CN1917577A - Method of reducing noise for combined images - Google Patents
Method of reducing noise for combined images Download PDFInfo
- Publication number
- CN1917577A CN1917577A CN 200610030746 CN200610030746A CN1917577A CN 1917577 A CN1917577 A CN 1917577A CN 200610030746 CN200610030746 CN 200610030746 CN 200610030746 A CN200610030746 A CN 200610030746A CN 1917577 A CN1917577 A CN 1917577A
- Authority
- CN
- China
- Prior art keywords
- noise reduction
- sigma
- image
- contourlet
- centerdot
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Image Processing (AREA)
Abstract
The method comprises: the Contourlet transformation is used to make the multi-scaling and multi-directional sparse decomposition for the inputted noisy image; making a noise reduction on Contourlet domain using Bayes shrinkage threshold value method; and getting the pre noise reduction image using Contourlet inverse transform; making further noise reduction for the pre noise reduction image using Wiener filter method to get final noise-reduced image. The invention can be used in optical imaging, target detection and security monitoring.
Description
Technical field
The present invention relates to a kind of method of reducing noise for combined images, this method adopts based on the method for reducing noise for combined images that moves constant Contourlet (profile small echo) transform domain noise reduction and Wei Na (Wiener) filtering, removes the noise in the image, to improve picture quality.In systems such as military field and non-military field such as optical imagery, target detection, security monitoring, all be widely used.
Background technology
Usually, the image that we obtain all is subjected to noise pollution in various degree, and for follow-up further processing, the necessary noise reduction process of carrying out leaches noise, and keeps all characteristic informations of image as much as possible, to improve the recovery quality of image.At present, image denoising method mainly contains: airspace filter, and as mean filter and medium filtering etc., and transform domain filtering, as low-pass filtering etc.
Nearly 20, wavelet transformation has obtained using widely at signal and image processing field, and successfully has been applied to the image noise reduction field with its good time-frequency characteristic and multiresolution thought.But, the two-dimentional separable wavelets conversion that is formed by tensor product by the one dimension small echo can only represent effectively that the unusual information of one dimension promptly puts unusual information, and two dimension or the unusual information of higher-dimension in the image can not be described effectively, as important informations such as line, profiles, thereby restricted the performance of wavelet de-noising method.
The Contourlet conversion is as a kind of new signal analysis instrument, solved wavelet transformation and can not effectively represent the two dimension or the shortcoming of higher-dimension singularity more, can exactly the edge in the image be captured in the subband of different scale, different frequency, different directions.It not only has the multiple dimensioned characteristic of wavelet transformation, also has directivity and anisotropy that wavelet transformation does not have, and therefore the contour feature in the presentation video that can be more sparse can be advantageously applied in the image processing, comprises the image noise reduction aspect.Because, the Contourlet conversion lacks translation invariance, in noise reduction process, can produce pseudo-gibbs (Gibbs) phenomenon, circulation translation (Cycle Spinning) method can be used for suppressing the pseudo-Gibbs phenomenon that Contourlet territory threshold value noise-reduction method produces, anti-acoustic capability obviously is better than the wavelet threshold noise-reduction method, has improved the performance of noise-reduction method to a great extent.But actual conditions show that this method can't be removed noise fully, and still residual small amount of noise influences picture quality in the noise reduction image, need take further noise reduction process.
Summary of the invention
The objective of the invention is to deficiency, proposed a kind of method of reducing noise for combined images, be used for removing the noise of image, to improve picture quality at the existence of conventional images noise-reduction method.
In order to achieve the above object, the present invention adopts following technical proposals:
A kind of method of reducing noise for combined images.It is characterized in that adopting method of reducing noise for combined images based on moving constant Contourlet transform domain noise reduction and Wiener filtering, this method is earlier in the Contourlet territory, obey generalized Gaussian distribution according to coefficient, choose Bayes (Bayes) collapse threshold, improve the effect of image noise reduction.Then,, adopt the Wiener filtering method to carry out further noise reduction process, reach the purpose of image noise reduction again to pre-noise reduction image through obtaining behind the noise reduction of Contourlet territory.
