一种改进的分水岭图像分割算法

A improved watershed image segmentation algorithm

分水岭算法在医学图像分割中有着广泛的应用。针对传统分水岭分割算法对噪声敏感和严重的过分割问题．本文提出了一种基于数学形态学的改进的分水岭图像分割算法。通过前期的预处理和汇水盆地的选取，有效地抑制了过分割现象。实验表明，该算法能够对血细胞图像进行快速、准确的分割，边缘定位精确，并且能够较好的克服噪声对图像的影响。

The watershed algorithm is widely used in medical image segmentation. In allusion to resolving the problems of noise sensitivity and over-segmentation existing in traditional watershed algorithm, this paper proposes an improved watershed segmentation algorithm based on morphological mathematics. Through the pretreatment in prophase and the catchment basin chosen, the phenomena of over-segmentation can be restrained. Experimental results show that the proposed algorithm can segment images of blood corpuscle quickly and accurately, and exactly locate edges. Furthermore, the influence of noisy can be averted by this way.