Share Email Print

Proceedings Paper

Interactive learning of image visual similarities and semantic categorization
Author(s): Zijun Yang; C.-C. Jay Kuo
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The query by example model has been extensively used to retrieve similar images in content-based image database management. The query is characterized by searching images with feature vectors similar to those of the example based upon either a default of a user-defined similarity metric. However, low level features often encounter a severe performance bottleneck as applied to natural image collections with complicated contents and great perceptual varieties. The feature-based similarity matching approach tends to retrieve many irrelevant images. This is not surprising since images different in semantic meanings but close enough in low level features can be returned as pertinent result. Such a query process lacks user involvement and therefore results in a gap between features and semantics.

Paper Details

Date Published: 11 October 2000
PDF: 12 pages
Proc. SPIE 4210, Internet Multimedia Management Systems, (11 October 2000); doi: 10.1117/12.403821
Show Author Affiliations
Zijun Yang, Univ. of Southern California (United States)
C.-C. Jay Kuo, Univ. of Southern California (United States)

Published in SPIE Proceedings Vol. 4210:
Internet Multimedia Management Systems
John R. Smith; Chinh Le; Sethuraman Panchanathan; C.-C. Jay Kuo, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?