Optical inspection of welding seams

Abstract

We present a framework for automatic inspection of welding seams based on specular reflections. To this end, we make use of a feature set - called specularity features (SPECs) - that describes statistical properties of specular reflections. For the classification we use a one-class support-vector approach. We show that the SPECs significantly outperform other approaches since they capture more complex characteristics and dependencies of shape and geometry. We obtain an error rate of 3.8%, which corresponds to the level of human performance. © 2010 Springer-Verlag Berlin Heidelberg.