ERIC7: an experimental tool for Content-Based Image encoding and Retrieval under the MPEG-7 standard

Authors:
L. Gagnon;S. Foucher;V. Gouaillier
Affiliations:
Computer Research Institute of Montreal, Montreal (Quebec), Canada;Computer Research Institute of Montreal, Montreal (Quebec), Canada;Computer Research Institute of Montreal, Montreal (Quebec), Canada
Venue:
WISICT '04 Proceedings of the winter international synposium on Information and communication technologies
Year:
2004

Citing 2
Cited 1

Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

International Journal of Computer Vision
Introduction to MPEG-7: Multimedia Content Description Interface

Introduction to MPEG-7: Multimedia Content Description Interface

Use of the MPEG-7 standard as metadata framework for a location scouting system: an evaluation study

DCMI '05 Proceedings of the 2005 international conference on Dublin Core and metadata applications: vocabularies in practice

Quantified Score

Hi-index	0.00

Visualization

Abstract

ERIC7 is a software test-bed that implements Content-Based Image Retrieval (CBIR) compatible with the MPEG-7 multimedia standard. In its current version, the system allows automatic MPEG-7/XML encoding of up to 15 color, texture and shape descriptors with two query modes: search from example images and database clustering. In addition, the system allows to navigate graphically among the various descriptors in the XML files in order to easily track encoding results and system performance. The system is being tested on various types of images, including images of man-made and natural objects, as well as "scape-type" scenes. The system architecture is expandable to video indexing and retrieval.