基于机器视觉的树脂镜片疵病检测系统研究  

Flaws Detection System for Resin Lenses Based on Machine Vision

作　　者：姚红兵[1] 马桂殿[1] 沈宝国[2] 顾寄南[1] 曾祥波[1] 郑学良[1] 汤发全[1] 

机构地区：[1]江苏大学机械工程学院,江苏镇江212013 [2]江苏省联合职业技术学院镇江分院,江苏镇江212016

出　　处：《激光与光电子学进展》2013年第11期108-115,共8页Laser & Optoelectronics Progress

基　　金：江苏省丹阳市应用技术研究计划(12142K)

摘　　要：为了实现对树脂镜片的自动检测,建立了图像采集系统。对该系统所采用的设备参数及图像预处理、特征提取、疵病识别等算法进行了研究。首先根据镜片的尺寸和缺陷的检测精度等参数搭建了图像采集系统。其次,通过相机标定完成了图像拼接。然后,对图像进行预处理,提取了疵病的图像。最后,介绍了各种疵病的特征提取及分类算法。实验结果表明:所建系统的检测精度为0.02mm,疵病种类的识别正确率为96.5%,基本满足镜片质量检测的分类准确、检测标准统一及检测速度快等要求。An image acquisition system is established to realize the automatic detection of resin lenses. The parameters of the system and algorithms for image pre-processing, feature extraction, defect recognition, etc. are investigated. The image acquisition system is built according to the size of lens and detection precision of defect. Image mosaic is realized by camera calibration. The defect images are acquired through image pre-processing. The algorithms of defect feature extraction and classification are finally discussed. The experimental results indicate that the detection precision of the system is 0.02 mm and the recognition rate reaches 96.5 %, which can meet the system requirements for lens detection.

关 键 词：图像处理 镜片检测 暗场成像法 同态滤波 直线拟合 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]