摘要
针对FCM算法缺少空间关联信息且计算量大的问题,本文提出一种结合图论和FCM的图像分割算法。首先,引入图论算法对图像进行预处理,将图分割为子图。接着,对分割后的子图进行FCM聚类得到聚类中心。然后,提出一种基于聚类中心颜色和空间信息的加权距离,作为并查集算法的合并准则。最后,采用改进的并查集算法对聚类结果进行区域合并。实验结果表明,本文算法在保证图像分割质量的同时提高了图像分割速度。
Aiming at fuzzy C-means clustering algorithm lacking spatial information and large amount of calculation, an algorithm combined graph theory with fuzzy C-means clustering is presented in this paper. Firstly, the graph is divided into subgraph by graph theory algorithm. After that, clustering center of the subgraph is obtained by FCM algorithm. And then, a weighted distance based on the color of clustering center and space information is proposed as the merging criterion of union-find sets algorithm. Finally, the improved union-find sets is used to merge the regions of clustering results. The experimental results indicate that the proposed algorithm can ensure the quality of image segmen- tation with better performance.
出处
《液晶与显示》
CAS
CSCD
北大核心
2016年第1期112-116,共5页
Chinese Journal of Liquid Crystals and Displays
