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.
Original languageEnglish
Title of host publicationComputer Vision, Imaging and Computer Graphics. Theory and Applications
EditorsAlpeshKumar Ranchordas, João Madeiras Pereira, Hélder J. Araújo, João Manuel R. S. Tavares
Number of pages14
Volume68
Place of PublicationBerlin, Heidelberg
PublisherSpringer Berlin Heidelberg
Publication date2010
Pages269-282
ISBN (Print)978-3-642-11839-5
ISBN (Electronic)978-3-642-11840-1
DOIs
Publication statusPublished - 2010
EventInternational Joint Conference - Lissabon, Portugal
Duration: 05.02.200908.02.2009

Fingerprint

Dive into the research topics of 'Optical Inspection of Welding Seams'. Together they form a unique fingerprint.

Cite this