Energy-based adaptive orthogonal FRIT and its application in image denoising

作     者：LIU YunXia PENG YuHua QU HuaiJing YIN Yong 

作者机构：School of Information Science and Engineering Shandong University Jinan 250100 China Shandong Tumor Hospital Jinan 250117 China 

出 版 物：《Science in China(Series F)》 (中国科学（F辑英文版）)

年 卷 期：2007年第50卷第2期

页      面：212-226页

核心收录：

学科分类：0711[理学-系统科学] 07[理学] 08[工学] 080401[工学-精密仪器及机械] 0804[工学-仪器科学与技术] 080402[工学-测试计量技术及仪器] 

基　　金：Scientific Research Foundation for the Returned Overseas Chinese Scholars the Ministry of Education (Grant No. 2004.176.4) the Natural Science Foundation of Shandong Province (Grant Nos. Z2004G01 and 2004ZRC03016) 

主　　题：orthogonal transform FRIT image denoising threshold 

摘      要：Efficient representation of linear singularities is discussed in this paper. We analyzed the relationship between the ＂wrap around＂ effect and the distribution of FRAT （Finite Radon Transform） coefficients first, and then based on study of some properties of the columnwisely FRAT reconstruction procedure, we proposed an energy-based adaptive orthogonal FRIT scheme （EFRIT）. Experiments using nonlinear approximation show its superiority in energy concentration over both Discrete Wavelet Transform （DWT） and Finite Ridgelet Transform （FRIT）. Furthermore, we have modeled the denoising problem and proposed a novel threshold selecting method. Experiments carried out on images containing strong linear singularities and texture components with varying levels of addictive white Gaussian noise show that our method achieves prominent improvement in terms of both SNR and visual quality as compared with that of DWT and FRIT.