Presentado al 11th Iberoamerican Congress on Pattern Recognition (CIARP/2006) celebrado en Cancún (México). ; We present a framework for object recognition based on simple scale and orientation invariant local features that when combined with a hierarchical multiclass boosting mechanism produce robust classifiers for a limited number of object classes in cluttered backgrounds. The system extracts the most relevant features from a set of training samples and builds a hierarchical structure of them. By focusing on those features common to all trained objects, and also searching for those features particular to a reduced number of classes, and eventually, to each object class. To allow for efficient rotation invariance, we propose the use of non-Gaussian steerable filters, together with an Orientation Integral Image for a speedy computation of local orientation. ; This work was supported by projects: 'Integration of robust perception, learning, and navigation systems in mobile robotics' (J-0929), 'Perception, action & cognition through learning of object-action complexes.' (4915). ; Financial support to M. Villamizar and A. Sanfeliu comes from the EURON Network Robot Systems Research Atelier NoE-507728, and the Spanish Ministry of Education and Science project NAVROB DPI 2004-05414. J. Andrade-Cetto is a Juan de la Cierva Postdoctoral Fellow of the Spanish Ministry of Education and Science under project TIC2003-09291, and is also funded in part by the EU PACO-PLUS project FP6-2004-IST-4-27657. ; Peer Reviewed
Orientation invariant features for multiclass object recognition
2006-01-01
Conference paper
Electronic Resource
English
DDC: | 629 |
Sharing Features: Efficient Boosting Procedures for Multiclass Object Detection
British Library Conference Proceedings | 2004
|Scale-Invariant Shape Features for Recognition of Object Categories
British Library Conference Proceedings | 2004
|