Texture classification with minimal training images

Conference item

The objective of this work is classifying texture from a single image under unknown lighting conditions. The current and successful approach to this task is to treat it as a statistical learning problem and learn a classifier from a set of training images, but this requires a sufficient number and variety of training images. We show that the number of training images required can be drastically reduced (to as few as three) by synthesizing additional training data using photometric stereo. We demonstrate the method on the PhoTex and ALOT texture databases. Despite the limitations of photometric stereo, the resulting classification performance surpasses the state of the art results.

Authors: Targhi, AT; Geusebroek, J-M; Zisserman, A

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: IEEE
• Host title: 2008 19th International Conference on Pattern Recognition
• Publication date: 2009-01-23
• Event title: 19th International Conference on Pattern Recognition (ICPR 2008)
• Event location: Tampa, FL, USA
• Event start date: 2008-12-08
• Event end date: 2008-12-11
• DOI: 10.1109/ICPR.2008.4761388
• ISSN: 1051-4651
• ISBN: 978-1-4244-2174-9
• Language: English
• Keywords: image databases; filters; availability; statistical learning; surface treatment; image generation; surface texture; lighting; photometry; training data