Adaptive Block-Based Singular Value Decomposition Filtering

Abstract

Noise reduction is one of the most important processes to enhance the quality of reconstructed image. In this paper, we present an adaptive block-based singular value decomposition method for noise reduction. Instead of applying block-based singular value decomposition (BSVD) directly to noisy images, we propose to apply BSVD on the noisy edge image version obtained from the difference between the original noisy image and its blur image version. From the experimental results, we demonstrate that our proposed approach compared with traditionally methods can remove noise, preserve edges as well as effectively smooth in the homogenous region. Therefore, our method leads to a practical method to be used for noise reduction.