iSearch: Mining Retrieval History for Content-Based Image Retrieval

Authors:
Hongyu Wang;Beng Chin Ooi;Anthony K. H. Tung
Affiliations:
-;-;-
Venue:
DASFAA '03 Proceedings of the Eighth International Conference on Database Systems for Advanced Applications
Year:
2003

Citing 0
Cited 3

Using relevance feedback with short-term memory for content-based spine X-ray image retrieval

Neurocomputing
Development of neuro-fuzzy system for image mining

WILF'05 Proceedings of the 6th international conference on Fuzzy Logic and Applications
Context-Based image similarity queries

AMR'05 Proceedings of the Third international conference on Adaptive Multimedia Retrieval: user, context, and feedback

Quantified Score

Hi-index	0.00

Visualization

Abstract

Relevance feekback is a powerful technique to bridge thegap between high-level concepts and low-level features,and has been successfully applied to the field of Content-Based Image Retrieval (CBIR) to improve the queryaccuracy in recent years.In this paper, we propose a novel model (iSearch) which predicts user's informationneed based on past retrieval history.Based on theprediction, we then transform the feature space based onthe user's feedback and employ an ExpectationMaximization (EM) approach to simulate the new spaceby a mixture of Gaussian distributions.The experimentalresults show that the proposed method is effective andcaptures the user's information need more precisely.