The Community for Technology Leaders
Web Intelligence, IEEE / WIC / ACM International Conference on (2005)
Compi?gne University of Technology, France
Sept. 19, 2005 to Sept. 22, 2005
ISBN: 0-7695-2415-X
pp: 581-585
Epimenides Voutsakis , Technical University of Crete
Euripides G.M. Petrakis , Technical University of Crete
Evangelos Milios , Dalhousie University
ABSTRACT
Image retrieval on the Web requires that important (authoritative) images satisfying the query selection criteria are assigned higher ranking over other relevant images. PicASHOW [5] achieves this goal using link information alone. This work proposes WPicASHOW (Weighted PicASHOW) a weighted scheme for co-citation analysis that incorporates within the link analysis method of PicASHOW the text and image content of the queries and of the Web pages. WPicASHOW is implemented and integrated into a fully automated Web retrieval system for logo and trademark images.
INDEX TERMS
null
CITATION

E. Milios, E. G. Petrakis and E. Voutsakis, "Weighted Link Analysis for Logo and Trademark Image Retrieval on the Web," Proceedings. The 2005 IEEE/WIC/ACM International Conference on Web Intelligence(WI), Compiegne, France, 2005, pp. 581-585.
doi:10.1109/WI.2005.162
90 ms
(Ver 3.3 (11022016))