不完全K-means聚类与分类优化结合的图像分割算法  

Image segmentation algorithm based on incomplete K-means clustering and category optimization

作　　者：杨明川[1] 吕学斌[1] 周群彪[1] 

机构地区：[1]四川大学计算机学院,成都610064

出　　处：《计算机应用》2012年第1期248-251,268,共5页journal of Computer Applications

基　　金：国家863计划项目(2006AA12A104)

摘　　要：为提升K均值聚类的效率及图像分割效果,提出了一种不完全K均值聚类与分类优化结合的图像分割(IKCO)算法。首先,采用简单的方法来进行数据精简及初始中心的确定;然后,根据给出的不完全聚类准则对图像进行聚类分割;最后,对分割结果进行分类优化以提升分割效果。实验结果表明,相对于传统的K均值聚类方法,IKCO算法在进行图像分割时具有很好的分割效率,且分割效果与人类视觉感知具有更高的一致性。To improve the clustering efficiency and image segmentation effect,the paper proposed an Incomplete K-means and Category Optimization（IKCO） method.First of all,the algorithm used simple approach to finish data subsampling and initial centers determining.Then,according to the clustering rules,the proposed algorithm finished image＇s segmentation.Finally,the algorithm used category optimization method to improve segmentation results.The experimental results show that,compared with the traditional K-means clustering method,the proposed algorithm has better segmentation efficiency,and the segmentation result has a higher consistency with human visual perception.

关 键 词：图像分割 不完全K均值聚类 分类优化 

分 类 号：TP391.413[自动化与计算机技术—计算机应用技术]