Comparisons on segmentation of brain MR image

2009 9th International Conference on Electronic Measurement & Instruments Pub Date : 2009-10-02 DOI:10.1109/ICEMI.2009.5274127

Chunlan Yang, Shuicai Wu, Yanping Bai, Hongjian Gao

引用次数: 0

Abstract

Image segmentation is a focused issue in image processing. Especially, brain segmentation is a key problem in neuroscience. In this study, our aim is to segment the real MR image into gray matter, white matter and cerebrospinal fluid. Several methods were compared. However, traditional methods such as fuzzy c-means, mixture Gaussian model can't achieve a satisfied result successfully. Markov random field (MRF) model is used and the experimental results show that MRF method is robust to noise which can achieves a perfect segmentation.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

脑磁共振图像分割方法的比较

图像分割是图像处理中的一个热点问题。特别是脑分割是神经科学中的一个关键问题。在这项研究中，我们的目的是将真实的MR图像分割成灰质，白质和脑脊液。比较了几种方法。然而，传统的模糊c均值、混合高斯模型等方法并不能获得满意的结果。采用马尔科夫随机场(MRF)模型，实验结果表明，该方法对噪声具有较强的鲁棒性，可以达到较好的分割效果。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

2009 9th International Conference on Electronic Measurement & Instruments

自引率

0.00%

发文量

期刊最新文献

Comparisons on segmentation of brain MR image Experiment study and fatigue life prediction of torsion shaft of self-propelled gun based on stochastic response surface method A reversible authentication scheme for JPEG2000 images Reading system for 2D code based on machine vision Research and simulation of superenvelopes UV communication system