Images Restoration Based on a New Optimal Parameter to Conjugate Gradient Method

Abstract

Image denoising plays a vital role in numerous image processing applications. This research presents a novel two-phase conjugate gradient method tailored for mitigating impulse noise. The approach leverages a center-weighted median filter, which adaptively identifies noise-affected pixels and applies the conjugate gradient technique to restore them. The method focuses on minimizing a specific functional that maintains edge integrity while reducing noise candidates. One of the key advantages of this technique is its descent-based search mechanism, with the possibility of achieving global convergence through the Wolfe line search conditions. Experimental evaluations demonstrate the method’s effectiveness in removing impulse noise using a spectral conjugate gradient approach.