Suppose that the noise image that observes is
I=f+n (1)
Wherein f is an original image, n be independent identically distributed white Gaussian noise signal N (0, σ
2).
The concrete steps of above-mentioned noise-reduction method are as follows:
1. beginningization setting.Make i=0, j=0 sets the maximal translation amount N on line direction and the column direction
1And N
2The middle LP that sets the Contourlet conversion simultaneously decomposes the direction Number of Decomposition L in number of plies K and every layer
k
2. the noisy image I of input is expert at and column direction on carry out the circulation translation of the significance bit amount of moving, obtain the translation image
S
ij=C
i,j(I), (2)
Wherein i ∈ (0, N
1) and j ∈ (0, N
2) be respectively the translational movement on line direction and the column direction;
3. the translation image S to obtaining
IjCarry out the sparse decomposition of multiple dimensioned, multidirectional Contourlet, promptly
Wherein T () is the Contourlet conversion.Thereby obtain a width of cloth low frequency subgraph as S
LfWith a series of high frequency subimage S with different resolution
Hf (k, l), wherein k ∈ (1, K) and l ∈ (1, L
k) indicate that subimage is positioned at the l direction of k layer LP (the tower decomposition of Laplce);
4. to the high frequency subimage S after the Contourlet conversion
Hf (k, l)Carry out the threshold value noise reduction process, obtain the noise reduction subimage,
Wherein, Λ () is a threshold function table, T
BBe threshold parameter.Obey generalized Gaussian distribution according to the Contourlet domain coefficient, select the Bayes threshold value for use
5. all noise reduction high frequency subimage S that obtain in going on foot the 4th
Dhf (k, l)With the low frequency subgraph that obtains in the 3rd step as S
LfImplement the Contourlet inverse transformation, obtain the noise reduction image behind difference translation i and j on line direction and the column direction,
Wherein, T
-1() is the Contourlet inverse transformation;
6. the image S that obtains in going on foot the 5th
I, j NfCarry out the reverse circulation translation of corresponding translational movement, have
7. repeating step 2 to 6, up to i=N
1And j=N
2Till, stop repetition;
8. all I to obtaining
I, j Nf(i=0 ..., N
1J=0 ..., N
2) ask average, obtain the pre-noise reduction image:
9. the pre-noise reduction image that previous step is obtained
Further carry out the Wiener Filtering Processing, obtain final noise reduction result
T in the 4th above-mentioned step
BThe concrete estimating step of value is:
1. for noise criteria difference σ
n, adopt the intermediate value of robustness to estimate,
S wherein
Hf (K, i)(i=1 ... L
K) be the highest frequency coefficient;
2. by
Have
Wherein,
S
Hf (k, i)It is the high frequency coefficient of being considered;
3. therefore can get threshold parameter
The inventive method has following conspicuous outstanding substantive distinguishing features and remarkable advantage compared with prior art:
This invention aims to provide a kind of method of reducing noise for combined images, at first the noisy image by the input of Contourlet transfer pair carries out multiple dimensioned, multidirectional sparse decomposition, obey generalized Gaussian distribution according to the Contourlet coefficient in transform domain then, carry out Bayes collapse threshold method noise reduction in the Contourlet territory, and obtain the pre-noise reduction image by the Contourlet inverse transformation, at last, adopt the Wiener filter method that the pre-noise reduction image is carried out further noise reduction process, to improve the recovery precision of image.Concrete characteristics and advantage are:
(1)------be two or higher-dimension singularity in the presentation video effectively at the shortcoming of wavelet transformation in the most representative existing wavelet field threshold value noise-reduction method, the Contourlet conversion is applied in the image noise reduction, carry out multiple dimensioned, multi-direction decomposition, for follow-up noise reduction process provides sparse iamge description coefficient.
(2) deficiency that the conventional images noise reduction technology is existed has proposed a kind of method of reducing noise for combined images, promptly based on the method for reducing noise for combined images that moves constant Contourlet transform domain noise reduction and Wiener filtering.
(3) the inventive method is in the image noise reduction stage of Contourlet transform domain, Contourlet domain coefficient at image is obeyed generalized Gaussian distribution (GGD), satisfying the assumed conditions of Bayes method of estimation---signal is obeyed generalized Gaussian distribution, employing is estimated threshold value based on Bayes, carry out noise reduction, improved anti-acoustic capability.
