Properties of series feature aggregation schemes Zhang, Jun and Ye, Lei 2008, Properties of series feature aggregation schemes, in ICITA 2008 : Fifth international conference on information technology &​ applications, ICITA, Bathurst, N.S.W., pp. 361-364. Attached Files Name Description MIMEType Size Downloads zhang-propertiesof-2008.pdf Published version application/pdf 443.54KB 190 Title Properties of series feature aggregation schemes Author(s) Zhang, Jun orcid.org/0000-0002-2189-7801 Ye, Lei Conference name International Conference on Information Technology and Applications (5th : 2008 : Cairns, Queensland.) Conference location Cairns, Qld. Conference dates 23-26 June 2008 Title of proceedings ICITA 2008 : Fifth international conference on information technology &​ applications Editor(s) Tien, David Kavakli, Manolya Publication date 2008 Conference series International Conference on Information Technology and Applications Start page 361 End page 364 Total pages 4 Publisher ICITA Place of publication Bathurst, N.S.W. Summary Feature aggregation is a critical technique in content-based image retrieval (CBIR) that combines multiple feature distances to obtain image dissimilarity. Conventional parallel feature aggregation (PFA) schemes failed to effectively filter out the irrelevant images using individual visual features before ranking images in collection. Series feature aggregation (SFA) is a new scheme that aims to address this problem. This paper investigates three important properties of SFA that are significant for design of systems. They reveal the irrelevance of feature order and the convertibility of SFA and PFA as well as the superior performance of SFA. Furthermore, based on Gaussian kernel density estimator, the authors propose a new method to estimate the visual threshold, which is the key parameter of SFA. Experiments, conducted with IAPR TC-12 benchmark image collection (ImageCLEF2006) that contains over 20,000 photographic images and defined queries, have shown that SFA can outperform conventional PFA schemes. ISBN 9780980326727 0980326729 Language eng Field of Research 080704 Information Retrieval and Web Search 080109 Pattern Recognition and Data Mining Socio Economic Objective 890301 Electronic Information Storage and Retrieval Services HERDC Research category E1.1 Full written paper - refereed Copyright notice ©2008, ICITA Free to Read? Yes Persistent URL http://hdl.handle.net/10536/DRO/DU:30039520 Document type: Conference Paper Collections: Faculty of Science, Engineering and Built Environment School of Information Technology Open Access Collection Related Links Link Description Connect to conference webpage Go to link with your DU access privileges     Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved. Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au. Versions Version Filter Type Wed, 26 Oct 2011, 12:46:58 EST Fri, 25 Nov 2011, 13:19:46 EST Fri, 25 Nov 2011, 13:21:59 EST Fri, 25 Nov 2011, 13:25:29 EST Wed, 08 Feb 2012, 16:01:09 EST Fri, 29 Jun 2012, 11:03:43 EST Thu, 26 Jun 2014, 10:18:32 EST Mon, 14 Jul 2014, 09:25:03 EST Mon, 14 Jul 2014, 09:26:27 EST Wed, 17 Sep 2014, 19:49:17 EST Fri, 19 Sep 2014, 14:29:03 EST Fri, 03 Oct 2014, 11:21:44 EST Fri, 03 Oct 2014, 11:27:42 EST Thu, 13 Nov 2014, 09:58:47 EST Sat, 17 Jun 2017, 03:08:29 EST Tue, 05 Dec 2017, 10:53:43 EST Fri, 07 Sep 2018, 15:33:24 EST Filtered Full Citation counts:   Cited 0 times in TR Web of Science Cited 1 times in Scopus Search Google Scholar Access Statistics: 408 Abstract Views, 190 File Downloads  -  Detailed Statistics Created: Wed, 26 Oct 2011, 12:46:57 EST