作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2008, Vol. 34 ›› Issue (10): 210-211. doi: 10.3969/j.issn.1000-3428.2008.10.076

• 人工智能及识别技术 • 上一篇    下一篇

基于改进Radon变换的芯片几何特征检测

孔华锋1,2,鲁宏伟1,胡东红3   

  1. (1. 华中科技大学计算机科学与技术学院,武汉 430074;2. 华中科技大学图像识别与人工智能研究所,武汉 430074;3. 湖北大学物理学与电子技术学院,武汉 430062)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-05-20 发布日期:2008-05-20

Geometry Feature Detection of Chip Based on Improved Radon Transform

KONG Hua-feng1,2, LU Hong-wei1, HU Dong-hong3   

  1. (1. School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan 430074; 2. Institute of Pattern Recognition and Artificial Intelligence, Huazhong University of Science and Technology, Wuhan 430074;3. School of Physics and Electronic Technology, Hubei University, Wuhan 430062)
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-05-20 Published:2008-05-20

摘要: 在分析芯片几何特征检测的基础上,根据Radon变换的基本思想,提出一种用于芯片几何特征检测的改进Radon变换算法,对该算法在矩形芯片边界直线的检测过程中确定边界直线、剔除干扰和加快速度的具体应用进行了研究。试验结果表明,与传统算法相比,该算法可以有效提高识别效率30%,同时具有鲁棒性好及检测结果准确等特点。

关键词: Radon变换, 直线检测, 图像处理, 模式识别

Abstract: Basing on analysis of geometry feature of chip and fundament of Radon transform, this paper presents a method for detecting the geometry feature of chip based on improved Radon transform. The algorithm research focuses on detecting edge lines, eliminating the disturbing and improving performance in the boundary detection process of rectangular chip. The enhancement on the efficiency of the algorithm is about 30% proved. Experimental result shows that this algorithm is robust and the result is accurate.

Key words: Radon transform, line detection, image processing, pattern recognition

中图分类号: