基于RANSAC和灰度一致性的PET瓶胚口缺陷检测  

PET preform defect detection based on RANSAC and uniformity of grey level

作　　者：尹玄武[1,2] 王贵锦[1] 施陈博[1] 何贝[1] 刘博[1] 廖庆敏[2] 

机构地区：[1]清华大学电子工程系,北京100084 [2]清华大学深圳研究生院,广东深圳518055

出　　处：《计算机应用研究》2012年第9期3525-3527,共3页Application Research of Computers

摘　　要：针对现代高速生产线上PET瓶胚口的缺陷检测问题,提出了一种基于RANSAC和灰度一致性的PET瓶胚口缺陷检测算法。算法利用RANSAC方法精确定位瓶胚口区域,然后利用瓶胚口区域内的灰度一致性进行缺陷检测。实验证明,该算法准确率高、速度快,对于640×480图像的检测速度为10 ms/帧,完全满足高速生产线的检测需求。To detect the defect on the mouth of the PET preform in modern high-speed production line,this paper proposed a detection algorithm based on RANSAC and the uniformity of gray level.The algorithm located the mouth of the preform accurately through the RANSAC method and then detected the defect on the surface by checking the uniformity of grey level.Experiments show the algorithm achieve short execution time and high accuracy.For a typical image of 640×480,the execution time is in 10 ms/frame.And the algorithm can meet the real time requirements of the high-speed production line

关 键 词：工业检测 PET瓶胚口 随机抽样一致性 椭圆拟合 灰度一致性 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]