基于改进SUSAN算法的片式元件角度识别  

Novel Algorithm Based on Improved SUSAN for Chip Angle Recognition

作　　者：杨立玲[1] 高红霞[1] 胡跃明[1] 蒋伟林[1] 

机构地区：[1]华南理工大学精密电子制造装备教育部工程研究中心自动化学院,广州五山510640

出　　处：《半导体技术》2009年第7期637-640,共4页Semiconductor Technology

基　　金：国家自然科学基金重点项目(60835001)

摘　　要：元件角度识别是贴片机元件视觉检测的关键,其参数的精确获取直接影响贴片机进行元件贴装的准确性。SUSAN算法是一种基于图像灰度比较的算法,不涉及梯度的计算。讨论了该算法的模板和门限的选取方法,继而提出一种改进的SUSAN边缘检测算法对矩形片式元件进行边缘检测,并通过试验比较了该算法与传统的几种边缘检测算法的优劣。试验证明改进的SUSAN算法能更好地提取复杂成像条件下元件图像的边缘,提高了贴装过程中元件角度识别的精度和稳定性。Angle recognition for chip component is one of the most difficult issues in electronics manufacturing, and it has direct impact on the mounting precision. SUSAN based on the gray comparison but not gradient. The selection of template and threshold was discussed, after analyzing the detecting task of chip in-depth, a new algorithm based on improved SUSAN edge detecting was proposed to detect edge of chip component. Then the advantages and disadvantages of improved SUSAN and other traditional algorithm for edge detection were compared by experiments. The results demonstrate that the proposed algorithm can detect the edge of component efficiently, even under the complex illumination condition, and the precision and stability of angle recognition are both improved.

关 键 词：SUSAN 边缘检测 角度识别 贴片机元件 灰度算法 贴装 

分 类 号：TP273.41[自动化与计算机技术—检测技术与自动化装置]