A Flexible PCB Inspection System Based on Statistical Learning
With the large variations in appearance for different kinds of defects in Printed Circuit Boards (PCBs), conventional rule-based inspection algorithms become insufficient for detecting and classifying defects. In this study, an automated PCB inspection system based on statistical learning strategies is developed. First, the partial Hausdorff distance is used to ascertain the positions of defects. Next, the defect patterns are categorized using the Support Vector Machine (SVM) classifier. Defects without regularities in appearance, which cannot be categorized, are identified through the regional defectiveness by comparing the block-wise probability distributions. Experimental results on a real visual inspection platform show that the proposed system is very effective for inspecting a variety of PCB defects.
KeywordsPCB SVM Automated visual inspection Image classification Defect classification Image alignment
This work was partially supported by the Center for Measurement Standards, Industrial Technology Research Institute, Hsinchu, Taiwan.
- 7.Spence, H. F. (1993). Printed circuit board diagnosis using artificial neural networks and circuit magnetic fields. In Proc. IEEE Systems Readiness Technology Conference, pp. 41–45.Google Scholar
- 8.Hodges, S. E., & Richards, R. J. (1995). Fast multi-resolution image processing for PCB manufacture. IEE Colloquium on Multi-resolution Modeling and Analysis in Image Processing and Computer Vision, pp. 1–8.Google Scholar
- 12.Kim, N. H., Pyun, J. Y., Choi, K. S., Choi, B. D., & Ko, S. J. (2001). Real-time inspection system for printed circuit boards. In Proc. 6th IEEE Int. Symp. Industrial Electronics, pp. 12–16.Google Scholar
- 13.Tominaga, S., & Okamoto, S. (2003). Reflectance-based material classification for printed circuit boards. In Proc. 12th Int. Conf. Image Analysis and Processing, pp. 238–243.Google Scholar
- 14.Ibrahim, Z., & Al-Attas, S. A. R. (2004). Wavelet-based printed circuit board inspection system. International Journal of Signal Processing, 1(1), 73–79.Google Scholar
- 21.Schölkopf, B., & Smola, A. J. (2001). Learning with kernels: Support vector machines, regularization, optimization, and beyond. MIT Press.Google Scholar
- 23.Platt, J. C., Cristianini, N., & Shawe-Taylor, J. (2000). Large margin DAG’s for multiclass classification. Adv. Neural Information Processing Systems, vol. 12, pp. 547–553. MIT Press.Google Scholar
- 26.Cover, T. M., & Thomas, J. A. (1991). Elements of information theory. Wiley.Google Scholar
- 27.Gonzalez, R. C., & Woods, R. E. (2001). Digital image processing (2nd edn.). Prentice Hall.Google Scholar
- 28.Benhabib, B., Charette, C. R., Smith, K. C., & Yip, A. M. (1990). Automatic visual inspection of printed circuit boards: an experimental system. International Journal of Robotics & Automation, 5(2), 1034–1044.Google Scholar
- 29.Widrow, B., & Hoff, M. E. (1960). Adaptive switching circuits. IRE WESCON Convention Record, Part 4 (pp. 96–104). New York: IRE.Google Scholar