(4) the inventive method can not be removed noise fully at the image denoising method of Contourlet transform domain, and still residual small amount of noise in the noise reduction image is taked the further noise reduction process of Wiener filter method.
Image denoising method provided by the invention can improve the noise reduction image quality, target and background information more comprehensively and accurately is provided, reach comparatively ideal noise reduction.In systems such as military field and non-military field such as optical imagery, target detection, security monitoring, all have wide application prospects.
Description of drawings
Fig. 1 is the image denoising method block diagram of one embodiment of the invention.
Fig. 2 is Fig. 1 example noise reduction photo figure as a result.Among the figure, (a) be subjected to noise reduction result under the different noise pollution situations to (e) for input picture, noise intensity is respectively 10,20,30,40 and 50.In each row, first width of cloth figure is the input that is subjected to noise pollution, and second width of cloth figure be the noise reduction image that adopts behind a kind of image denoising method noise reduction of Contourlet transform domain, and the 3rd width of cloth figure is the noise reduction image behind employing the inventive method noise reduction.
Embodiment
A preferred embodiment of the present invention is auspicious in conjunction with the accompanying drawings state as follows:
The present invention aims to provide a kind of method of reducing noise for combined images, as shown in Figure 1.This method is carried out multiple dimensioned, multidirectional sparse decomposition by the noisy image of Contourlet transfer pair input earlier, obey generalized Gaussian distribution according to the Contourlet coefficient in transform domain then, carry out Bayes collapse threshold method noise reduction in the Contourlet territory, and obtain the pre-noise reduction image by the Contourlet inverse transformation, at last, adopt the Wiener filter method that the pre-noise reduction image is carried out further noise reduction process, obtain final noise reduction image, reach the purpose of image noise reduction.
Concrete steps are:
1. initialization setting.Make i=0, j=0 sets the maximal translation amount N on line direction and the column direction
1And N
2The middle LP that sets the Contourlet conversion simultaneously decomposes the direction Number of Decomposition L in number of plies K and every layer
k
2. the noisy image I of input is expert at and column direction on carry out the circulation translation of the significance bit amount of moving, obtain the translation image
S
ij=C
i,j(I),
Wherein i ∈ (0, N
1) and j ∈ (0, N
2) be respectively the translational movement on line direction and the column direction;
3. the translation image S to obtaining
IjCarry out the sparse decomposition of multiple dimensioned, multidirectional Contourlet, promptly
Wherein T () is the Contourlet conversion.Thereby obtain a width of cloth low frequency subgraph as S
LfWith a series of high frequency subimage S with different resolution
Hf (k, l), wherein k ∈ (1, K) and l ∈ (1, L
k) indicate that subimage is positioned at the l direction of k layer LP (the tower decomposition of Laplce);
4. to the high frequency subimage S after the Contourlet conversion
Hf (k, l)Carry out the threshold value noise reduction process, obtain the noise reduction subimage,
Wherein, Λ () is a threshold function table, T
BBe threshold parameter.Obey generalized Gaussian distribution according to the Contourlet domain coefficient, therefore, present embodiment is selected the Bayes threshold value for use
Concrete estimating step is:
1. for noise criteria difference σ
n, adopt the intermediate value of robustness to estimate,
S wherein
Hf (K, i)(i=1 ... L
K) be the highest frequency coefficient;
2. by
Have
Wherein,
S
Hf (k, i)It is the high frequency coefficient of being considered;
3. therefore can get threshold value
5. all noise reduction high frequency subimage S that obtain in going on foot the 4th
Dhf (k, l)With the low frequency subgraph that obtains in the 3rd step as S
LfImplement the Contourlet inverse transformation, obtain the noise reduction image behind difference translation i and j on line direction and the column direction,
Wherein, T
-1() is the Contourlet inverse transformation;
6. the image S that obtains in going on foot the 5th
I, j NfCarry out the reverse circulation translation of corresponding translational movement, have
7. repeating step 2 to 6, up to i=N
1And j=N
2Till, stop repetition;
8. all I to obtaining
I, j Nf(i=0 ..., N
1J=0 ..., N
2) ask average, obtain the pre-noise reduction image:
9. the pre-noise reduction image that previous step is obtained
Further carry out the Wiener Filtering Processing, obtain final noise reduction result
As can be seen from Figure 2, on visual effect, the inventive method obviously is better than based on the Bayes collapse threshold method of moving constant Contourlet transform domain.In the process of noise reduction, the latter just carries out the Bayes threshold denoising to the high frequency coefficient that obtains after the process Contourlet conversion, and does not consider low frequency part, so the still residual small amount of noise of the image behind the noise reduction.And the inventive method is further adopting the estimator with optimum under the MSE meaning on this basis---the Wiener filter is implemented filtering; thereby in the protection image detail information; further improve the PSNR of noise reduction image, further reduced the MSE of noise reduction image.
