基于机器视觉的贴片LED编带过程在线检测算法研究  

Machine-Vision-Based Online Detection Algorithm of the SMD LED Braiding Process

作　　者：孟凡清[1] 游福成[1] 智金波[1] 

机构地区：[1]北京印刷学院信息工程学院,北京102600

出　　处：《北京印刷学院学报》2013年第4期54-57,共4页Journal of Beijing Institute of Graphic Communication

基　　金：北京市自然基金重点项目(KZ201210015015);北京市自然基金资助项目(4122026);北京市教委面上项目(KM201210015006;KM201210015007);北京印刷学院校级重点资助项目(E-a-2012-23)

摘　　要：为了对贴片LED编带过程中的混料、空料、反料、侧料、极性不一致等缺陷进行检测,以保证产品的一致性,设计了一个用于LED编带过程缺陷检测的视觉系统。将基于金字塔的模板匹配算法用于产品缺陷识别,用VS2010编写了检测软件,并在实验中检测了不同的缺陷。结果表明,给出的算法能够识别出常见的缺陷,并能区分出缺陷的类型。The defects, including different LED, LED deletion, side-inversion, position-offset, polarity-reversal, are demanded to inspect in order to ensure the identity of product in the braiding process of SMD LED. A vision system is designed for the defects inspection on the LED braiding process in this paper. The template matching algorithm based on pyramid is used to inspect the defects. The detection software is developed by using VS2010, and the LED defects are inspected in experiments. The results show that the proposed algorithm can inspect the common defects and recognize them.

关 键 词：贴片LED 图像金字塔 模板匹配 

分 类 号：TP391.7[自动化与计算机技术—计算机应用技术]