首页> 外文会议>Computer Applications in Industry and Engineering >Printed Circuit Board Inspection Using Support Vector Machine
【24h】

Printed Circuit Board Inspection Using Support Vector Machine

机译:使用支持向量机的印刷电路板检查

获取原文
获取原文并翻译 | 示例

摘要

This paper proposes an efficient method for inspecting defects of printed circuit boards(PCBs) through the use of a Support Vector Machine to classify the PCB defects. An Image comparison technique is used to extract characteristic features of PCB defects. The SVM then uses these features to identify the optimal separating hyperplane by maximizing the distance of other classes from the hyperplane. As a result, each defect of PCB can then be classified into one of several predefined types. The proposed method has been implemented and tested with various types of PCB defect Experimental results show that the proposed method produces a high classification rate in the nonlinearly separable problem of classifying the PCB defects.
机译:本文提出了一种通过使用支持向量机对印刷电路板(PCB)缺陷进行检查的有效方法。图像比较技术用于提取PCB缺陷的特征。然后,SVM使用这些功能,通过最大化其他类别与超平面的距离来识别最佳的分离超平面。结果,可以将PCB的每个缺陷分类为几种预定义类型之一。该方法已在各种类型的PCB缺陷上得到了实现和测试。实验结果表明,该方法在非线性可分离的PCB缺陷分类问题中具有很高的分类率。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号