ECAI 2004 Conference Paper

[full paper]

Learning to focus attention on discriminative regions for object detection

Gerald Fritz, Lucas Paletta, Christin Seifert, Horst Bischof

A major task of visual attention is to focus processing on regions of interest to enable rapid and robust object search. Instead of integrating generic feature extraction into object specific interpretation we strictly pursue a top-down approach. Early features are tuned to selectively respond to task related visual features. In this work we determine discriminative regions from the information content in the local appearances patterns. A rapid mapping from appearances to discriminative regions is estimated using decision trees. The focus of attnetion on discriminative patterns enables then efficient detection and the definition of a sparse object representation. Evaluation of complete image analyis under various degrees of partial occlusion and image noise resulted in highly ropbust recognition even in the presence of severe occlusion and noise effects.

Keywords: visual attention, object recognition, cascaded detection, decision trees

Citation: Gerald Fritz, Lucas Paletta, Christin Seifert, Horst Bischof: Learning to focus attention on discriminative regions for object detection. In R.López de Mántaras and L.Saitta (eds.): ECAI2004, Proceedings of the 16th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2004, pp.932-936.