Characterization and recognition of dynamic textures based on the 2D+T curvelet transform

The research context of this article is the recognition and description of dynamic textures. In image processing, the wavelet transform has been successfully used for characterizing static textures. To our best knowledge, only two works are using spatio-temporal multiscale decomposition based on tensor product for dynamic texture recognition. One contribution of this article is to analyse and compare the ability of the 2D+T curvelet transform, a geometric multiscale decomposition, for characterizing dynamic textures in image sequences. Two approaches using the 2D+T curvelet transform are presented and compared using three new large databases. A second contribution is the construction of these three publicly available benchmarks of increasing complexity. Existing benchmarks are either too small, not available or not always constructed using a reference database. Feature vectors used for recognition are described Sloven Dubois Université de Lyon, F-42023, CNRS, UMR5516, Laboratoire Hubert Curien, F-42000, Université de Saint-Étienne, Jean Monnet, F-42000, Saint-Étienne, France Tel.: +33 477 915 797 Fax: +33 477 915 781 E-mail: [email protected] Renaud Péteri Laboratoire Mathématiques, Image et Applications, Avenue Michel Crépeau, 17042 La Rochelle, France Tel.: +33 546 457 219 Fax: +33 546 458 240 E-mail: [email protected] Michel Ménard Laboratoire Informatique, Image et Interaction, Avenue Michel Crépeau, 17042 La Rochelle, France Tel.: +33 546 458 296 Fax: +33 546 458 242 E-mail: [email protected] as well as their relevance, and performances of the different methods are discussed. Finally, future prospects