APEX: an adaptive visual information retrieval system

Author

De Mauro, Ciro ; Gori, Marco ; Maggini, Marco

Author_Institution

Dipt. di Ingegneria dell´´Inf., Siena Univ., Italy

fYear

2001

fDate

6/23/1905 12:00:00 AM

Firstpage

898

Lastpage

902

Abstract

Given a user´s visual query, most visual information retrieval (VIR) systems rank the images in the database according to a predefined measure of similarity and return the most similar ones. We propose an adaptive VIR system that uses a retrieval process based on relevance feedback in order to learn the similarity criterion from the user. Our system is based on a structured representation of the image which is then processed by a recursive neural network. The search algorithm refines its response trying to minimize the number of steps required to find the target image

Keywords

content-based retrieval; directed graphs; neural nets; relevance feedback; search engines; APEX; adaptive visual information retrieval system; recursive neural network; relevance feedback; retrieval process; search algorithm; similarity criterion; structured representation; visual query; Adaptive systems; Content based retrieval; Image databases; Image retrieval; Information retrieval; Neural networks; Neurofeedback; Search engines; Spatial databases; Visual databases;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 2001. Proceedings. Sixth International Conference on

Conference_Location

Seattle, WA

Print_ISBN

0-7695-1263-1

Type

conf

DOI

10.1109/ICDAR.2001.953916

Filename

953916