Material Classification for Printed Circuit Boards by Kernel Fisher Discriminant Analysis
This paper proposes an approach to a reliable material classification for printed circuit boards by kernel Fisher discriminant analysis. The proposed approach uses only three dimensional features of the surface-spectral reflectance reduced from the high-dimensional spectral imaging data for effectively classifying the surface material on each pixel point into several elements such as substrate, metal, resist, footprint, and silk-screen paint. We show that a linear classification of these elements does not work well, because the feature distribution is not well separated in the three dimensional feature space. In this paper, a kernel technique is used to constructs a subspace where the class separability is maximized in a high-dimensional feature space. The performance of the proposed method is compared with the previous algorithms using the high-dimensional spectral data.
KeywordsMaterial classification printed circuit board spectral reflectance region segmentation kernel discriminant analysis
- 4.Ibrahim, Z., Al-Attas, S.A.R.: Wavelet-based Printed Circuit Board Inspection Algorithm. Integrated Computer-Aided Engineering 12, 201–213 (2005)Google Scholar
- 6.Leta, F.R., Feliciano, F.F., Martins, F.P.R.: Computer Vision System for Printed Circuit Board Inspection. In: ABCM Symp. Series in Mechatronics, vol. 3, pp. 623–632 (2008)Google Scholar
- 7.Tominaga, S.: Material Identification via Multi-Spectral Imaging and Its Application to Circuit Boards. In: 10th Color Imaging Conference, Color Science, Systems and Applications, Scottsdale, Arizona, pp. 217–222 (2002)Google Scholar
- 8.Tominaga, S., Okamoto, S.: Reflectance-Based Material Classification for Printed Circuit Boards. In: 12th Int. Conf. on Image Analysis and Processing, Italy, pp. 238–243 (2003)Google Scholar