一种改进的粘连颗粒图像分割算法  

An Improved Segmenting Algorithm for Touched Particle Image

作　　者：李希[1,2] 王天江[1] 周鹏[3] 

机构地区：[1]华中科技大学计算机科学与技术学院,湖北武汉430074 [2]湖南师范大学数学与计算机科学学院,湖南长沙410081 [3]湖南师范大学物理与信息科学学院,湖南长沙410081

出　　处：《湖南大学学报（自然科学版）》2012年第12期84-88,共5页Journal of Hunan University:Natural Sciences

基　　金：湖南省自然科学基金资助项目(12JJ5022)

摘　　要：针对颗粒图像分割中产生过分割、欠分割及粘连区域存在孔洞从而导致分割不理想的情况,提出了一种改进算法.该算法在基于边界跟踪的分割算法的基础上,采用根据真实欧氏距离所提取的局部极大值点信息对分割策略进行控制,以减少过分割、欠分割的产生,同时对含有孔洞的粘连区域增加内边界跟踪处理.实验结果表明,算法获得了更好的分割效果.In order to overcome the unsatisfactory segmenting results such as over-segmentation,under-segmentation and touched region with holes in particle image,an improved segmenting algorithm was presented.Based on the boundary tracing segmenting algorithm,the proposed algorithm controls the segmenting process with the local maximum value point information of the true Euclidean distance to decrease the occurrence of over-segmentation and under-segmentation.And for the touched region with holes,the inner boundary was traced also,while the outer boundary was traced.The experiment result shows that this algorithm has acquired better segmenting effect.

关 键 词：图像分割 粘连颗粒图像 过分割 欠分割 孔洞 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]