TY - CHAP A1 - Reinhold, M. A1 - Deinzer, Frank A1 - Denzler, Joachim A1 - Paulus, D. A1 - Pösl, Joseph ED - Girod, B. ED - Niemann, Heinrich ED - Seidel, H.-P. T1 - Active Appearance-Based Object Recognition Using Viewpoint Selection T2 - Proceedings of the 2000 Conference on Vision Modeling and Visualization N2 - In this paper we address the classification of 3–D objects that look similar from sev-eral sights and can only be distinguished from some certain viewpoints. For this purpose we combine a statistical appearance-based object recognition approach with an active viewpoint selection mechanism. For appearance-based object recognition lo-cal features are derived from wavelet multires-olution analysis. The recognition process is performed hierarchically in a statistical frame-work by a maximum likelihood estimation. Based on this result the active viewpoint se-lection mechanism chooses one further view that allows a reliable classification. Hereby the viewpoint selection mechanism can be trained unsupervised and represents the space of possible viewpoints continuously. Experimental results show that our approach is well suited for a reliable classifica-tion of similar looking objects only by one fur-ther view. Y1 - 2000 UR - http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2000/Reinhold00-AAO.pdf SP - 105 EP - 112 ER -