Title :
Modelling composite shapes by Gibbs random fields
Author :
Flach, Boris ; Schlesinger, Dmitrij
Author_Institution :
Czech Tech. Univ., Prague, Czech Republic
Abstract :
We analyse the potential of Gibbs Random Fields for shape prior modelling. We show that the expressive power of second order GRFs is already sufficient to express spatial relations between shape parts and simple shapes simultaneously. This allows to model and recognise complex shapes as spatial compositions of simpler parts.
Keywords :
Markov processes; shape recognition; GRF; Gibbs random fields; composite shape modelling; shape recognition; Estimation; Image color analysis; Image edge detection; Image segmentation; Labeling; Mathematical model; Shape;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on
Conference_Location :
Providence, RI
Print_ISBN :
978-1-4577-0394-2
DOI :
10.1109/CVPR.2011.5995726
