Halimah Alsurayhi and Mahmoud R. El-Sakka, "An Improved Weighted Average Reprojection Image Denoising Method", International Conference on Image Analysis and Recognition, ICIAR'2019, LNCS 11662, pp. 207-215, Springer-Verlag Berlin Heidelberg, August 2019, Waterloo, Canada.

Abstract

Patch-based denoising algorithms have an effective improvement in the image denoising domain. Weighted Average (WAV) reprojection algorithm is a simple and effective patch-based spatial domain denoising algorithm. In this paper, an improved WAV reprojection algorithm is proposed. It improves the method by adaptively deciding the patch sizes to be used based on the image structure. The image structure is identified using a classification method based on the structure tensor matrix. The classification result is also utilized to improve the identification of similar patches in the image. The experimental results show that the denoising performance of the proposed method is better than that of the original WAV reprojection algorithm.