Optimal Geometric Matching for Patch-Based Object Detection
Keysers, Daniel (German Research Center for Artificial Intelligence (Kaiserslautern, Alemanya))
Deselaers, Thomas (Human Language Technology and Pattern Recognition Group (Aachen, Alemanya))
Breuel, Thomas M. (German Research Center for Artificial Intelligence (Kaiserslautern, Alemanya))

Date:	2007
Abstract:	We present an efficient method to determine the optimal matching of two patch-based image object representations under rotation, scaling, and translation (RST). This use of patches is equivalent to a fullyconnected part-based model, for which the presented approach offers an efficient procedure to determine the best fit. While other approaches that use fully connected models have a high complexity in the number of parts used, we achieve linear complexity in that variable, because we only allow RST-matchings. The presented approach is used for object recognition in images: by matching images that contain certain objects to a test image, we can detect whether the test image contains an object of that class or not. We evaluate this approach on the Caltech data and obtain very competitive results.
Rights:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades.
Language:	Anglès
Document:	Article ; recerca ; Versió publicada
Subject:	Object recognition ; Registration and matching ; Reconeixement objecte ; Registre i rastreig ; Reconocimiento objeto ; Registro y rastreo
Published in:	ELCVIA : Electronic Letters on Computer Vision and Image Analysis, V. 6 n. 1 (2007) , p. 44-54, ISSN 1577-5097

Adreça original: https://elcvia.cvc.uab.es/article/view/v6-n1-keysers-deselaers-breuel
Adreça alternativa: https://raco.cat/index.php/ELCVIA/article/view/85558
DOI: 10.5565/rev/elcvia.136

11 p, 731.8 KB

The record appears in these collections:
Articles > Published articles > ELCVIA
Articles > Research articles