基于模糊聚类的工业薄片件图像亚像素检测  

Subpixel Edge Detection of Image for Industrial Thin Sheet Parts Based on Fuzzy Clustering

作　　者：陈永清[1] 朱晓靖 王玉槐[3] 郭建亮[1] 陈廉清[1] 

机构地区：[1]宁波工程学院机械工程学院,浙江宁波315016 [2]浙江中力机械有限公司,浙江湖州313300 [3]杭州师范大学钱江学院,杭州310012

出　　处：《组合机床与自动化加工技术》2014年第10期66-68,共3页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：国家自然科学青年基金(61103171);浙江省公益性技术应用研究计划项目(2011C31048;2012C31006);教育厅2011年度科研计划项目(Y201120001);2012年度宁波市北仑科技创新基金

摘　　要：针对机器视觉检测工业薄片件边缘存在精度不高的问题,基于模糊数学理论,引入模糊聚类思想,提出了一种图像亚像素综合定位算法。用OTSU法对源图像进行二值化处理;用5×5矩形域最大梯度模检测像素级轮廓边缘;用基于模糊聚类的亚像素边缘定位算法进行极片亚像素边缘定位,实现了边缘的高精度定位。实验结果表明,该方法算法简便,精度较高,易于编程实现,且兼具多种检测算法的优势,尤其适合工业生产现场的机器视觉检测系统。A subpixel integrated location algorithm is proposed to address the issue of inaccuracy in machine vision detection of industry sheets by introducing the fuzzy clustering scheme based on fuzzy mathematics fundamental. Binarization of original image using the OTSU approach was carried out to detect a pixel-level contour edge with the maximal gradient module over a 5 × 5 rectangle area. High precision location of edge was implemented by adopting the subpixel edge location algorithm. The experimental results show that the proposed algorithm is simple and easy to realize via programming and also has the advantages from multiple algorithms so that it apply to the machine vision detection system in the practical production.

关 键 词：机器视觉 边缘检测 模糊聚类分析 亚像素 

分 类 号：TH16[机械工程—机械制造及自动化] TG386[金属学及工艺—金属压力加工]