摘要
MR图像中常含有偏移场以及噪声现象,传统的FM模型无法得到正确的分类。本文在FM目标函数中加入偏移场估计和噪声去除,完善其分类效果,使分类结果较好地克服偏移场和噪声影响。实验表明,本文算法在得到较准确的分类结果的同时还能很好地估计偏移场。
The classical FM model can＇t get the precise classification results of magnetic resonance images, which is polluted by bias and noises.In order to overcome this limitation of FM, bias estimation and noise remove are incorporated in FM model.The new model can reduce the effect of bias and noise.Experiments on the segmentation of magnetic resonance images show this model has better effect in image segmentation, and can get the estimated bias at the same time.
出处
《微计算机信息》
2010年第8期202-204,共3页
Control & Automation
关键词
有限混合模型
偏移场
去噪
Finite mixture mode
bias
noise remove
