Institute of Information Theory and Automation

You are here

Publication details

Natural Material Recognition with Illumination Invariant Textural Features

Conference Paper (international conference)

Vácha Pavel, Haindl Michal


serial: 20th International Conference on Pattern Recognition, p. 858-861

action: 20th International Conference on Pattern Recognition ICPR 2010, (Istanbul, TR, 23.08.2010-26.08.2010)

research: CEZ:AV0Z10750506

project(s): 1M0572, GA MŠk, GA102/08/0593, GA ČR, 2C06019, GA MŠk

keywords: texture, colour, Markov random field, illumination invariance

preview: Download

abstract (eng):

A visual appearance of natural materials fundamentally depends on illumination conditions, which significantly complicates a real scene analysis. We propose textural features based on fast Markovian statistics, which are simultaneously invariant to illumination colour and robust to illumination direction. No knowledge of illumination conditions is required and a recognition is possible from a single training image per material. Material recognition is tested on the currently most realistic visual representation - Bidirectional Texture Function (BTF), using the Amsterdam Library of Textures (ALOT), which contains 250 natural materials acquired in different illumination conditions. Our proposed features significantly outperform several leading alternatives including Local Binary Patterns (LBP, LBP-HF) and Gabor features.

RIV: BD

2012-12-21 16:10