A Novel Patch-based Image Denoising Algorithm using Finite Radon Transform for Good VisualQ uality
作者单位：The Hong Kong Polytechnic University Kowloon Hong Kong
会议名称：《2011年亚太信号与信息处理协会年会》
会议日期：2011年
学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程]
基 金：supported by the Centre for Multimedia Signal Processing Department of Electronic and Information Engineering and the Hong Kong Polytechnic University. Liu Yun-Xia acknowledges the research studentships provided by the University
摘 要：Patch-based denoising methods have recently emerged due to its good denoising performance. In this paper, based on analysis of the optimal over-complete patch aggregation, we highlight the importance of a local transform for good image features representation. A finite Radon transform （FRAT） based two-stage over-complete image denoising algorithm is then proposed for obtaining good visual quality of denoised images. Experimental results demonstrate good performance in that the denoised images obtained by the proposed method are less influenced by artifacts.