基于凹点搜索的重叠粉体颗粒的自动分离算法  

Automatic segmentation of overlapping powder particle based on searching concavity points

作　　者：刘伟华[1,2] 隋青美[1] 

机构地区：[1]山东大学控制科学与工程学院,济南250014 [2]山东经济学院信息管理学院,济南250014

出　　处：《电子测量与仪器学报》2010年第12期1095-1100,共6页Journal of Electronic Measurement and Instrumentation

基　　金：国家自然科学基金(编号:61074163)资助项目

摘　　要：提出了一种利用凹点搜索和匹配并构造分离线分割重叠的不规则颗粒的方法,实现了不同重叠程度、多个重叠颗粒的自动分割。首先利用计算曲率及切线夹角的方法选取待匹配凹点;而后根据凹点和颗粒个数的对应关系确定了颗粒重叠的不同类型,提出了不同的凹点匹配规则;最后用Bresenham画线连接匹配凹点分离颗粒。该算法在MATLAB环境下实现,通过对多幅不同重叠类型的颗粒图像进行的分离实验表明,该算法实现简单,速度快,效果理想,且在分离颗粒的同时能保持其大小和形状不变。An algorithm of powder particle automatic segmentation is proposed,which makes use of automatic finding and pairing concavity points and drawing line to segment overlapping particles.Different kinds of overlapping particles could be correctly separated.According to calculated curvature and corner,concavity points are selected for ascertaining the separation pair-point.Then,different kinds of matching rules are given by comparing the numbers of concave points with the numbers of particle.Segment lines are drawn based on Bresenham and overlapping particles are separated after obtainning matching concavity points.This algorithm is carried to separate the overlapping particle image under the Matlab environment.The experimental results showed that algorithm was simple,effective,and the correction rate of segmentation was 97.6%.The segmented particles also had small deformation and smooth boundaries.

关 键 词：重叠 粉体颗粒 凹点搜索 自动分离 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]