Medical image segmentation based on Mathematical Morphology
基于数学形态学的医学图像分割

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.