[1]黄靖,陈小勇,罗堪,等.基于MSURF算法的PCB图像配准[J].福建工程学院学报,2018,16(03):275-280.[doi:10.3969/j.issn.1672-4348.2018.03.014]
　HUANG Jing,CHEN Xiaoyong,LUO Kan,et al.A modified SURF algorithm for PCB image registration[J].Journal of FuJian University of Technology,2018,16(03):275-280.[doi:10.3969/j.issn.1672-4348.2018.03.014]
点击复制

基于MSURF算法的PCB图像配准()
分享到：

《福建工程学院学报》[ISSN:2097-3853/CN:35-1351/Z]

卷:
第16卷
期数:
2018年03期
页码:
275-280
栏目:
出版日期:
2018-06-25

文章信息/Info

Title:
A modified SURF algorithm for PCB image registration
作者:
黄靖; 陈小勇; 罗堪; 季雨枫; 何松; 林龙彬; 李俊男
福建工程学院信息科学与工程学院
Author(s):
HUANG Jing ;  CHEN Xiaoyong;  LUO Kan;  JI Yufeng;  HE Song;  LIN Longbin;  LI Junnan
School of Information Science and Engineering, Fujian University of Technology
关键词:
PCB配准;  特征提取;  SURF
Keywords:
PCB registration; feature extraction;  SURF(speeded up robust feature)
分类号:
TP391
DOI:
10.3969/j.issn.1672-4348.2018.03.014
文献标志码:
A
摘要:
针对PCB板缺陷检测中用传统SURF算法进行图像匹配精度不高的问题，提出一种生产工序中运动平台机械误差先验信息与SURF特征提取相结合的MSURF配准算法。通过提取计算SURF特征点，求出对应特征点对的距离；在PCB运动平台机械误差分析的基础上，依据先验阈值边界条件筛除异常匹配特征点对；求出两幅图像满足最小二乘拟合准则的映射关系，并将其用于图像配准。在机械运动误差0.05~0.10 mm范围内对42 mm×42 mm的PCB图像配准实验，结果表明：提出的图像配准方法速度快、精度高，适用于产线PCB缺陷检测。
Abstract:
Aiming at the low accuracy of the traditional SURF algorithm in image matching for PCB board defect detection, a modified SURF registration algorithm was proposed that combined the prior information of the mechanical error of the motion platform and the SURF feature extraction in the production process. Firstly, the distance between the corresponding feature point pairs was obtained by extracting and calculating the SURF feature points. Secondly, based on the mechanical error analysis of the PCB motion platform, the abnormal matching feature point pairs were screened according to prior threshold boundary conditions. Finally, the mapping relation of two images satisfying the least square fitting criterion was obtained and used for image registration. The results of the 42 mm×42 mm PCB image registration experiments conducted with the error range of mechanical motion controlled to be 0.05~0.10 mm indicate that the image registration method proposed is fast and accurate, thereby suitable for PCB defect detection in production.

参考文献/References:

[1] 王耀南, 刘良江, 周博文．一种基于混沌优化算法的PCB 板元件检测方法［J］．仪器仪表学报,2010，31(2):411-415．
[2] XIA R, ZHAO J, LIU Y. A robust feature-based registration method of multimodal image using phase congruency and coherent point drift[C].Mippr:Pattern Recognition & Computer Vision, SPIE,2013, 8919: 401-410.
[3] ZHANG J, WANG J, WANG X, et al. Multi-modal image registration with joint structure tensor and local entropy[J]. International Journal of Computer Assisted Radiology and Surgery, 2015,10(11): 1765-1775.
[4] ROCHE A, MALANDAIN G, PENNEC X, et al. The correlation ratio as a new similarity measure for multimodal image registration[C]. International Conference on Medical Image Computing & Computer-assisted Intervention, 1998, 1496: 1115-1124.
[5] MAES F, COLLIGNON A, VANDERMEULEN D, et al. Multimodality image registration by maximization of mutual information[J]. IEEE Trans Med Imaging, 1997, 16(2): 187-198.
[6] KAO S C，HO C. Monitoring a process of exponentially distributed characteristics through minimizing the sum of the squared differences[J]. Quality & Quantity,2007,41(1):137-149.
[7] CHEN J, TIAN J. Real-time multi-modal rigid registration based on a novel symmetric-SIFT descriptor [J]. Progress in Natural Science: Materials International, 2008, 19(5): 643-651.
[8] BARRERA F, LUMBRERAS F, SAPPA A D. Multispectral piecewise planar stereo using Manhattan-world assumption[J]. Pattern Recognition Letter, 2013, 34(1): 52-61.
[9] 侯北平,朱文,马连伟，等．基于形状特征的移动目标实时分类研究[J]．仪器仪表学报,2010,31(8):1819-1825．
[10] LINDEBERG T．Edge detection and ridge detection with automatic scale selection［J］．International Journal of Computer Vision, 1998, 30(2): 117-154．
[11] LOWE D G．Distinctive image features from scale-invariant key points［J］．International Journal of Compute1 Vision, 2004，60(2): 91-110．
[12] 王永明，王贵锦．图像局部不变性特征与描述［M］．北京:国防工业出版社，2010．
[13] 傅卫平，秦川，刘佳．基于 SIFT 算法的图像目标匹配与定位［J］．仪器仪表学报，2011，32(1):163-169．
[14] 郑永斌，黄新生，丰松江．SIFT 和旋转不变 LBP 相结合的图像匹配算法［J］．计算机辅助设计与图形学学报，2010，22(2): 286-292．
[15] BAUER J，SUNDERHAUF N，PROTZEL P． Comparing several implementations of two recently published feature detectors［C］.Proceedings of the international conference on intelligence and autonomous systems，Toulouse，France，2007．
[16] 高素青，谭勋军，黄承夏．一种基于SURF的图像配准改进算法［J］．解放军理工大学学报(自然科学版)，2013，14(4): 372 －376．
[17] 陈艺虾,孙权森,徐焕宇,等.SURF算法和RANSAC算法相结合的遥感图像匹配方法[J].计算机科学与探索,2012,6(9) :822-828.

更新日期/Last Update: 2018-06-25