inria-00614523, version 1
Bag-of-colors for improved image search
Christian Wengert
a, 1Matthijs Douze
b, 2, 3Hervé Jégou
4
ACM Multimedia (2011)
Abstract: This paper investigates the use of color information when used within a state-of-the-art large scale image search system. We introduce a simple yet effective and efficient color signature generation procedure. It is used either to produce global or local descriptors. As a global descriptor, it outperforms several state-of-the-art color description methods, in particular the bag-of-words method based on color SIFT. As a local descriptor, our signature is used jointly with SIFT descriptors (no color) to provide complementary information. This significantly improves the recognition rate, outperforming the state of the art on two image search benchmarks. We will provide an open source package of our signature.
- a – Kooaba
- b – INRIA
- 1: Kooaba
- Kooaba research team
- 2: LEAR (INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann)
- CNRS : FR71 – CNRS : UMR5527 – INRIA – Laboratoire Jean Kuntzmann – Université Joseph Fourier - Grenoble I – Institut National Polytechnique de Grenoble (INPG)
- 3: Service Expérimentation et Développement (SED)
- INRIA
- 4: TEXMEX (INRIA - IRISA)
- CNRS : UMR6074 – INRIA – INSA Rennes – Université de Rennes 1
- Collaboration : KOOABA
- Domain : Computer Science/Computer Vision and Pattern Recognition
- inria-00614523, version 1
- http://hal.inria.fr/inria-00614523
- oai:hal.inria.fr:inria-00614523
- From: Hervé Jégou
- Submitted on: Friday, 12 August 2011 10:13:29
- Updated on: Friday, 12 August 2011 10:23:11






Associated documents
Export