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.
Originalsprache | Englisch |
---|---|
Titel | Computer Vision, Imaging and Computer Graphics. Theory and Applications |
Redakteure/-innen | AlpeshKumar Ranchordas, João Madeiras Pereira, Hélder J. Araújo, João Manuel R. S. Tavares |
Seitenumfang | 14 |
Band | 68 |
Erscheinungsort | Berlin, Heidelberg |
Herausgeber (Verlag) | Springer Berlin Heidelberg |
Erscheinungsdatum | 2010 |
Seiten | 269-282 |
ISBN (Print) | 978-3-642-11839-5 |
ISBN (elektronisch) | 978-3-642-11840-1 |
DOIs | |
Publikationsstatus | Veröffentlicht - 2010 |
Veranstaltung | International Joint Conference - Lissabon, Portugal Dauer: 05.02.2009 → 08.02.2009 |