Table 1 has provided noise-reduction method noise reduction result's of the present invention objective evaluation index.
In the table, method 1 refers to adopt Y-PSNR (PSNR) and least mean-square error (MSE) to weigh the quality of noise reduction image based on the Bayes collapse threshold noise-reduction method that moves constant Contourlet transform domain, and then estimates the quality of noise-reduction method.
As can be seen from the table, no matter this image denoising method is aspect PSNR, still aspect MSE, all can obtain good noise reduction, reduces the noise signal in the image effectively, improves picture quality.
In addition, from table, be not difficult to find, rising along with noise level, the noise reduction image index that obtains behind the inventive method noise reduction (PSNR and MSE) constantly increases based on the Bayes collapse threshold method increase rate that moves constant Contourlet transform domain, shows that the advantage of noise-reduction method of the present invention is obvious all the more.Aspect visual effect, also can draw identical conclusion from Fig. 2.
In a word, no matter be from the human eye vision effect, still from the objective evaluation index, show that all the inventive method reduces the noise signal in the image better, protected the material particular information in the image, improved the quality of image.
Noise reduction result's evaluation index relatively under the different noise levels of table 1
σ n=10 | σ n=20 | σ n=30 | σ n=40 | σ n=50 | ||||||
PSNR | MSE | PSNR | MSE | PSNR | MSE | PSNR | MSE | PSNR | MSE | |
Noisy image | 28.16 | 99.22 | 22.15 | 396.52 | 18.73 | 871.62 | 16.39 | 1492.37 | 14.63 | 2238.94 |
Method 1 | 28.55 | 90.85 | 28.90 | 83.70 | 27.06 | 127.87 | 25.84 | 169.63 | 24.26 | 243.96 |
The inventive method | 28.60 | 89.84 | 29.88 | 66.90 | 28.33 | 95.57 | 27.37 | 119.16 | 25.62 | 178.30 |
Claims (3)
1, a kind of method of reducing noise for combined images, it is characterized in that adopting method of reducing noise for combined images based on moving constant Contourlet transform domain noise reduction and Wiener filtering, this method is that the noisy image of importing by the Contourlet transfer pair earlier carries out multiple dimensioned, multidirectional sparse decomposition, obey generalized Gaussian distribution according to the Contourlet coefficient in transform domain then, carry out Bayes collapse threshold method noise reduction in the Contourlet territory, and obtain the pre-noise reduction image by the Contourlet inverse transformation, at last, adopt the Wiener filter method that the pre-noise reduction image is carried out further noise reduction process, obtain final noise reduction image, reach the purpose of image noise reduction.
