Speeded-up, relaxed spatial matching

Tolias, G; Avrithis, Y

dc.contributor.author	Tolias, G	en
dc.contributor.author	Avrithis, Y	en
dc.date.accessioned	2014-03-01T02:53:28Z
dc.date.available	2014-03-01T02:53:28Z
dc.date.issued	2011	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/36348
dc.subject.other	Descriptors	en
dc.subject.other	Feature correspondence	en
dc.subject.other	Geometric invariance	en
dc.subject.other	Matching process	en
dc.subject.other	Multiple matching	en
dc.subject.other	Non-rigid objects	en
dc.subject.other	One-to-one mappings	en
dc.subject.other	Re-ranking	en
dc.subject.other	Rigidity constraint	en
dc.subject.other	Space requirements	en
dc.subject.other	Spatial matching	en
dc.subject.other	State of the art	en
dc.subject.other	Image retrieval	en
dc.subject.other	Search engines	en
dc.subject.other	Image processing	en
dc.title	Speeded-up, relaxed spatial matching	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICCV.2011.6126427	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICCV.2011.6126427	en
heal.identifier.secondary	6126427	en
heal.publicationDate	2011	en
heal.abstract	A wide range of properties and assumptions determine the most appropriate spatial matching model for an application, e.g. recognition, detection, registration, or large scale image retrieval. Most notably, these include discriminative power, geometric invariance, rigidity constraints, mapping constraints, assumptions made on the underlying features or descriptors and, of course, computational complexity. Having image retrieval in mind, we present a very simple model inspired by Hough voting in the transformation space, where votes arise from single feature correspondences. A relaxed matching process allows for multiple matching surfaces or non-rigid objects under one-to-one mapping, yet is linear in the number of correspondences. We apply it to geometry re-ranking in a search engine, yielding superior performance with the same space requirements but a dramatic speed-up compared to the state of the art. © 2011 IEEE.	en
heal.journalName	Proceedings of the IEEE International Conference on Computer Vision	en
dc.identifier.doi	10.1109/ICCV.2011.6126427	en
dc.identifier.spage	1653	en
dc.identifier.epage	1660	en