Filter Bank Based Nonlocal Means for Denoising Magnetic Resonance Images  

作　　者：郭甜莉 刘且根 骆建华 

机构地区：[1]School of Aeronautics and Astronautics, Shanghai Jiaotong University

出　　处：《Journal of Shanghai Jiaotong university(Science)》2014年第1期72-78,共7页上海交通大学学报（英文版）

基　　金：the Postgraduate Innovation Ability Cultivating Foundation of China(No.Z-SY-009)

摘　　要：Image denoising is a classical problem in image processing. Its essential goal is to preserve the image features and to reduce noise effiectively. The nonlocal means(NL-means) filter is a successful approach proposed in recent years due to its patch similarity comparison. However, the accuracy of similarities in this algorithm degrades when it suffiers from heavy noise. In this paper, we introduce feature similarities based on a multichannel filter into NL-means filter. The multi-bank based feature vectors of each pixel in the image are computed by convolving from various orientations and scales to Leung-Malik set(edge, bar and spot filters), and then the similarities based on this information are computed instead of pixel intensity. Experiments are carried out with Rician noise. The results demonstrate the superior performance of the proposed method. The wavelet-based method and traditional NL-means in term of both mean square error(MSE) and perceptual quality are compared with the proposed method, and structural similarity(SSIM) and quality index based on local variance(QILV) are given.Image denoising is a classical problem in image processing. Its essential goal is to preserve the image features and to reduce noise effectively. The nonlocal means （NL-means） filter is a successful approach proposed in recent years due to its patch similarity comparison. However, the accuracy of similarities in this algorithm degrades when it suffers from heavy noise. In this paper, we introduce feature similarities based on a multi- channel filter into NL=means filter. The multi-bank based feature vectors of each pixel in the image are computed by convolving from various orientations and scales to Leung-Malik set （edge, bar and spot filters）, and then the similarities based on this information are computed instead of pixel intensity. Experiments are carried out with Rician noise. The results demonstrate the superior performance of the proposed method. The wavelet-based method and traditional NL-means in term of both mean square error （MSE） and perceptual quality are compared with the proposed method, and structural similarity （SSIM） and quality index based on local variance （QILV） are given.

关 键 词：Leung-Malik(LM) filter nonlocal means SIMILARITY image denoising Rician noise 

分 类 号：TN911.73[电子电信—通信与信息系统]