caa a22 4500 467914575 CHVBK 20180406152858.0 cr unu---uuuuu 170328e20060401xx s 000 0 eng 10.1007/s11263-005-3964-7 doi (NATIONALLICENCE)springer-10.1007/s11263-005-3964-7 Simultaneous Object Recognition and Segmentation from Single or Multiple Model Views [Elektronische Daten] [Vittorio Ferrari, Tinne Tuytelaars, Luc Van Gool] We present a novel Object Recognition approach based on affine invariant regions. It actively counters the problems related to the limited repeatability of the region detectors, and the difficulty of matching, in the presence of large amounts of background clutter and particularly challenging viewing conditions. After producing an initial set of matches, the method gradually explores the surrounding image areas, recursively constructing more and more matching regions, increasingly farther from the initial ones. This process covers the object with matches, and simultaneously separates the correct matches from the wrong ones. Hence, recognition and segmentation are achieved at the same time. The approach includes a mechanism for capturing the relationships between multiple model views and exploiting these for integrating the contributions of the views at recognition time. This is based on an efficient algorithm for partitioning a set of region matches into groups lying on smooth surfaces. Integration is achieved by measuring the consistency of configurations of groups arising from different model views. Experimental results demonstrate the stronger power of the approach in dealing with extensive clutter, dominant occlusion, and large scale and viewpoint changes. Non-rigid deformations are explicitly taken into account, and the approximative contours of the object are produced. All presented techniques can extend any view-point invariant feature extractor. Springer Science + Business Media, Inc., 2006 Ferrari Vittorio Computer Vision Group (BIWI), ETH Zuerich, Switzerland aut Tuytelaars Tinne ESAT-PSI, University of Leuven, Belgium aut Van Gool Luc Computer Vision Group (BIWI), ETH Zuerich, Switzerland aut International Journal of Computer Vision Kluwer Academic Publishers 67/2(2006-04-01), 159-188 0920-5691 67:2<159 2006 67 11263 https://doi.org/10.1007/s11263-005-3964-7 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s11263-005-3964-7 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Ferrari Vittorio Computer Vision Group (BIWI), ETH Zuerich, Switzerland aut NATIONALLICENCE 700 1- Tuytelaars Tinne ESAT-PSI, University of Leuven, Belgium aut NATIONALLICENCE 700 1- Van Gool Luc Computer Vision Group (BIWI), ETH Zuerich, Switzerland aut NATIONALLICENCE 773 0- International Journal of Computer Vision Kluwer Academic Publishers 67/2(2006-04-01), 159-188 0920-5691 67:2<159 2006 67 11263 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer