Non Local Means Denoising for 3D MR Images

摘要：

　　Denoising is a crucial step to increase image conspicuity and to improve the performances of all the processing needed for quantitative image analysis.In this paper,the main method we proposed is Non Local Means.We carried out our experiments based on 3D MR images from Brain Web.We compared The NL-means with some classical methods,such as Anisotropic Diffusion Filter and Bilateral Filter.The results show that the Filtering performance of NL-means is better than other methods.Moreover,we present an optimized version of original NL-means and parailelize the computation on GPU device.

关键词： NL-means denoising 3D MRI parallelize GPU

作者: Hao Song Jing Jin

作者单位: School of Electronic Engineering University of Electronic Science and Technology of China Chengdu,Ch School of Communication and Information Engineering University of Electronic Science and Technology

会议类型: 国际会议

会议名称: 2013 2nd International Conference on Computer Science and Electronics Engineering(ICCSEE2013)(2013年第二届计算机科学与电子工程国际会议)

会议地点: 杭州

会议语种:英文

页码: 780-783

在线出版日期: 2013-03-22（万方平台首次上网日期，不代表论文的发表时间）