Dimension Reduction and Classification Methods for Object Recognition in Vision - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2004

Dimension Reduction and Classification Methods for Object Recognition in Vision

Abstract

This paper addresses the challenging task of recognizing and locating objects in natural images. In computer vision, many successful approaches to object recognition use local image descriptors. Such descriptors do not require segmentation, in addition they are robust to partial occlusion and invariant to image transformations (particularly scale changes). Among the existing descriptors, a recent comparison [4] showed that the SIFT descriptor [2] was particularly robust. However, the SIFT descriptor is high-dimensional (typically 128-dimensional) and this penalizes classification. In this paper, we propose to use statistical dimension reduction techniques to obtain a more discriminant representation of data, in order to increase recognition results. We will first describe the two stages of the recognition process (See Fig. 1), learning and recognition, then we will present experimental results obtained on motorbikes images.
Fichier principal
Vignette du fichier
BGS04.pdf (166.16 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00548547 , version 1 (20-12-2010)

Identifiers

  • HAL Id : inria-00548547 , version 1

Cite

Charles Bouveyron, Stéphane Girard, Cordelia Schmid. Dimension Reduction and Classification Methods for Object Recognition in Vision. 5th French-Danish Workshop on Spatial Statistics and Image Analysis in Biology, May 2004, Saint-Pierre de Chartreuse, France. pp.109--113. ⟨inria-00548547⟩
158 View
185 Download

Share

Gmail Facebook Twitter LinkedIn More