融合颜色聚类和分水岭算法的铁谱图像分割  

Ferrographic image segmentation by the method combining k-means clustering and watershed algorithm

作　　者：王静秋[1] 张龙[1] 王晓雷[1] 

机构地区：[1]南京航空航天大学江苏省精密与微细制造技术重点实验室,江苏南京210016

出　　处：《中国矿业大学学报》2013年第5期866-872,共7页Journal of China University of Mining & Technology

基　　金：国家自然科学基金项目(51205202);江苏省高校优势学科建设工程项目;南京航空航天大学基本科研业务费专项科研项目(NP2011028)

摘　　要：通过分析不同颜色空间下铁谱图像k-means颜色聚类效果,提出在CIELAB颜色空间利用二维颜色分量进行k-means均值聚类的算法,从而实现铁谱图像背景和磨粒的分离.将kmeans颜色聚类结果作为基础图像,利用阈值法分别针对背景和磨粒提取区域极小值,从而获得背景和磨粒标记图像,在此基础上利用标记分水岭算法实现了铁谱图像磨粒沉积链自动分割.研究结果表明,本文所提出的方法消除了背景因素对磨粒沉积链分割的不良影响,提高了分割的准确度.By evaluating the results of k-means clustering in different color spaces including RGB, HSI and CIELAB, this study proposed the algorithm of k-means clustering using two di- mensional color components in CIELAB color space. By this algorithm, the wear particles could be segmented directly from the background of ferrographic image. Then, the results of k- means clustering are used as basic images, threshold method is adopted to extract regional min- imal values of particles and background to obtain the marker images of both particles and back- ground. At last, the automatic segmentation of wear particles is achieved by using improved watershed algorithm. The results show that the method in this study could improve the seg- mentation accuracy of wear particle chains by eliminating the influences from background.

关 键 词：铁谱图像 图像分割 K-MEANS聚类 分水岭变换 

分 类 号：TH117.2[机械工程—机械设计及理论]