粒子群模糊聚类方法在病理图像分类中的应用

结合模糊C均值(FCM)算法局部搜索的特点,将PSO优化聚类结果作为后续FCM算法的初始值,使算法有很强的全局搜索能力.同时,采用Markov随机场与模糊聚类的耦合策略计算适应度函数,利用新的分类中心调整粒子位置,产生新的聚类中心,并将该方法应用于病理图像的分割.与传统的处理方法进行了比较,结果表明,该聚类更为准确且对病理图像的分割效果比原算法效果更好,但对于如何减少算法的运算量仍需作深入研究.

Fuzzy clustering method based on particle swarm optimization used in pathology image segmentation

By incorporating the local search of fuzzzy clustering method (FCM) algorithm and taking the clustering result of PSO as the initialized value of the FCM. By adopting the couple method of Markov random field and fuzzy clustering to express the adapt function. And the algorithm is applied to the representative image segmentation to get the center of clustering. Results from two pathology image are compared, show the new algorithm has better nicety and fit the pathological images segmentation better.