Sciweavers

Share
ICPR
2004
IEEE

Training of Classifiers Using Virtual Samples Only

9 years 6 months ago
Training of Classifiers Using Virtual Samples Only
This paper describes the training of classifiers entirely based on virtual images, rendered by a ray-tracing software. Two classifiers, a support vector machine and a polynomial classifier, are trained solely with virtual samples and used for classification of real samples. The objects to be distiguished are holes vs. garbage (non-holes) out of a set of hole candidates in images of flanges. We analysed the effect of different classifier parameters and manipulation of the virtual samples.
Annika Kuhl, Lars Krüger, Christian Wöhl
Added 09 Nov 2009
Updated 09 Nov 2009
Type Conference
Year 2004
Where ICPR
Authors Annika Kuhl, Lars Krüger, Christian Wöhler, Ulrich Kressel
Comments (0)
books