Image Denoising Method with Adaptive Bayes Threshold in Nonsubsampled Contourlet Domain
16
Citation
12
Reference
10
Related Paper
Citation Trend
Abstract:
In this paper, an improved image denoising method based on a nonlinear thresholding function with adaptive bayes threshold in Nonsubsampled Contourlet Transform (NSCT) domain. In overcoming the shortcomings of the same threshold, the noise deviation of the different sub-band are estimated based on the coefficients of different directional and level sub-bands in NSCT domain, and the thresholds of every sub-band is estimated by Bayesian threshold estimation method. After choosing the thresholds, a nonlinear thresholding function was chosen to overcome the shortcomings of the soft and the hard thresholding function. The simulation results show that the proposed method in this paper can remove Gaussian white noise more effectively, and get a higher PSNR value and keep image texture and detail information more clearly, which also has a better visual effect.Keywords:
Contourlet
In Chapter 2, the author formulates a quantitative model of the simple binary detection problem in which the received waveform consists of a white Gaussian noise process in one hypothesis and the sum of a Gaussian signal process and the white Gaussian noise process in the other hypothesis.
Gaussian Noise
Cite
Citations (1)
Contourlet is a new effective signal representation tool in many imageapplications. Proposed is a contourlet-based image denoising algorithm using directional windows which takes advantage of the captured directional information of the images. Experiments show that the proposed algorithm achieves better performance than other contourlet-based image denoising algorithms.
Contourlet
Representation
Cite
Citations (39)
In the contourlet transform,the image obtained by Laplacian Pyramid decomposition may produce artifacts on singularity of signal,which is harmful to image denoising.Due to the lack,the improved contourlet transform which is composed of the improved Laplacian Pyramid(LP) decomposition is proposed,and the improved Laplacian Pyramid can effectively suppress the artifacts around the edge of the subband image obtained by contourlet transform.At the same time,SAR image enhancement algorithm based on improved contourlet transform is presented.Experiment results show that the algorithm is superior not only in speckle reduction but also in edge preservation.
Contourlet
Pyramid (geometry)
Speckle noise
Cite
Citations (3)
Contourlet
Cite
Citations (0)
The contourlet Transform is an efficient directional multiresolution image representation, but it is not shift-invariant. The nonsubsampled contourlet transform (NSCT), is a fully shift-invariant, multiscale, and multidirection expansion that has a fast implementation, but the computational efficiency is lower than the contourlet transform, such an efficient representation has to be obtained by structured transform and fast algorithm. In this paper, we adopt an optimized directional filter bank and embed it into NSCT to pursue the desired speed, sacrificed the PSNR of the reconstructed image, we obtain the obvious increase of processing speed. Experimental results show that the quality of reconstructed image is sufficient for the human visual system (HVS), and the modified NSCT has a speed about several times than the speed of the customary one, this is very valuable for practical applications of the NSCT.
Contourlet
Filter bank
Representation
Cite
Citations (1)
Contourlet
Cite
Citations (12)
Gaussian Noise
Cite
Citations (14)
Contourlet transform overcomes the weakness of wavelet in higher dimensions. According to the theory of Contourlet, Contourlet can represent the characteristics of image. When Contourlet is applied to image fusion, the characteristic of original images can be effectively extracted and more important information is preserved. The Contourlet coefficients are recognized as independent in traditional image fusion method based on Contourlet. However,the coefficients of Contourlet have strongly dependency among different region and different direction subbands,and using the characteristic of Contourlet coefficients can design fusion rule. Experimental results have evidenced the effectiveness of the proposed method and it can preserve and extract the characteristic more reliable, accuracy and effective.
Contourlet
Cite
Citations (1)
Classical Gaussian white noise in communications and signal processing is viewed as the limit of zero mean second order Gaussian processes with a compactly supported flat spectral density as the support goes to infinity. The difficulty of developing a theory to deal with nonlinear transformations of white noise has been to interpret the corresponding limits. In this paper we show that a renormalization and centering of powers of band-limited Gaussian processes is Gaussian white noise and as a consequence, homogeneous polynomials under suitable renormalization remain white noises.
Gaussian Noise
Cite
Citations (8)