Capturing shape and text for retrieval

Authors:
Oliver Lorenz;Gladys Monagan
Affiliations:
Institut für Informationssysteme, ETH, Zürich, Switzerland;Institut für Informationssysteme, ETH, Zürich, Switzerland
Venue:
MIRO'95 Proceedings of the Final conference on Multimedia Information Retrieval
Year:
1995

Citing 5
Cited 0

A two-step string-matching procedure

Pattern Recognition
Visual Database Systems: Proceedings of the IFIP TC2 Wg2.6 Working Conference, Tokyo, Japan, 3-7 April, 1989

Visual Database Systems: Proceedings of the IFIP TC2 Wg2.6 Working Conference, Tokyo, Japan, 3-7 April, 1989
Information Retrieval

Information Retrieval
Computer Vision

Computer Vision
Proceedings of the IFIP TC2/WG 2.6 Second Working Conference on Visual Database Systems II

Proceedings of the IFIP TC2/WG 2.6 Second Working Conference on Visual Database Systems II

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a system for content-based retrieval of line drawings. Line drawings are schematic diagrams consisting of two kinds of information, text and graphics. The textual part is indexed from the results of word recognition. The indexing for the graphic content uses no a-priori knowledge about the content of a drawing and depends only on features derived from the shape of graphic structures. The indexing scheme is used in a vector based information retrieval system. Results and problems in evaluating such a system are discussed.