Learning visual distance function for object identification from one example - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2006

Learning visual distance function for object identification from one example

Abstract

Comparing images is essential to several computer vision problems, like image retrieval or object identification. The comparison of two images heavily relies on the definition of a good distance function. Standard functions (e.g. the euclidean distance in the original feature space) are too generic and fail to encode the domain specific information. In this paper, we propose to learn a similarity measure specific to a given category (e.g. cars). This distance is learned from a training set of pairs of images labeled “same” or “different”, indicating if the two images represent the same object (e.g. same car model) or not. After learning, this measure is used to predict how similar two images of never seen objects are (see figure 1).
Fichier principal
Vignette du fichier
5.pdf (108.41 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00548582 , version 1 (06-01-2011)

Identifiers

  • HAL Id : inria-00548582 , version 1

Cite

Eric Nowak, Frédéric Jurie. Learning visual distance function for object identification from one example. Learning to Compare Examples (NIPS'06 Workshop), Dec 2006, Whistler, Canada. ⟨inria-00548582⟩
228 View
258 Download

Share

Gmail Facebook X LinkedIn More