14 February 2008 Human-centered content-based image retrieval
Author Affiliations +
Abstract
A breakthrough is needed in order to achieve a substantial progress in the field of Content-Based Image Retrieval (CBIR). This breakthrough can be enforced by: 1) optimizing user-system interaction, 2) combining the wealth of techniques from text-based Information Retrieval with CBIR techniques, 3) exploiting human cognitive characteristics, especially human color processing, and 4) conducting benchmarks with users for evaluating new CBIR techniques. In this paper, these guidelines are illustrated by findings from our research conducted the last five years, which have lead to the development of the online Multimedia for Art ReTrieval (M4ART) system: http://www.m4art.org. The M4ART system follows the guidelines on all four issues and is assessed on benchmarks using 5730 queries on a database of 30,000 images. Therefore, M4ART can be considered as a first step into a new era of CBIR.
© (2008) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Egon L. van den Broek, Egon L. van den Broek, Thijs Kok, Thijs Kok, Theo E. Schouten, Theo E. Schouten, Louis G. Vuurpijl, Louis G. Vuurpijl, } "Human-centered content-based image retrieval", Proc. SPIE 6806, Human Vision and Electronic Imaging XIII, 68061L (14 February 2008); doi: 10.1117/12.767190; https://doi.org/10.1117/12.767190
PROCEEDINGS
12 PAGES


SHARE
RELATED CONTENT

Object and image retrieval over the Internet
Proceedings of SPIE (December 26 2000)
Multimedia for Art ReTrieval (M4ART)
Proceedings of SPIE (January 16 2006)
Multimedia search engine with relevance feedback
Proceedings of SPIE (December 19 2001)
Content-based image retrieval
Proceedings of SPIE (February 26 2010)

Back to Top