Colour and rotation invariant textural features based on Markov random fields

0357314 - ÚTIA 2011 RIV NL eng J - Journal Article
Vácha, Pavel - Haindl, Michal - Suk, Tomáš
Colour and rotation invariant textural features based on Markov random fields.
Pattern Recognition Letters. Roč. 32, č. 6 (2011), s. 771-779. ISSN 0167-8655. E-ISSN 1872-7344
R&D Projects: GA MŠMT 1M0572; GA ČR GA102/08/0593
Grant - others:GA MŠk(CZ) 2C06019
Institutional research plan: CEZ:AV0Z10750506
Keywords : Image modelling * colour texture * Illumination invariance * Markov random field * rotation invariance
Subject RIV: BD - Theory of Information
Impact factor: 1.034, year: 2011
http://library.utia.cas.cz/separaty/2011/RO/vacha-0357314.pdf

A visual appearance of natural materials significantly depends on acquisition circumstances, particularly illumination conditions and viewpoint position, whose variations cause difficulties in the analysis of real scenes. We address this issue with novel texture features, based on fast estimates of Markovian statistics, that are simultaneously rotation and illumination invariant. The proposed features are invariant to inplane material rotation and illumination spectrum (colour invariance), they are robust to local intensity changes (cast shadows) and illumination direction. No knowledge of illumination conditions is required and recognition is possible from a single training image per material. The material recognition is tested on the currently most realistic visual representation – Bidirectional Texture Function (BTF), using CUReT and ALOT texture datasets with more than 250 natural materials.
Permanent Link: http://hdl.handle.net/11104/0195620