基于Fisher准则的多铆钉线聚类融合识别算法  

Cluster-fusion recognition method for rivet lines based on Fisher discriminant criterion function

作　　者：胡丹丹[1] 李万民[2] 刘芳[2] 高庆吉[1] 

机构地区：[1]中国民航大学机器人研究所,天津300300 [2]东北电力大学自动化系,长春132022

出　　处：《计算机应用》2010年第4期953-955,959,共4页journal of Computer Applications

基　　金：国家自然科学基金资助项目(60776811);中央高校基本科研业务费中国民航大学专项(ZXH2009D014)

摘　　要：针对飞机蒙皮缺陷检查中多铆钉线的识别问题,基于Fisher压缩准则提出一种聚类融合识别算法。对采用Canny算子提取的铆钉边缘进行形态学运算,得到铆钉区域及其由质心构成的线段向量集合,采用Fisher准则函数对可能的铆钉线方向的线段向量进行聚类。根据原点到同一铆钉线上的线段向量的距离相等的特点对聚类线段向量进行融合,拟合出实际铆钉线。实验结果表明,该方法具有较高的准确性和鲁棒性,能满足飞机蒙皮缺陷检查机器人实时检测要求。A cluster-fusion recognition method for rivet lines was proposed based on Fisher discriminant criterion function.The edge points were extracted using Canny operator,and processed by morphology in order to get the location of the centroid.Then,any two centroids were combined to construct the collection of line segments which were classified by Fisher criterion.According to the principle that the distance from the segments on one rivet line to origin point is similar,the segment-vectors were fused to fit the rivet line.The experimental results show that its accuracy and robustness are improved,which can meet the requirements of real-time detection.

关 键 词：铆钉质心 线段向量 铆钉线 FISHER准则 聚类融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]