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

Muhammad Tahir, Fei Yan, Mark Barnard, Muhammad Awais, Krystian Mikolajczyk, Josef Kittler

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

5 Citations (Scopus)

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.
Original languageEnglish
Title of host publicationProceedings of the 20th International Conference on Pattern Recognition (ICPR 2010)
Place of PublicationPiscataway, NJ
PublisherIEEE
Pages850-853
ISBN (Print)978-1424475421
DOIs
Publication statusPublished - 2010
EventThe University of Surrey Visual Concept Detection System at ImageCLEF@ICPR: Working Notes - Guildford Surrey
Duration: 1 Jan 2010 → …

Conference

ConferenceThe University of Surrey Visual Concept Detection System at ImageCLEF@ICPR: Working Notes
Period1/01/10 → …

Fingerprint Dive into the research topics of 'The University of Surrey visual concept detection system at imageCLEF@ICPR: working notes'. Together they form a unique fingerprint.

Cite this