摘要
针对传统工业中SOP芯片引脚缺陷检测速度慢、精度低等问题,设计了一个基于机器视觉的SOP芯片引脚缺陷检测系统,通过MATLAB软件调用CCD相机采集芯片图像,采用改进的Canny边缘检测等算法实现引脚边缘的连接,采用连通域标记和灰度投影算法对得到的二值芯片引脚图像进行缺陷检测并完成GUI界面的设计。由实验数据可知,系统对芯片引脚缺陷检测的正确率为99.6%,测量误差在±0.03 mm之内,满足了工业生产中SOP芯片引脚缺陷检测实时性和准确性的需求。
Aiming at the problem of low detection speed and low accuracy of pin defects in traditional SOP chip in industry,a pin defect detection system based on machine vision was designed.The chip image was collected by using CCD camera through MATLAB software,and the improved Canny edge detection algorithm was used to realize pin edge connection.The defect detection of binary chip pin image is carried out by using connected domain marker and gray projection algorithm.The GUI interface is designed.According to the experimental data,the accuracy rate of chip pin defect detection by the system is 99.6%,and the measurement error is within±0.03 mm,which meets the real-time and accuracy requirements of pin defect detection of SOP chip in industrial production.
作者
王建冲
高军伟
张炳星
刘佳浩
WANG Jianchong;GAO Junwei;ZHANG Bingxing;LIU Jiahao(College of Automation,Qingdao University,Shandong Qingdao 266071,China;Shandong Provincial Key Laboratory of Industrial Control Technology,Shandong Qingdao 266071,China)
出处
《工业仪表与自动化装置》
2022年第5期32-37,共6页
Industrial Instrumentation & Automation
基金
山东省自然科学基金资助项目(ZR2019MF063)
山东省重点研发计划项目(2017GGX10115)。
关键词
机器视觉
改进的边缘检测
连通域标记
灰度投影
缺陷检测
machine vision
improved edge detection
connected domain marker
gray projection
defect detection
