Sciweavers

BMVC
2000

Region-Based Object Recognition: Pruning Multiple Representations and Hypotheses

13 years 4 months ago
Region-Based Object Recognition: Pruning Multiple Representations and Hypotheses
We address the problem of object recognition in computer vision. We represent each model and the scene in the form of Attributed Relational Graph. A multiple region representation is provided at each node of the scene ARG to increase the representation reliability. The process of matching the scene ARG against the stored models is facilitated by a novel method for identifying the most probable representation from among the multiple candidates. The scene and model graph matching is accomplished using probabilistic relaxation which has been modified to minimise the label clutter. The experimental results obtained on real data demonstrate promising performance of the proposed recognition system.
Alireza Ahmadyfard, Josef Kittler
Added 01 Nov 2010
Updated 01 Nov 2010
Type Conference
Year 2000
Where BMVC
Authors Alireza Ahmadyfard, Josef Kittler
Comments (0)