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. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-11840-1_20 | Communications in Computer and Information Science |
Field | DocType | Volume |
Computer vision,Specularity,Pattern recognition,Computer science,Specular reflection,Binary image,Word error rate,Feature set,Artificial intelligence,Linear discriminant analysis,Fresnel lens,Welding | Conference | 68 |
ISSN | Citations | PageRank |
1865-0929 | 1 | 0.35 |
References | Authors | |
12 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Fabian Timm | 1 | 11 | 1.99 |
Thomas Martinetz | 2 | 1462 | 231.48 |
Erhardt Barth | 3 | 653 | 58.33 |