14 March 2013 MR images denoising using DCT-based unbiased nonlocal means filter
Author Affiliations +
Proceedings Volume 8768, International Conference on Graphic and Image Processing (ICGIP 2012); 876873 (2013) https://doi.org/10.1117/12.2008435
Event: 2012 International Conference on Graphic and Image Processing, 2012, Singapore, Singapore
Abstract
The non-local 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 by using a low-pass filtered and low dimensional version of neighborhood for calculating the similarity weights. The discrete cosine transform (DCT) is used as a smoothing kernel, allowing both improvements in similarity estimation and computational speed-up. Experimental results show that the proposed filter achieves better denoising performance in MR Images compared to others filters, such as recently proposed NLM filter and unbiased NLM (UNLM) filter.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xiuqing Zheng, Xiuqing Zheng, Jinrong Hu, Jinrong Hu, Jiuliu Zhou, Jiuliu Zhou, "MR images denoising using DCT-based unbiased nonlocal means filter", Proc. SPIE 8768, International Conference on Graphic and Image Processing (ICGIP 2012), 876873 (14 March 2013); doi: 10.1117/12.2008435; https://doi.org/10.1117/12.2008435
PROCEEDINGS
5 PAGES


SHARE
RELATED CONTENT


Back to Top