WELDING INSPECTION USING NOVEL SPECULARITY FEATURES AND A ONE-CLASS SVM

Fabian Timm, Sascha Klement, Erhardt Barth, Thomas Martinetz

2009

Abstract

We present a framework for automatic inspection of welding seams based on specular reflections. Therefore, we introduce a novel feature set -- called specularity features (SPECs) -- describing statistical properties of specular reflections. For classification we use a one-class support-vector approach. The SPECs significantly outperform statistical geometric features and raw pixel intensities, since they capture more complex characteristics and depencies of shape and geometry.We obtain an error rate of 9%, which corresponds to the level of human performance.

Paper Citation

in Harvard Style

Timm F., Klement S., Barth E. and Martinetz T. (2009). WELDING INSPECTION USING NOVEL SPECULARITY FEATURES AND A ONE-CLASS SVM . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 145-152. DOI: 10.5220/0001776301450152

in Bibtex Style

@conference{visapp09,
author={Fabian Timm and Sascha Klement and Erhardt Barth and Thomas Martinetz},
title={WELDING INSPECTION USING NOVEL SPECULARITY FEATURES AND A ONE-CLASS SVM},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={145-152},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001776301450152},
isbn={978-989-8111-69-2},
}

in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)
TI - WELDING INSPECTION USING NOVEL SPECULARITY FEATURES AND A ONE-CLASS SVM
SN - 978-989-8111-69-2
AU - Timm F.
AU - Klement S.
AU - Barth E.
AU - Martinetz T.
PY - 2009
SP - 145
EP - 152
DO - 10.5220/0001776301450152