2, method of reducing noise for combined images according to claim 1 is characterized in that concrete steps are:
1) initialization setting.Make i=0, j=0 sets the maximal translation amount N on line direction and the column direction
1And N
2
The middle LP that sets the Contourlet conversion simultaneously decomposes the direction Number of Decomposition L in number of plies K and every layer
k
2) the noisy image I of input is expert at and column direction on carry out the circulation translation of the significance bit amount of moving, obtain the translation image
S
ij=C
i,j(I),
Wherein i ∈ (0, N
1) and j ∈ (0, N
2) be respectively the translational movement on line direction and the column direction;
3) the translation image S to obtaining
IjCarry out the sparse decomposition of multiple dimensioned, multidirectional Contourlet, promptly
Wherein T () is the Contourlet conversion; Thereby obtain a width of cloth low frequency subgraph as S
LfWith a series of high frequency subimage S with different resolution
Hf (k, l), wherein k ∈ (1, K) and l ∈ (1, L
k) indicate that subimage is positioned at the l direction of the tower decomposition of k layer Laplce (LP);
4) to the high frequency subimage S after the Contourlet conversion
Hf (k, l)Carry out the threshold value noise reduction process, obtain the noise reduction subimage,
Wherein, Λ () is a threshold function table, and Thr is a threshold value, obeys generalized Gaussian distribution according to the Contourlet coefficient in transform domain, selects the Bayes threshold value for use
5) to the 4th) all noise reduction high frequency subimage S of obtaining in the step
Dhf (k, l)With the 3rd) low frequency subgraph that obtains in the step is as S
LfImplement the Contourlet inverse transformation, obtain again on line direction and the column direction noise reduction image behind the translation i and j respectively,
Wherein, T
-1() is the Contourlet inverse transformation;
6) to the 5th) the image S that obtains in the step
I, j NfCarry out the reverse circulation translation of corresponding translational movement, have
7) repeating step 2) to 6), up to i=N
1And j=N
2Till, stop repetition;
8) all I to obtaining
I, j Nf(i=0 ..., N
1J=0 ..., N
2) ask average, obtain the pre-noise reduction image:
3, method of reducing noise for combined images according to claim 2 is characterized in that the described the 4th) threshold value T in the step
BConcrete estimating step is as follows:
1. for noise criteria difference σ
n, adopt the intermediate value of robustness to estimate,
S wherein
Hf (K, i)(i=1 ... L
k) be the highest frequency coefficient;
2. by
Have
Wherein,
S
Hf (k, j)It is the high frequency coefficient of being considered;
3. therefore can get threshold parameter
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNB2006100307462A CN100417191C (en) | 2006-09-01 | 2006-09-01 | Method of reducing noise for combined images |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNB2006100307462A CN100417191C (en) | 2006-09-01 | 2006-09-01 | Method of reducing noise for combined images |
Publications (2)
Publication Number | Publication Date |
---|---|
CN1917577A true CN1917577A (en) | 2007-02-21 |
CN100417191C CN100417191C (en) | 2008-09-03 |
Family
ID=37738459
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNB2006100307462A Expired - Fee Related CN100417191C (en) | 2006-09-01 | 2006-09-01 | Method of reducing noise for combined images |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN100417191C (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2009074117A1 (en) * | 2007-12-13 | 2009-06-18 | Mediatek Inc. | In-loop fidelity enhancement for video compression |
CN101799916A (en) * | 2010-03-16 | 2010-08-11 | 刘国传 | Biologic chip image wavelet de-noising method based on Bayesian estimation |
CN101847257A (en) * | 2010-06-10 | 2010-09-29 | 上海电力学院 | Image denoising method based on non-local means and multi-level directional images |
CN101719268B (en) * | 2009-12-04 | 2011-10-19 | 西安电子科技大学 | Generalized Gaussian model graph denoising method based on improved Directionlet region |
CN102316282A (en) * | 2011-09-20 | 2012-01-11 | 中国科学院理化技术研究所 | Image noise reduction device based on optics dolby |
CN101477679B (en) * | 2009-01-16 | 2012-07-25 | 西安电子科技大学 | Image denoising process based on Contourlet transforming |
TWI561068B (en) * | 2015-03-25 | 2016-12-01 | Realtek Semiconductor Corp | Image processing apparatus and method |
