0410848 20240103182243.620060210235959.9 0-7695-1699-8 1 Los Alamitos IEEE Computer Society 2002 4 s. 255-258KasturiR.LaurendeauD.SuenC. texture synthesis cav_un_auth*0101093 Haindl Michal UTIA-B Department of Pattern Recognition Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0101100 Havlíček Vojtěch UTIA-B Department of Pattern Recognition Ústav teorie informace a automatizace AV ČR, v. v. i. 09K IST-2001-34744 Commission EC XE cav_un_auth*0200688 GA102/00/0030 GA ČR cav_un_auth*0004016 GA106/00/1715 GA ČR cav_un_auth*0005263 CEZ:AV0Z1075907 A fast recursive model-based algorithm for realistic colour texture synthesis is proposed. The algorithm starts with a colour texture image decomposition into a multi-resolution grid. Each band pass colour factors are independently modelled by their dedicated 3D causal autoregressive random field models. We estimate an optimal contextual neighbourhood and parameters for each of the CAR submodel. Finally the synthesized multi-resolution colour texture pyramid is collapsed into the resulting texture. cav_un_auth*0212920 International Conference on Pattern Recognition /16./ Québec City CA 11.08.2002-15.08.2002 BD RO http://hdl.handle.net/11104/0130935 UTIA-B 20020062 2002 2002 Los Alamitos IEEE Computer Society 0-7695-1699-8 Proceedings of the 16th International Conference on Pattern Recognition 255 258 Kasturi R. 340 Laurendeau D. 340 Suen C. 340