Skip to Main content Skip to Navigation
Reports

The Image Shape Spectrum for Image Retrieval

Chahab Nastar 1
1 SYNTIM - Image Analysis and Synthesis
Inria Paris-Rocquencourt
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 occlusi on. We present several retrieval examples in large benchmark databases, inclu ding face databases and a database of 3D objects, for which the method reaches an ideal recognition rate.
Document type :
Reports
Complete list of metadata

https://hal.inria.fr/inria-00073483
Contributor : Rapport de Recherche Inria <>
Submitted on : Wednesday, May 24, 2006 - 12:58:29 PM
Last modification on : Friday, May 25, 2018 - 12:02:05 PM
Long-term archiving on: : Sunday, April 4, 2010 - 11:47:54 PM

Identifiers

  • HAL Id : inria-00073483, version 1

Collections

Citation

Chahab Nastar. The Image Shape Spectrum for Image Retrieval. [Research Report] RR-3206, INRIA. 1997. ⟨inria-00073483⟩

Share

Metrics

Record views

180

Files downloads

235