摘要
针对我国半导体生产后工序设备中的焊机一人一机手动的现状,本文提出手动焊机自动化改造的软件设计思想。讨论分析目前常用的基于灰度的快速模板匹配技术,着重研究芯片识别中所采用的关键技术———模板匹配。经实验对比发现,序贯相似检测算法(SSDA)具有较高的计算速度和定位精度,比较适合于高要求的工业应用。为进一步满足系统的要求,本文改进了自适应门限序列的SSDA,将匹配过程分为两步进行,第一步为粗匹配,第二为精匹配,大大提高了识别的精度与速度。
In semiconductor production, there is one person operating one machine by hands in the later process of bonder. According to this situation, in this paper, the software proposal of reconstruction is brought forward, and the key skill in the chip recognition pattern match is especially researched. Some commonly used fast image matching algorithms base on gray matching are discussed. By comparison, Sequential Similarity Detection algorithm bears the characteristics of speedy calculation, accurate orientation and anti-jammlng, which is fit for the high requirement in industry. In this proiect, we improve the arithmetic of SSDA and divide the matching process into two steps： the first one is the rough matching and the second one is the precise matching. This greatly improves the precision and pace in recognition.
出处
《计算机科学》
CSCD
北大核心
2006年第11期246-248,284,共4页
Computer Science
基金
东省教育厅自然科学基金(Z03021)
关键词
自动焊机
图形识别
模板匹配
序贯相似检测算(SSDA)
Automatic bonder, Image recognition, Template matching,Sequential similarity detection algorithm（SSDA）
