An Efficient Method of PCB Images Stitching

In solder paste inspection, since the camera' field of view is small relative to the size of PCB, it is necessary to stitch the partial PCB images taken in different parts. Stitching PCB images requires real-time processing, while common existing methods are not satisfactory, so this paper proposes a novel method to further speed up image stitching. This study contributes in three ways: First, a 4-step improved method used for corner detection is introduced, which builds on the well-known FAST corner detection method. Second, the nearest and next nearest neighbor ratio method, bidirectional matching method and RANSAC are adopted to reduce the possibility of mismatching and optimize the performance of the corner matching. Third, several corner detection methods are compared. Performances in terms of quantitative and qualitative results are discussed so as to move towards the selection of the most appropriate method. The experiments demonstrate that the improved image stitching method outperforms other methods both in efficiency and accuracy.

[1]  Hammam A. Alshazly,et al.  Image Features Detection, Description and Matching , 2016 .

[2]  Jingjing Zhang,et al.  Research on rubbing image mosaic based on SIFT feature , 2017, 2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD).

[3]  Zhou Lian-ling Research of parsing Gerber file in PCB automatic optical inspection , 2012 .

[4]  M. Kamruzzaman,et al.  A machine vision based automatic system for real time recognition and sorting of Bangladeshi bank notes. , 2008, 2008 11th International Conference on Computer and Information Technology.

[5]  Tom Drummond,et al.  Machine Learning for High-Speed Corner Detection , 2006, ECCV.

[6]  Tom Drummond,et al.  Faster and Better: A Machine Learning Approach to Corner Detection , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[8]  Hui A Contour-Based Approach to Multisensor Image Registration , 2009 .