计算机科学 ›› 2016, Vol. 43 ›› Issue (Z6): 152-155.doi: 10.11896/j.issn.1002-137X.2016.6A.036

• 模式识别与图像处理 • 上一篇    下一篇

一种新型的PCB图像快速配准算法

王栋,马纯永,陈戈   

  1. 中国海洋大学信息科学与工程学院 青岛266100,中国海洋大学信息科学与工程学院 青岛266100,中国海洋大学信息科学与工程学院 青岛266100
  • 出版日期:2018-12-01 发布日期:2018-12-01

Fast Image Registration Algorithm for PCB Images

WANG Dong, MA Chun-yong and CHEN Ge   

  • Online:2018-12-01 Published:2018-12-01

摘要: PCB图像配准是进行自动光学检测的关键步骤。PCB中往往存在许多相似图形和区域,一般特征点提取和匹配方法效率低,且容易产生误匹配。提出一种以PCB图像中特定几何图形的中心作为特征点,基于相似三角形约束的快速配准算法。提取实测图和标准图中圆形和方形的中心点集进行DT剖分,找出两幅图三角网中的相似三角形集,再对相似三角形的中心点集进行二次剖分和比对,以增强匹配的可靠性。实验证明:该方法计算速度快、匹配正确率高,且能得到均匀分布的正确匹配点。

关键词: 图像配准,DT剖分,相似三角形,PCB

Abstract: PCB(Printed Circuit Board) image registration is a key step in automatic optical inspection.There are many similar graphics and area in PCB.The general method of extracting and matching of feature points is low efficiency and easy to produce false match.A fast registration algorithm based on the similarity triangle constraint was proposed,which takes specific geometric center as the feature points.The sets of centers of round and square were Delaunay triangulated.Similar triangles were found in two triangulation networks and implemented another subdivision and comparison to enhance reliability.Experiments show that the method is rigid and has higher accuracy,which can get the correct matching point of uniform distribution.

Key words: Image registration,Delaunay triangulation,Similar triangle,PCB(printed circuit board)

[1] 胡涛.基于轮廓对比的PCB裸板缺陷检测算法研究[D].武汉:华中科技大学,2009
[2] 张静.PCB表观缺陷的自动光学检测理论与技术[D].成都:电子科技大学,2013
[3] 丁南南.基于特征点的图像配准技术研究[D].长春:中国科学院长春光学精密机械与物理研究所,2012
[4] Szymanski C,Stemmer M R.Automated PCB inspection in small series production based on SIFT algorithm[C]∥2015 IEEE 24th International Symposium on IEEE in Industrial Electronics (ISIE).Buzios,2015:594-599
[5] 张永宏,黄晓华.基于SIFT匹配算法的PCB板缺陷检测[J].计算机测量与控制,2012,20(9):2328-2330
[6] Wu Li-zhen,Niu Yi-feng,Zhang Hui-xia,et al.Robust Feature Point Matching Based on Local Feature Groups (LFGs) and Relative Spatial Configuration[J].Journal of Computational Information Systems,2011,9(7):3235-3244
[7] 陈洁,付冬梅,刘燕.基于相似三角形匹配的红外与可见光图像配准方法[J].激光与红外,2010,40(2):215-218
[8] 张东兴,祝明波,李相平,等.Delaunay三角形剖分约束下的图像配准算法[J].信号处理,2013,29(12):1644-1649
[9] 吴飞,蔡胜渊,郭同强,等.三角形约束下的图像特征点配准方法[J].计算机辅助设计与图形学学报,2010,2(3):1-8
[10] Wu T,et al.A WTLS-Based Method for Remote Sensing Imagery Registration[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(1):102-116
[11] 秦开怀,王海颍,郑辑涛.一种基于Hough变换的圆和矩形的快速检测方法[J].中国图象图形学学报,2010,15(1):109-115
[12] 武晓波,王世新,肖春生.Delaunay三角网的生成算法研究[J].测绘学报,1999,28(1):28-35

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!