Computational and Mathematical Methods in Medicine
Volume 2012 (2012), Article ID 232685, 14 pages
Research Article

Improved DCT-Based Nonlocal Means Filter for MR Images Denoising

1College of Computer Science, Sichuan University, Chengdu 610064, China
2College of Computer Science, Sichuan University, Chengdu 610065, China
3College of Electronic and Information Engineering, Sichuan University, Chengdu 610064, China

Received 21 August 2011; Revised 22 November 2011; Accepted 9 December 2011

Academic Editor: Quan Long

Copyright © 2012 Jinrong Hu et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


The nonlocal means (NLM) filter has been proven to be an efficient feature-preserved denoising method and can be applied to remove noise in the magnetic resonance (MR) images. To suppress noise more efficiently, we present a novel NLM filter based on the discrete cosine transform (DCT). Instead of computing similarity weights using the gray level information directly, the proposed method calculates similarity weights in the DCT subspace of neighborhood. Due to promising characteristics of DCT, such as low data correlation and high energy compaction, the proposed filter is naturally endowed with more accurate estimation of weights thus enhances denoising effectively. The performance of the proposed filter is evaluated qualitatively and quantitatively together with two other NLM filters, namely, the original NLM filter and the unbiased NLM (UNLM) filter. Experimental results demonstrate that the proposed filter achieves better denoising performance in MRI compared to the others.