一种改进的分水岭算法在彩色图像分割中的应用

Application of an Improved Watershed Algorithm to Color Image Segmentation

针对分水岭变换算法在图像分割中容易产生过分割的问题,提出了一种基于分水岭变换和模糊C均值聚类算法相结合的彩色图像分割算法。该算法的优点是解决了分水岭变换算法的过分割问题,而且同时解决了模糊C均值聚类算法初始值难以确定的问题。实验结果表明,改进后的算法可以快速准确地分割出目标,因而能够很好地应用于自动分割系统中。

In allusion to the problem of watershed transform algorithm in image segmentation prone to over-segmentation,a color image segmentation approach of combination of watershed transform and fuzzy C-means clustering is put forward in this paper.The advantage of the algorithm is that it solves the problem of over-segmentation and the difficulty to determine the initial value of the fuzzy C-means clustering algorithm.The results of our experiment demonstrate that the improved algorithm can segregate the target quickly and accurately,and thus can be well applied to automatic segmentation system.