Publication details

A multiresolution causal colour texture model

Conference Paper (international conference)

Haindl Michal, Havlíček Vojtěch


serial: Advances in Pattern Recognition. Proceedings, p. 114-122 , Eds: Ferri F. J., Inesta J. M., Amin A., Pudil P.

publisher: Springer, (Berlin 2000)

edition:

action: Joint IAPR International Workshops SSPR 2000 and SPR 2000, (Alicante, ES, 30.08.2000-01.09.2000)

research: AV0Z1075907

project(s): GA102/00/0030, GA ČR, ISE-86L8-13, Hewlett Packard, GA106/00/1715, GA ČR

abstract (eng):

An efficient recursive algorithm for realistic colour texture synthesis is proposed. The algorithm starts with spectral factorization of an input colour texture image using the Karhunen-Loeve decorrelation. Single orthogonal monospectral components are further decomposed into a multi-resolution grid and each resolution data are independently modeled by their dedicated simultaneous causal autoregressive random field model (CAR). We estimate an optimal contextual neighbourhood and model parameters.

Cosati: 09K

RIV: BD