Region characteristics-based fusion of spatial and transform domain image denoising methods

Abstract

Nonlocal means (NLM)-and wavelet-based image denoising methods have drawn much attention in image processing due to their effectiveness and simplicity. The performance of these algorithms varies according to region characteristics in an image. For example, NLM performs well for smooth regions due to deployment of redundancy available in images, whereas wavelet-based approaches may preserve key image features by controlling the degree of threshold for shrinking the noisy coefficients. This paper presents a simple novel approach that estimates an original image by simply taking the weighted average of the denoised images pixel values obtained by NLM and wavelet thresholding schemes based on natural characteristics of regions in an image. Extensive simulations on standard images demonstrate that the proposed approach outperforms the benchmark wavelet-based schemes, NLM and its variants, in terms of peak signal-to-noise ratio (PSNR(dB)), mean structural similarity metric (MSSIM), and visual quality.

An Adaptive Threshold Method for WMSN Image Denoising

“…The large-scale space corresponds to the general form of the signal, and the smallscale space corresponds to the details of the signal. When the scale changes from large to small, the overall conditions and information details of the signal could be observed [20].…”