Share Email Print

Proceedings Paper

Document description: What works for images should also work for text?
Author(s): Nicolas Hervé; Nozha Boujemaa; Michael E. Houle
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The success of the bag-of-words approach for text has inspired the recent use of analogous strategies for global representation of images with local visual features. Many applications have been proposed for object detection, image annotation, queries-by-example, relevance feedback, automatic annotation, and clustering. In this paper, we investigate the validity of the bag-of-words analogy for image representation and, more specifically, local pattern selection for feature generation. We propose a generalized document representation framework and apply it to the evaluation of two pattern selection strategies for images: dense sampling and point-of-interest detection. We present empirical results that support our contention that text-based experimentation can provide useful insights into the effectiveness of image representations based on the bag-of-visual-words technique.

Paper Details

Date Published: 19 January 2009
PDF: 12 pages
Proc. SPIE 7255, Multimedia Content Access: Algorithms and Systems III, 72550B (19 January 2009); doi: 10.1117/12.810038
Show Author Affiliations
Nicolas Hervé, INRIA Paris-Rocquencourt (France)
Nozha Boujemaa, INRIA Paris-Rocquencourt (France)
Michael E. Houle, National Institute of Informatics (Japan)

Published in SPIE Proceedings Vol. 7255:
Multimedia Content Access: Algorithms and Systems III
Raimondo Schettini; Ramesh C. Jain; Simone Santini, Editor(s)

© SPIE. Terms of Use
Back to Top