The University of Surrey visual concept detection system at imageCLEF@ICPR: working notes

Tahir, Muhammad, Yan, Fei, Barnard, Mark, Awais, Muhammad, Mikolajczyk, Krystian and Kittler, Josef (2010) The University of Surrey visual concept detection system at imageCLEF@ICPR: working notes. In: Proceedings of the 20th International Conference on Pattern Recognition (ICPR 2010). IEEE, Piscataway, NJ, pp. 850-853. ISBN 978-1424475421

Full text not available from this repository. (Request a copy)

Abstract

Visual concept detection is one of the most important tasks in image and video indexing. This paper describes our system in the ImageCLEF@ICPR Visual Concept Detection Task which ranked first for large-scale visual concept detection tasks in terms of Equal Error Rate (EER) and Area under Curve (AUC) and ranked third in terms of hierarchical measure. The presented approach involves state-of-the-art local descriptor computation, vector quantisation via clustering, structured scene or object representation via localised histograms of vector codes, similarity measure for kernel construction and classifier learning. The main novelty is the classifier-level and kernel-level fusion using Kernel Discriminant Analysis with RBF/Power Chi-Squared kernels obtained from various image descriptors. For 32 out of 53 individual concepts, we obtain the best performance of all 12 submissions to this task.

Item Type:	Book Section
Additional Information:	Proceedings of the 20th International conference on Pattern Recognition held on 23-26 August 2010, in Istanbul, Turkey.
Subjects:	G400 Computer Science
Department:	Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User:	Sarah Howells
Date Deposited:	17 Sep 2012 15:00
Last Modified:	12 Oct 2019 22:29
URI:	http://nrl.northumbria.ac.uk/id/eprint/8937

Downloads