CN114037747A (en) * | 2021-11-25 | 2022-02-11 | 佛山技研智联科技有限公司 | Image feature extraction method and device, computer equipment and storage medium |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101639934B (en) * | 2009-09-04 | 2012-07-04 | 西安电子科技大学 | SAR image denoising method based on contour wave domain block hidden Markov model |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100965880B1 (en) * | 2003-09-29 | 2010-06-24 | 삼성전자주식회사 | Method and apparatus of image denoising |
CN100410925C (en) * | 2004-12-30 | 2008-08-13 | 中国科学院长春光学精密机械与物理研究所 | Digital signal processing method for ultrasonic signals |
-
2006
- 2006-09-01 CN CNB2006100307462A patent/CN100417191C/en not_active Expired - Fee Related
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2009074117A1 (en) * | 2007-12-13 | 2009-06-18 | Mediatek Inc. | In-loop fidelity enhancement for video compression |
CN101477679B (en) * | 2009-01-16 | 2012-07-25 | 西安电子科技大学 | Image denoising process based on Contourlet transforming |
CN101719268B (en) * | 2009-12-04 | 2011-10-19 | 西安电子科技大学 | Generalized Gaussian model graph denoising method based on improved Directionlet region |
CN101799916A (en) * | 2010-03-16 | 2010-08-11 | 刘国传 | Biologic chip image wavelet de-noising method based on Bayesian estimation |
CN101847257A (en) * | 2010-06-10 | 2010-09-29 | 上海电力学院 | Image denoising method based on non-local means and multi-level directional images |
CN101847257B (en) * | 2010-06-10 | 2012-06-20 | 上海电力学院 | Image denoising method based on non-local means and multi-level directional images |
CN102316282A (en) * | 2011-09-20 | 2012-01-11 | 中国科学院理化技术研究所 | Image noise reduction device based on optics dolby |
CN102316282B (en) * | 2011-09-20 | 2014-05-07 | 中国科学院理化技术研究所 | Image noise reduction device based on optics dolby |
TWI561068B (en) * | 2015-03-25 | 2016-12-01 | Realtek Semiconductor Corp | Image processing apparatus and method |
US9619864B2 (en) | 2015-03-25 | 2017-04-11 | Realtek Semiconductor Corporation | Image processing apparatus and method for increasing sharpness of images |
CN114037747A (en) * | 2021-11-25 | 2022-02-11 | 佛山技研智联科技有限公司 | Image feature extraction method and device, computer equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN100417191C (en) | 2008-09-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN1917577A (en) | Method of reducing noise for combined images | |
CN100550978C (en) | A kind of self-adapting method for filtering image that keeps the edge | |
CN101950414B (en) | Non-local mean de-noising method for natural image | |
CN101847257B (en) | Image denoising method based on non-local means and multi-level directional images | |
CN106709928B (en) | fast two-dimensional maximum inter-class variance threshold method for noisy images | |
CN1920881A (en) | Image noise reducing method for Contourlet transform | |
CN1921562A (en) | Method for image noise reduction based on transforming domain mathematics morphology | |
CN101477679B (en) | Image denoising process based on Contourlet transforming | |
CN104103041B (en) | Ultrasonoscopy mixed noise Adaptive Suppression method | |
CN103093433A (en) | Natural image denoising method based on regionalism and dictionary learning | |
CN102890820A (en) | Image denoising method based on shearlet transformation and Wiener filtering | |
CN110349106B (en) | Wavelet soft threshold image denoising method based on Renyi entropy | |
CN104881847A (en) | Match video image enhancement method based on wavelet analysis and pseudo-color processing | |
CN1251145C (en) | Pyramid image merging method being integrated with edge and texture information | |
CN105894477A (en) | Astronomical image noise removal method | |
CN104835127A (en) | Adaptive smooth filtering method | |
CN112750090A (en) | Underwater image denoising method and system for improving wavelet threshold | |
CN110706186B (en) | Underwater information anti-interference method based on compressed sensing and Renyi entropy | |
CN1254770C (en) | Image merging method based on maximum expectation value and discrete wavelet frame | |
CN103903228A (en) | Non-local image denoising method based on HWD conversion | |
CN103077507A (en) | Beta algorithm-based multiscale SAR (Synthetic Aperture Radar) image denoising method | |
CN106296599A (en) | A kind of method for adaptive image enhancement | |
CN104754183A (en) | Real-time monitoring video adaptive filtering method and real-time monitoring video adaptive filtering system | |
CN102184530B (en) | Image denoising method based on gray relation threshold value | |
CN101930590B (en) | Transform domain neighborhood self-adapting image denoising method for detecting fire accident |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
C17 | Cessation of patent right | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20080903 Termination date: 20110901 |