Learning Overcomplete Dictionaries with Application to Image Denoising

Abstract

In recent years there has been a growing interest in the study of sparse representation of signals. Using an overcomplete dictionary that contains prototype signal-atoms, signals are described by sparse linear combinations of these atoms. Image denoising is an important application of this sparse model. However, whether the sparse representation can efficiently separate image and noise depends much on the atoms of dictionary can capture the structure of images. In this paper, we address the image denoising problem, where zero-mean white and homogeneous Gaussian additive noise is to be removed from a given image. The approach taken is based on sparse and redundant representations in overcomplete dictionaries that is learned by the K singular value decomposition algorithm. Experiments show that the dictionary can describe the image content effectively and leads to an state-of-the-art denoising performance.