Improved Image Denoising Technique Using Neighboring Wavelet Coefficients of Optimal Wavelet with Adaptive Thresholding

Abstract

Abstract—These Wavelet thresholding is a signal estimation technique that exploits the capabilities of wavelet transform for signal denoising applications. But the optimal choice of the wavelet and thresholding function has restricted there wide spread use in image denoising application. The aim of this paper is twofold; firstly to suggest some new thresholding method for image denoising in the wavelet domain by keeping into consideration the shortcomings of conventional methods and secondly to explore the optimal wavelet for image denoising. In this paper we proposed a computationally more efficient thresholding scheme by incorporating the neighbouring wavelet coefficients, with different threshold value for different sub bands and it is based on generalized Gaussian Distribution (GGD) modeling of sub band coefficients. In this proposed method, the choice of the threshold estimation is carried out by analyzing the statistical parameters of the wavelet sub band coefficients like standard deviation, arithmetic mean and geometrical mean. It is demonstrated that our proposed method performs better than: VisuShrink, Normalshrink and NeighShrink algorithms in terms of PSNR ratio. Further a comparative analysis has been made between Daubechies, Haar, Symlet and Coiflet wavelets to explore the optimum wavelet for image denoising with respect to Lena image. It has been found that with Coiflet wavelet higher PSNR ratio is achieved than others. Hence proposed for denoising the Lena image.

6 Figures and Tables

Cite this paper

@inproceedings{KumarImprovedID, title={Improved Image Denoising Technique Using Neighboring Wavelet Coefficients of Optimal Wavelet with Adaptive Thresholding}, author={Rakesh Kumar and B. S. Saini} }