub>
<mo>+</mo>
<mfrac>
<mrow>
<mo>|</mo>
<mrow>
<msub>
<mi>Y</mi>
<mrow>
<mi>j</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>P</mi>
<mi>n</mi>
</msub>
</mrow>
<mo>|</mo>
</mrow>
<mrow>
<mo>|</mo>
<mrow>
<msub>
<mi>Y</mi>
<mrow>
<mi>j</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>Y</mi>
<mi>j</mi>
</msub>
</mrow>
<mo>|</mo>
</mrow>
</mfrac>
<mo>&times;</mo>
<msub>
<mi>g</mi>
<mrow>
<mi>j</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>.</mo>
</mrow>
4. a kind of adaptive non-local mean image de-noising method of noise intensity according to claim 2, its feature exists
In the detailed process of the step 3 is：
3.1, it will treat that the graphical representation of denoising, for g (x, y), natural logrithm conversion is carried out to it, transformation results are g1(x, y)=lng
(x,y)；
3.2, in log-domain to g1(x, y) carries out denoising using non-local mean method, is specially：
To g1Each pixel (x, y) of (x, y), using the corresponding optimal removing-noise strength of its original image g (x, y) brightness value
Parameter h, according to denoising formula to g1(x, y) denoising, obtains the image after denoising, is designated as g2(x,y)；
3.3, to g2(x, y) carries out exponential transform, obtains the image h (x, y) after final denoising, is as a result h (x, y)=exp (g2
(x,y))。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510057999.8A CN104616259B (en) | 2015-02-04 | 2015-02-04 | A kind of adaptive non-local mean image de-noising method of noise intensity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510057999.8A CN104616259B (en) | 2015-02-04 | 2015-02-04 | A kind of adaptive non-local mean image de-noising method of noise intensity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104616259A CN104616259A (en) | 2015-05-13 |
| CN104616259B true CN104616259B (en) | 2017-08-25 |
Family
ID=53150692
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510057999.8A Expired - Fee Related CN104616259B (en) | 2015-02-04 | 2015-02-04 | A kind of adaptive non-local mean image de-noising method of noise intensity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104616259B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105913427B (en) * | 2016-04-12 | 2017-05-10 | 福州大学 | Machine learning-based noise image saliency detecting method |
| CN106228515A (en) * | 2016-07-13 | 2016-12-14 | 凌云光技术集团有限责任公司 | A kind of image de-noising method and device |
| CN110390643B (en) * | 2018-04-20 | 2022-04-26 | 杭州海康威视数字技术股份有限公司 | License plate enhancement method and device and electronic equipment |
| CN110533602A (en) * | 2019-07-19 | 2019-12-03 | 中国石油天然气集团有限公司 | Inner buried hill image enhancement method and apparatus based on signal-to-noise ratio field dynamic constrained |
| CN114155161B (en) * | 2021-11-01 | 2023-05-09 | 富瀚微电子(成都)有限公司 | Image denoising method, device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020918A (en) * | 2013-01-09 | 2013-04-03 | 西安电子科技大学 | Shape-adaptive neighborhood mean value based non-local mean value denoising method |
| CN103093433A (en) * | 2013-01-25 | 2013-05-08 | 西安电子科技大学 | Natural image denoising method based on regionalism and dictionary learning |
| CN103955903A (en) * | 2014-05-09 | 2014-07-30 | 东南大学 | Weight window self-adaptation non-local mean image denoising method |
| CN104036465A (en) * | 2014-06-17 | 2014-09-10 | 南京邮电大学 | Edge detection based on self-adaptive nonlocal mean denoising method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130202079A1 (en) * | 2012-02-07 | 2013-08-08 | Lifeng Yu | System and Method for Controlling Radiation Dose for Radiological Applications |
| CN103686194B (en) * | 2012-09-05 | 2017-05-24 | 北京大学 | Video denoising method and device based on non-local mean value |
-
2015
- 2015-02-04 CN CN201510057999.8A patent/CN104616259B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020918A (en) * | 2013-01-09 | 2013-04-03 | 西安电子科技大学 | Shape-adaptive neighborhood mean value based non-local mean value denoising method |
| CN103093433A (en) * | 2013-01-25 | 2013-05-08 | 西安电子科技大学 | Natural image denoising method based on regionalism and dictionary learning |
| CN103955903A (en) * | 2014-05-09 | 2014-07-30 | 东南大学 | Weight window self-adaptation non-local mean image denoising method |
| CN104036465A (en) * | 2014-06-17 | 2014-09-10 | 南京邮电大学 | Edge detection based on self-adaptive nonlocal mean denoising method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104616259A (en) | 2015-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yu et al. | Image denoising using trivariate shrinkage filter in the wavelet domain and joint bilateral filter in the spatial domain | |
| Ghani et al. | Enhancement of low quality underwater image through integrated global and local contrast correction | |
| CN104616259B (en) | A kind of adaptive non-local mean image de-noising method of noise intensity | |
| CN104463804B (en) | Image enhancement method based on intuitional fuzzy set | |
| CN111583123A (en) | Wavelet transform-based image enhancement algorithm for fusing high-frequency and low-frequency information | |
| Xu et al. | Structure-texture aware network for low-light image enhancement | |
| CN104574293A (en) | Multiscale Retinex image sharpening algorithm based on bounded operation | |
| Zhang et al. | Decision-based non-local means filter for removing impulse noise from digital images | |
| CN102930508A (en) | Image residual signal based non-local mean value image de-noising method | |
| Mustafa et al. | Image enhancement technique on contrast variation: a comprehensive review | |
| Liu et al. | True wide convolutional neural network for image denoising | |
| CN107516302A (en) | A kind of method of the mixed image enhancing based on OpenCV | |
| CN107146202B (en) | Image blind deblurring method based on L0 regularization and fuzzy kernel post-processing | |
| CN115809966A (en) | Low-illumination image enhancement method and system | |
| CN106981052B (en) | Adaptive uneven brightness variation correction method based on variation frame | |
| Maragatham et al. | Contrast enhancement by object based histogram equalization | |
| Josephus et al. | Multilayered contrast limited adaptive histogram equalization using frost filter | |
| Ein-shoka et al. | Quality enhancement of infrared images using dynamic fuzzy histogram equalization and high pass adaptation in DWT | |
| Asghar et al. | Automatic enhancement of digital images using cubic Bézier curve and Fourier transformation | |
| El Hassani et al. | Efficient image denoising method based on mathematical morphology reconstruction and the Non-Local Means filter for the MRI of the head | |
| CN110545414B (en) | Image sharpening method | |
| Cho et al. | Enhancement technique of image contrast using new histogram transformation | |
| CN114359083B (en) | High-dynamic thermal infrared image self-adaptive preprocessing method for interference environment | |
| Parihar | Histogram modification and DCT based contrast enhancement | |
| Cao et al. | A License Plate Image Enhancement Method in Low Illumination Using BEMD. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170825 Termination date: 20210204 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |