Publication details

Texture modelling

Conference Paper (international conference)

Haindl Michal


serial: Proceedings of the World Multiconference on Systemics, Cybernetics and Informatics, p. 634-639 , Eds: Sanchez B., Pineda J. M., Wolfmann J., Bellahsene Z., Ferri F.

publisher: International Institute of Informatics and Systemics, (Orlando 2000)

edition:

action: World Multiconference on Systemics, Cybernetics and Informatics, (Orlando, US, 23.07.2000-26.07.2000)

research: AV0Z1075907

project(s): GA102/00/0030, GA ČR

abstract (eng):

Two our fast algorithms for realistic multispectral texture modelling are compared. Both algorithms start with spectral factorization of an input multispectral texture image using the Karhunen-Loeve expansion. Single orthogonal monospectral components are further decomposed into a multi-resolution grid and each resolution data are independently modeled by their dedicated monospectral models which are either a Gaussian Markov random field model (GMRF) or a causal simultaneous autoregressive model (CAR).

Cosati: 09K

RIV: BD