Robust tile-based texture synthesis using artificial immune system

Weiming Dong 1 Ning Zhou 2 Jean-Claude Paul 3
3 CAD - Computer Aided Design
LIAMA - Laboratoire Franco-Chinois d'Informatique, d'Automatique et de Mathématiques Appliquées, Inria Paris-Rocquencourt
Abstract : One significant problem in tile-based texture synthesis is the presence of conspicuous seams in the tiles. The reason is that sample patches employed as primary patterns of the tile set may not be well stitched if carelessly picked. In this paper, we introduce a robust approach that can stably generate an ω-tile set of high quality and pattern diversity. First, an extendable rule is introduced to increase the number of sample patches to vary the patterns in an ω-tile set. Second, in contrast to other concurrent techniques that randomly choose sample patches for tile construction, ours uses artificial immune system (AIS) to select the feasible patches from the input example. This operation ensures the quality of the whole tile set. Experimental results verify the high quality and efficiency of the proposed algorithm.
Type de document :
Article dans une revue
Neural Computing & Applications, John MacIntyre, 2009, 〈10.1007/s00521-008-0174-6〉
Liste complète des métadonnées
Contributeur : Weiming Dong <>
Soumis le : mardi 7 septembre 2010 - 12:10:47
Dernière modification le : mercredi 10 octobre 2018 - 14:28:07
Document(s) archivé(s) le : mercredi 8 décembre 2010 - 02:44:50


Fichiers produits par l'(les) auteur(s)




Weiming Dong, Ning Zhou, Jean-Claude Paul. Robust tile-based texture synthesis using artificial immune system. Neural Computing & Applications, John MacIntyre, 2009, 〈10.1007/s00521-008-0174-6〉. 〈inria-00515540〉



Consultations de la notice


Téléchargements de fichiers