基于数学形态学的医学图像分割  

Medical image segmentation based on Mathematical Morphology

作　　者：王蜀[1] 李永宁[1] 陈楷民[1] 黄戈[1] 

机构地区：[1]四川大学计算机学院,四川成都610064

出　　处：《计算机应用》2005年第10期2381-2382,2386,共3页journal of Computer Applications

摘　　要：采用分水岭算法对医学图像进行分割,并针对其容易产生过分割的缺点,作了两点改进:首先对原始图像进行自适应加权的多尺度形态滤波,然后引入浮点活动图像作为分水岭算法的输入。实验表明,该方法算法简单,能有效地抑制过分割现象,得到较好的分割效果。In this paper, the watershed algorithm to segment medical images was introduced. The two improved methods considering the over-segmentation phenomena of watershed algorithm were presented. First, get the original image through multi-scale morphological filter with auto-adapted determinations weights, and then, introduced a floating-point active image as the input of watershed algorithm. Experiments show that the algorithm is very simple, and can restrain the over-segmentation phenomena effectively, so can obtain good results.

关 键 词：数学形态学 分水岭算法 自适应加权的多尺度形态滤波 浮点活动图像 

分 类 号：TP75[自动化与计算机技术—检测技术与自动化装置]