Topological Attribute Patterns for Texture Recognition - ENSTA Paris - École nationale supérieure de techniques avancées Paris Accéder directement au contenu
Article Dans Une Revue Pattern Recognition Letters Année : 2016

Topological Attribute Patterns for Texture Recognition

Résumé

An efficient texture modelling framework based on Topological Attribute Patterns (TAP) is presented considering topology related attributes calculated from Local Binary Patterns (LBP). Our main contribution is to introduce new efficient mapping mechanisms that improve some typical mappings for LBP-based operators in texture classification such as rotation invariant patterns (ri), rotation invariant uniform patterns (riu2), and Local Binary Count (LBC). Like them, the proposed approach allows contrast and rotation invariant image description using more compact descriptors by projecting binary patterns to a reduced feature space. However, its expressiveness, and then its discrimination capability, is higher, since it includes additional information, related to the connected components of the binary patterns. The proposed mapping, evaluated and compared with different popular mappings, validates the interest of our approach. We then develop Complemented Patterns of Topological Attributes (CTAP) that generalise TAP model and exploit complemented information to further enhance its discrimination capability, and evaluate it on different texture datasets.
Fichier principal
Vignette du fichier
PRL16.pdf (368.96 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01451126 , version 1 (31-01-2017)

Identifiants

Citer

Thanh G Nguyen, Antoine Manzanera, Walter G Kropatsch, Xuan Son Nguyen. Topological Attribute Patterns for Texture Recognition. Pattern Recognition Letters, 2016, 80, pp.91 - 97. ⟨10.1016/j.patrec.2016.06.003⟩. ⟨hal-01451126⟩
274 Consultations
259 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More