Texton theory revisited: A bag-of-words approach to combine textons

Susana Alvarez, Maria Vanrell

Producció científica: Contribució a una revistaArticleRecercaAvaluat per experts

38 Cites (Scopus)


The aim of this paper is to revisit an old theory of texture perception and update its computational implementation by extending it to colour. With this in mind we try to capture the optimality of perceptual systems. This is achieved in the proposed approach by sharing well-known early stages of the visual processes and extracting low-dimensional features that perfectly encode adequate properties for a large variety of textures without needing further learning stages. We propose several descriptors in a bag-of-words framework that are derived from different quantisation models on to the feature spaces. Our perceptual features are directly given by the shape and colour attributes of image blobs, which are the textons. In this way we avoid learning visual words and directly build the vocabularies on these low-dimensional texton spaces. Main differences between proposed descriptors rely on how co-occurrence of blob attributes is represented in the vocabularies. Our approach overcomes current state-of-art in colour texture description which is proved in several experiments on large texture datasets. © 2012 Elsevier Ltd.
Idioma originalEnglish
Pàgines (de-a)4312-4325
RevistaPattern Recognition
Estat de la publicacióPublicada - 1 de gen. 2012


Navegar pels temes de recerca de 'Texton theory revisited: A bag-of-words approach to combine textons'. Junts formen un fingerprint únic.

Com citar-ho