Show simple item record

How to Use SIFT Vectors to Analyze an Image with Database Templates

dc.contributor.authorAuclair, Adrien
dc.contributor.authorCohen, Laurent D.
HAL ID: 738939
dc.contributor.authorVincent, Nicole
dc.date.accessioned2014-03-20T09:42:56Z
dc.date.available2014-03-20T09:42:56Z
dc.date.issued2008
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/12925
dc.language.isoenen
dc.subjectdatabasesen
dc.subjectSIFT vectorsen
dc.subject.ddc518en
dc.titleHow to Use SIFT Vectors to Analyze an Image with Database Templatesen
dc.typeCommunication / Conférence
dc.description.abstractenDuring last years, local image descriptors have received much attention because of their efficiency for several computer vision tasks such as image retrieval, image comparison, features matching for 3D reconstruction... Recent surveys have shown that Scale Invariant Features Transform (SIFT) vectors are the most efficient for several criteria. In this article, we use these descriptors to analyze how a large input image can be decomposed by small template images contained in a database. Affine transformations from database images onto the input image are found as described in [16]. The large image is thus covered by small patches like a jigsaw puzzle. We introduce a filtering step to ensure that found images do not overlap themselves when warped on the input image. A typical new application is to retrieve which products are proposed on a supermarket shelf. This is achieved using only a large picture of the shelf and a database of all products available in the supermarket. Because the database can be large and the analysis should ideally be done in a few seconds, we compare the performances of two state of the art algorithms to search SIFT correspondences: Best-Bin-First algorithm on Kd-Tree and Locality Sensitive Hashing. We also introduce a modification in the LSH algorithm to adapt it to SIFT vectors.en
dc.identifier.citationpages224-236en
dc.relation.ispartofseriestitleLecture Notes in Computer Scienceen
dc.relation.ispartofseriesnumber4918en
dc.relation.ispartoftitleAdaptive Multimedia Retrieval: Retrieval, User, and Semantics 5th International Workshop, AMR 2007, Paris, France, July 5-6, 2007 Revised Selected Papersen
dc.relation.ispartofeditorBoujemaa, Nozha
dc.relation.ispartofeditorDetyniecki, Marcin
dc.relation.ispartofeditorNürnberger, Andreas
dc.relation.ispartofpublnameSpringeren
dc.relation.ispartofpublcityBerlinen
dc.relation.ispartofdate2008
dc.relation.ispartofpages265en
dc.relation.ispartofurlhttp://dx.doi.org/10.1007/978-3-540-79860-6en
dc.subject.ddclabelModèles mathématiques. Algorithmesen
dc.relation.ispartofisbn978-3-540-79859-0en
dc.relation.conftitle5th International Workshop on Adaptive Multimedia Retrieval: Retrieval, User, and Semantics, AMR 2007en
dc.relation.confdate2008-07
dc.relation.confcityParisen
dc.relation.confcountryFranceen
dc.relation.forthcomingnonen
dc.identifier.doihttp://dx.doi.org/10.1007/978-3-540-79860-6_18en


Files in this item

Thumbnail
Name:
auclairAMR07.pdf
Size:
1.723Mb
Format:
PDF
View/Open

This item appears in the following Collection(s)

Show simple item record