Title :
Long term learning for image retrieval over networks
Author :
Picard, David ; Revel, Arnaud ; Cord, Matthieu
Author_Institution :
CNRS, Univ. Cergy-Pontoise, Cergy-Pontoise
Abstract :
In this paper, we present a long term learning system for content based image retrieval over a network. Relevant feedback is used among different sessions to learn both the similarity function and the best routing for the searched category. Our system is based on mobile agents crawling the network in search of relevant images. An ant-behavior algorithm is used to learn the category dependent routing. With experiments on trecvid´05 key-frame dataset, we show that the smart association of category dependent routing and active learning leads to an improvement of the quality of the retrieval over time.
Keywords :
content-based retrieval; human computer interaction; image retrieval; learning (artificial intelligence); mobile agents; relevance feedback; active learning; ant-behavior algorithm; category dependent routing; content based image retrieval; long term learning system; mobile agent; network crawling; relevant feedback; similarity function; user interaction; Computer networks; Concurrent computing; Content based retrieval; Feedback; Image retrieval; Information retrieval; Labeling; Mobile agents; Routing; Software; Cooperative systems; Distributed information systems; Image databases; Information retrieval;
Conference_Titel :
Image Processing, 2008. ICIP 2008. 15th IEEE International Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
978-1-4244-1765-0
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2008.4711908
