The Image Shape Spectrum for Image Retrieval

Abstract

: We present an appearance-based technique for image characterization and retrieval. Our method is translation/rotation and scale- invariant and encodes the significant data in the image without using any segmentation. It is also very well suited to small viewpoint changes and is robust to noise and occlusion. We present several retrieval examples in large benchmark databases, including face databases and a database of 3D objects, for which the method reaches an ideal recognition rate. Key-words: image databases, image indexing, image retrieval, appearance, invariance. (R'esum'e : tsvp) [e-mail] Unite de recherche INRIA Rocquencourt Domaine de Voluceau, Rocquencourt, BP 105, 78153 LE CHESNAY Cedex (France) Telephone : [phone] -- Telecopie : (33) 01 39 63 53 Le spectre de forme pour l'indexation d'images R'esum'e : Nous pr'esentons une technique fond'ee sur l'apparence pour caract 'eriser et rechercher des images dans une base. Notre m'ethode est invarian...