Object recognition systems aiming to work in real world settings should use multiple cues in order to achieve robustness. We present a new cue integration scheme which extends the...
Abstract. This paper proposes an expert peering system for information exchange. Our objective is to develop a real-time search engine for an online community where users can ask e...
In this paper, we introduce a robust novel approach for detecting objects category in cluttered scenes by generating boosted contextual descriptors of landmarks. In particular, ou...
Nearest neighbour (NN) searches and k nearest neighbour (k-NN) searches are widely used in pattern recognition and image retrieval. An NN (k-NN) search finds the closest object (...
In this paper we present a methodical evaluation of the performance of a new and two traditional approaches to automatic target recognition (ATR) based on silhouette representatio...