Translator Disclaimer
Paper
19 January 2009 Document description: what works for images should also work for text?
Author Affiliations +
Proceedings Volume 7255, Multimedia Content Access: Algorithms and Systems III; 72550B (2009) https://doi.org/10.1117/12.810038
Event: IS&T/SPIE Electronic Imaging, 2009, San Jose, California, United States
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.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Nicolas Hervé, Nozha Boujemaa, and Michael E. Houle "Document description: what works for images should also work for text?", Proc. SPIE 7255, Multimedia Content Access: Algorithms and Systems III, 72550B (19 January 2009); https://doi.org/10.1117/12.810038
PROCEEDINGS
12 PAGES


SHARE
Advertisement
Advertisement
Back to Top