摘要
提出了一种结合Watershed变换和融合ROI信息的单调推进Snake模型的感兴趣区域提取的新方法。通过非线性扩散滤波对原始图像进行平滑,利用Watershed算法对图像进行过度分割,采用Snake模型提取出感兴趣区域,并由ROI能量函数推导出区域速度函数项,与基于边界的速度函数融合,根据区域之间的统计特性的相似度,重新定义Snake模型的速度函数。实验表明,该方法能够精确地提取对比度低且细窄的ROI区域。
This paper focuses on the ROI ( region of interest) extraction , which is one of the key problems in medical image processing. An efficient approach to ROI extraction based on the combination of watershed transformation and monotonically marching snake integrating ROI information is proposed. First, the original image is smoothed by using nonlinear diffusion filter. Then the smoothed image is over- segmented by the watershed algorithm. Finally, the ROI is extracted automatically by using the snake model. Moreover, the speed function is defined based on the statistical similarity degree of the regions and the ROI energy. Experimental results show that the algorithm can obtain segmentation result of medical image fast and accurately.
出处
《杭州电子科技大学学报(自然科学版)》
2006年第2期19-22,共4页
Journal of Hangzhou Dianzi University:Natural Sciences
关键词
感兴趣区域
提取
医学图像
region of interest
extraction
medical image