A COMPARATIVE STUDY ON WAVELET BASED IMAGE DENOISING

Nisha Joy

Abstract: The field of image processing deals with a major issue, i.e., the suppression of noise from the wanted images. The intention of this message is to highlight some of the unique properties of spline wavelets. In this paper image denoising is performed using simulated noise images with various characteristics with the help of semi-orthogonal spline wavelets in comparison with CDF 9/7 wavelets. B-spline analysis can be utilized for different signal/imaging applications such as compression, prediction, and denoising. The exquisite features of wavelet transforms are utilized in the area of image processing which perform better compared to other transforms. Simulated noise images are used to evaluate the denoising performance of b-spline wavelets with the help of Bayes Shrink algorithm and along with another wavelet-based denoising like Cohen-Daubechies-Feauveau (CDF 9/7). It is shown through experimental results that, for certain images and input noise levels, the orthogonal b-splines give the best peak signal-to-noise ratio (PSNR), as compared to standard wavelet bases (Daubechies wavelets). Illustrative results that demonstrate the difference in efficiency of the approaches are presented.

Keywords: Wavelet Transforms, Spline Wavelets, Image Denoising, Thresholding

DOI: https://doi.org/10.15623/ijret.2016.0516055