Reclassement d'images par le contenu - Archive ouverte HAL Access content directly
Conference Papers Year : 2012

Reclassement d'images par le contenu

Abstract

This article presents a method for re-ranking images retrieved by a web scale and state of the art search engine using key words for entering queries. This method uses the visual content of the images and it is based on the idea that the relevant images should be similar to each other while the non relevant images should be different from each other and from relevant images. This idea has been implemented by ranking the images according to their average distances to their nearest neighbors. The re-ranking performed with this method only does not perform better than the original ranking but, when combined to it, it yields a relative performance gain of about 3\% in term of mean average precision and of about 7\% if the complement to 1 of the average precision is considered. This gain is statistically significant and it is brought to a system which is already very effective for exploiting all the textual information available with the images.
Fichier principal
Vignette du fichier
Quenot-Thollard-CORIA2012.pdf (141.3 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00770631 , version 1 (07-01-2013)

Identifiers

  • HAL Id : hal-00770631 , version 1

Cite

Georges Quénot, Franck Thollard. Reclassement d'images par le contenu. CORIA 2012 - COnférence en Recherche d'Information et Applications, Mar 2012, Bordeaux, France. pp.203-214. ⟨hal-00770631⟩
104 View
58 Download

Share

Gmail Facebook Twitter LinkedIn More