Abstract
Template based printed circuit board (PCB) inspection needs aligning the test image to the reference image, but most of the current image alignment methods are very time-consuming. In order to improve the efficiency of PCB inspection, we put forward an image alignment algorithm based on connected components matching, and design a procedure to detect defects and classify defects. Experimental results show that the proposed method achieves good results for real single layer, bare PCB inspection.
Publisher
Trans Tech Publications, Ltd.
Reference8 articles.
1. Madhav Moganti, Fikret Ercal, Cihan H. Dagli, and Shou Shunekawa. Automatic PCB Inspection Algorithm: A Survey. Computer vision and image understanding, 63(2)(1996): 287-313.
2. Fabiana R. Leta, Flávio F. Feliciano, Flavius P. R. Martins. Computer Vision System For Printed Circuit Board Inspection. ABCM Symposium Series in Mechatronics, Vol. 3, pp.623-632, (2008).
3. W.Y. Wu, M. J. Wang, and C. M. Liu, Automated inspection of printed circuit boards through machine vision, Computer in Industry, 28 (2), pp.103-111, (1996).
4. C. -H. Yeh and D. -M. Tsai, A Rotation-Invariant and Non-Referential Approach for Ball Grid Array (BGA) Substrate Conducting Path Inspection, Adv Manuf Technol (2001) 17: 412–424.
5. Tatibana, M. H., Lotufo, R. de A., Novel Automatic PCB Inspection Technique Based on Connectivity". In: X Brazilian Symp. on Computer Graphics and Image Processing-SIBGRAPI, 97, Campos de Jordão, 1997, pp.187-194.