Share Email Print

Proceedings Paper

An approach for combining multiple descriptors for image classification
Author(s): Duc Toan Tran; Bart Jansen; Rudi Deklerck; Olivier Debeir
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Recently, efficient image descriptors have shown promise for image classification tasks. Moreover, methods based on the combination of multiple image features provide better performance compared to methods based on a single feature. This work presents a simple and efficient approach for combining multiple image descriptors. We first employ a Naive-Bayes Nearest-Neighbor scheme to evaluate four widely used descriptors. For all features, “Image-to-Class” distances are directly computed without descriptor quantization. Since distances measured by different metrics can be of different nature and they may not be on the same numerical scale, a normalization step is essential to transform these distances into a common domain prior to combining them. Our experiments conducted on a challenging database indicate that z-score normalization followed by a simple sum of distances fusion technique can significantly improve the performance compared to applications in which individual features are used. It was also observed that our experimental results on the Caltech 101 dataset outperform other previous results.

Paper Details

Date Published: 14 February 2015
PDF: 6 pages
Proc. SPIE 9445, Seventh International Conference on Machine Vision (ICMV 2014), 94450Y (14 February 2015); doi: 10.1117/12.2181017
Show Author Affiliations
Duc Toan Tran, Vrije Univ. Brussel (Belgium)
Univ. Libre de Bruxelles (Belgium)
Bart Jansen, Vrije Univ. Brussel (Belgium)
Interdisciplinary Institute for Broadband Technology (Belgium)
Rudi Deklerck, Vrije Univ. Brussel (Belgium)
Olivier Debeir, Univ. Libre de Bruxelles (Belgium)

Published in SPIE Proceedings Vol. 9445:
Seventh International Conference on Machine Vision (ICMV 2014)
Antanas Verikas; Branislav Vuksanovic; Petia Radeva; Jianhong Zhou, Editor(s)

© SPIE. Terms of Use
Back to Top