Skip to content Home Contact Mobile MyRMIT Library A-Z
RMIT UniversityResearch Repository
 

Combining image and structured text retrieval

Awg Iskandar, D, Pehcevski, J, Thom, J and Tahaghoghi, S 2006, 'Combining image and structured text retrieval', in N. Fuhr, M. Lalmas, S. Malik & G. Kazai (ed.) Advances in XML information retr ieval: 4th international workshop of the Initiative for the evaluation if XML retrieval, INEX 2005 (Revised selected papers), Schloss Dagstuhl, Germany, 28 June 2006.

Document type: Conference Paper
Collection: Conference Papers

Title Combining image and structured text retrieval
Author(s) Awg Iskandar, D
Pehcevski, J
Thom, J
Tahaghoghi, S
Year 2006
Conference name International Workshop of the Initiative for the Evaluation of XML Retrieval
Conference location Schloss Dagstuhl, Germany
Conference dates 28 June 2006
Proceedings title Advances in XML information retr ieval: 4th international workshop of the Initiative for the evaluation if XML retrieval, INEX 2005 (Revised selected papers)
Editor(s) N. Fuhr, M. Lalmas, S. Malik & G. Kazai
Publisher Springer
Place of publication Heidelgberg, Germany
Abstract Two common approaches in retrieving images from a collection are retrieval by text keywords and retrieval by visual content. However, it is widely recognised that it is impossible for keywords alone to fully describe visual content. This paper reports on the participation of the RMIT University group in the INEX 2005 multimedia track, where we investigated our approach of combining evidence from a content-oriented XML retrieval system and a content-based image retrieval system using a linear combination of evidence. Our approach yielded the best overall result for the INEX 2005 Multimedia track using the standard evaluation measures. We have extended our work by varying the parameter for the linear combination of evidence, and we have also examined the performance of runs submitted by participants by using the newly proposed HiXEval evaluation metric. We show that using CBIR in conjunction with text search leads to better retrieval performance.
Subjects Business Information Management (incl. Records, Knowledge and Information Management, and Intelligence)
Copyright notice © Springer-Verlag Berlin Heidelberg 2006
 
Versions
Version Filter Type
Access Statistics: 71 Abstract Views  -  Detailed Statistics
Created: Wed, 08 Apr 2009, 09:42:32 EST by Catalyst Administrator