Share Email Print

Journal of Electronic Imaging

Image retrieval using wavelet-based salient points
Author(s): Qi Tian; Nicu Sebe; Michael S. Lew; E. Loupias; Thomas S. Huang
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Content-based image retrieval (CBIR) has become one of the most active research areas in the past few years. Most of the attention from the research has been focused on indexing techniques based on global feature distributions. However, these global distributions have limited discriminating power because they are unable to capture local image information. The use of interest points in content-based image retrieval allow image index to represent local properties of the image. Classic corner detectors can be used for this purpose. However, they have drawbacks when applied to various natural images for image retrieval, because visual features need not be corners and corners may gather in small regions. In this paper, we present a salient point detector. The detector is based on wavelet transform to detect global variations as well as local ones. The wavelet-based salient points are evaluated for image retrieval with a retrieval system using color and texture features. The results show that salient points with Gabor feature perform better than the other point detectors from the literature and the randomly chosen points. Significant improvements are achieved in terms of retrieval accuracy, computational complexity when compared to the global feature approaches.

Paper Details

Date Published: 1 October 2001
PDF: 15 pages
J. Electron. Imag. 10(4) doi: 10.1117/1.1406945
Published in: Journal of Electronic Imaging Volume 10, Issue 4
Show Author Affiliations
Qi Tian, Univ. of Illinois/Urbana-Champaign (United States)
Nicu Sebe, Leiden Institute of Advanced Computer Science (Netherlands)
Michael S. Lew, Leiden Institute of Advanced Computer Science (Netherlands)
E. Loupias, INSA-Lyon (France)
Thomas S. Huang, Univ. of Illinois/Urbana-Champaign (United States)

© SPIE. Terms of Use
Back to Top