Multimodal object recognition using random clustering trees

Abstract

In this paper, we present an object recognition approach that in addition allows to discover intra-class mo dalities exhibiting high-correlated visual information. Unlike to more conventional approaches based on computing multiple sp ecialized classiers, the proposed approach combines a single classier, Boosted Random Ferns (BRFs), with probabilistic Latent Semantic Analysis (pLSA) in order to recognize an object class and to find automatically the most prominent intra-class appearance mo dalities (clusters) through tree-structured visual words. The proposed approach has b een validated in synthetic and real experiments where we show that the method is able to recognize objects with multiple appearance