基于轮廓匹配的引线键合机视觉定位方法  

Visual Positioning Method of Wire Bonding Machine Based on Contour Matching

作　　者：康永新 靳宇婷 KANG Yong-xin;JIN Yu-ting(The 2nd Research Institute of CETC,Taiyuan 030024 China)

机构地区：[1]中国电子科技集团公司第二研究所,山西太原030024

出　　处：《科技创新与生产力》2022年第7期117-119,122,共4页Sci-tech Innovation and Productivity

摘　　要：视觉定位系统是芯片封装设备中的重要组成部分,视觉定位的精度对芯片加工精度具有很大的影响。基于轮廓特征的图像匹配相对于其他模板匹配算法更加有区分度,能够实现更高精度的定位。但传统像素级的轮廓提取算法无法满足小于1像素的图像处理要求,因此提出一种基于亚像素轮廓提取的模板匹配算法,根据该算法进行引线键合机视觉系统定位实验,有效提高了引线键合机的定位精度。Visual positioning system is an important part of chip packaging equipment.The accuracy of visual positioning has a great impact on the accuracy of chip processing.Compared with other template matching algorithms,image matching based on contour features is more discriminative and can achieve higher precision positioning.However,the traditional pixel level contour extraction algorithm can not meet the image processing requirements of less than 1 pixel.Therefore,a template matching algorithm based on sub-pixel contour extraction is proposed.According to this algorithm,the positioning experiment of wire bonding machine vision system is carried out,which effectively improves the positioning accuracy of wire bonding machine.

关 键 词：引线键合 亚像素轮廓提取 模板匹配 

分 类 号：F204[经济管理—国民经济] F279.24