Sciweavers

CVPR
2006
IEEE

Perception Strategies in Hierarchical Vision Systems

14 years 5 months ago
Perception Strategies in Hierarchical Vision Systems
Flat appearance-based systems, which combine clever image representations with standard classifiers, might be the most effective way to recognize objects using current technologies. In the future, however, it seems probable that hierarchical representations might have better performance. In such systems, the image representation consists of a sequence of sets of features, where each subsequent set is computed based on the previous sets. The main contributions of this paper are to: (1) pose the question "what is the best way to employ discriminative methods for hierarchical image representations?"; (2) enumerate some of the alternative hierarchies while drawing connections to recent work by brain researchers; (3) study experimentally the different alternatives. As we will show, the strategy used can make a substantial difference.
Lior Wolf, Stanley M. Bileschi, Ethan Meyers
Added 12 Oct 2009
Updated 28 Oct 2009
Type Conference
Year 2006
Where CVPR
Authors Lior Wolf, Stanley M. Bileschi, Ethan Meyers
Comments (0)