摘要
针对受噪声影响的图像,提出了一种基于边缘保持的快速全局k均值聚类分割算法,该方法包括双边滤波预处理和快速全局k均值聚类分割两部分,在噪声存在的情况下,能有效抑制过分割,并且解决了k均值聚类初始中心点的随机选择问题.实验结果表明,该方法提高了聚类分割的准确性.
A new fast global k-means clustering segmentation based on edge-preserving is presented for the images affected by noise. The method is constructed by bilateral filtering and fast global k-means clustering. In the case of the presence of noise, the proposed method can effectively inhibit the over-segmentation, and also solve the k-means clustering initial centers randomly selected questions. Experimental results show that the proposed method improves the accuracy of the clustering segmentation.
出处
《伊犁师范学院学报（自然科学版）》
2015年第3期67-72,共6页
Journal of Yili Normal University：Natural Science Edition
基金
喀什师范学院校内教研教改重点项目(KJDZ1303)
关键词
聚类分割
K均值
边缘保持
clustering segmentation
k-means
edge-preserving
