Authors: | Ntalianis, Klimis Doulamis, Anastasios Papadakis, Nikos Stamoulis, George |
Publisher: | IEEE |
Issue Date: | 1-Jun-2009 |
Conference: | 16th International Conference on Systems, Signals and Image Processing (IWSSIP 2009), 18-20 June 2009, Chalkida, Greece |
Book: | 16th International Conference on Systems, Signals and Image Processing (IWSSIP 2009) |
Keywords: | Automatic wrapper, Multi-agent web data extraction, Multi-resolution visualization, Multimedia retrieval, Web mining |
Abstract: | Web-based image search engines and CBIR techniques are blind to the actual content. As a result querying for a specific object is often cluttered with irrelevant data, leading to low precision. Furthermore recall rates are also very low since retrieval procedures are usually based either on context (surrounding text) and file captions or on low-level visual features. In this paper an automatic multi-agent image retrieval system is proposed. Our novel system exploits the format of multimedia sharing web sites to discover the underlying structure in order to finally infer and extract multimedia files and corresponding associated keywords from the web pages. The system first identifies the section of the web page that contains the multimedia file to be extracted and then extracts it by using clustering techniques and other tools of statistical origin. Experimental results on real-world image sharing web sites are presented and discussed in this paper, indicating the promising performance of the proposed system. |
ISBN: | 978-1-4244-4530-1 |
DOI: | 10.1109/IWSSIP.2009.5367695 |
URI: | https://uniwacris.uniwa.gr/handle/3000/2830 |
Type: | Conference Paper |
Department: | Department of Business Administration |
School: | School of Administrative, Economics and Social Sciences |
Affiliation: | University of West Attica (UNIWA) |
Appears in Collections: | Book Chapter / Κεφάλαιο Βιβλίου |
CORE Recommender
SCOPUSTM
Citations
2
checked on Nov 16, 2024
Page view(s)
7
checked on Nov 21, 2024
Google ScholarTM
Check
Altmetric
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.