基于数学形态学的医学图像分割

Medical image segmentation based on Mathematical Morphology

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.