基于机器视觉的零件缺陷检测算法  

作　　者：吴强 崔跃利[1] 张耀[1] 

机构地区：[1]台州学院物理与电子工程学院,浙江台州318000

出　　处：《科学技术创新》2018年第26期65-66,共2页Scientific and Technological Innovation

基　　金：浙江省大学生科技创新项目(2017R430007)立项资助

摘　　要：提出一种新的基于机器视觉的零件表面的缺陷检测算法。根据零件缺陷特点,系统采用二值化、中值滤波、形态学处理等方法对获取的图像进行处理。搭建了包括图像处理模块、上位机、图像采集部分的零件表面的缺陷检测平台。实验仿真结果显示,该算法能够准确识别零件表面缺陷,并具有较高识别率和鲁棒性。A new defect detection algorithm based on machine vision for parts surface is presented. According to the characteristics of parts defects, the system uses two valued, median filtering, morphological processing and other methods to process the acquired images. The defect detection platform of parts surface including image processing module, upper computer and image acquisition part is built. The simulation results show that the algorithm can accurately identify parts surface defects, and has a high recognition rate and robustness.

关 键 词：机器视觉 零件缺陷 缺陷检测 缺陷识别 

分 类 号：TH161.1[机械工程—机械制造及自动化]