Improving Image Similarity With Vectors of Locally Aggregated Tensors

David Picard 1 Philippe-Henri Gosselin 2
2 MIDI
ETIS - Equipes Traitement de l'Information et Systèmes
Abstract : Within the Content Based Image Retrieval (CBIR) framework, three main points can be highlighted: visual descriptors extraction, image signatures and their associated similarity measures, and machine learning based relevance functions. While the first and the last points have vastly improved in recent years, this paper addresses the second point. We propose a novel approach to compute vector representations extending state of the art methods in the field. Furthermore, our method can be viewed as a linearization of efficient well known kernel methods. The evaluation shows that our representation significantly improve state of the art results on the difficult VOC2007 database by a fair margin.
Document type :
Conference papers
2011 IEEE International Conference on Image Processing (IEEE ICIP2011), Sep 2011, Brussels, Belgium. pp.669 - 672, 2011, 〈10.1109/ICIP.2011.6116641〉
Liste complète des métadonnées

Cited literature [11 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00591993
Contributor : David Picard <>
Submitted on : Wednesday, August 10, 2011 - 7:00:04 AM
Last modification on : Thursday, May 3, 2018 - 3:18:06 PM
Document(s) archivé(s) le : Monday, November 12, 2012 - 3:16:11 PM

File

vlat_icip2011.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

David Picard, Philippe-Henri Gosselin. Improving Image Similarity With Vectors of Locally Aggregated Tensors. 2011 IEEE International Conference on Image Processing (IEEE ICIP2011), Sep 2011, Brussels, Belgium. pp.669 - 672, 2011, 〈10.1109/ICIP.2011.6116641〉. 〈hal-00591993〉

Share

Metrics

Record views

257

Files downloads

344