基于动态聚类算法的显微刻度线自动提取  

Automatic Extraction Method of Microscopic Graduation Line Based on Dynamic Clustering Algorithm

作　　者：李建兴[1] 柏俊杰[2,3] 董健[4] 

机构地区：[1]福建工程学院电子信息与电气工程系,福建福州350108 [2]重庆科技学院电气与信息工程学院,重庆401331 [3]东南大学仪器科学与工程学院,江苏南京210096 [4]东南大学自动化学院,江苏南京210096

出　　处：《福建师范大学学报（自然科学版）》2012年第6期42-46,共5页Journal of Fujian Normal University：Natural Science Edition

基　　金：国家自然科学基金资助项目(60876088);福建省资助省属高校科研专项计划项目(JK2011038)

摘　　要：设计一种基于机器视觉的显微刻度线自动提取系统,提出了一种实时、自适应能力强的刻度线全自动提取方法.根据Hough变换对刻度图像进行刻度边缘直线提取;基于动态聚类的方法对所提取的刻度边缘直线进行有效归类,给出了自动选取归类阈值的方法,借助归类信息进行非刻度线直线剔除操作;对优选后的直线使用最小二乘法对刻度线中线进行精确拟合.实验结果表明,使用该方法提取刻度线的精度高、抗干扰能力强.A system of extracting graduation lines based on machine vision was designed, and a real-time, full-automatic extracting method of microscopic graduation lines which has strong adaptive ability was proposed. Using Hough transformation, the edge lines of gradua- tion lines were extracted. All the extracted lines were classified effectively based on a dynam- ic clustering method. The automatic selection method of classifying threshold was given, and according to the classified information, the non-graduated lines were rejected. The midlines of these selected optimization lines were preciously fitted based on the least square method. The experimental results show that the method has higher precious and stronger anti-inter- ference ability to extract graduation lines.

关 键 词：显微刻度线 自动提取 HOUGH变换 动态聚类 最小二乘 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]