Relevance Feedback Techniques for Image Retrieval Using Multiple Attributes

Authors:
Tat-Seng Chua;Chun-Xin Chu;Mohan Kankanhalli
Affiliations:
National University of Singapore;National University of Singapore;National University of Singapore
Venue:
ICMCS '99 Proceedings of the IEEE International Conference on Multimedia Computing and Systems - Volume 2
Year:
1999

Citing 0
Cited 2

MUSE: A Content-Based Image Search and Retrieval System Using Relevance Feedback

Multimedia Tools and Applications
Bayesian Learning for Image Retrieval Using Multiple Features

IDEAL '00 Proceedings of the Second International Conference on Intelligent Data Engineering and Automated Learning, Data Mining, Financial Engineering, and Intelligent Agents

Quantified Score

Hi-index	0.02

Visualization

Abstract

This paper proposes a relevance feedback (RF) approach to content-based image retrieval using multiple attributes. The proposed approach has been applied to images' text and color attributes. In order to ensure that meaningful features are extracted, a pseudo object model based on color coherence vector has been adopted to model color content. The RF approach employs techniques developed in the fields of information retrieval and machine learning to extract pertinent features from each of the attributes. It then uses the user's relevance judgments to estimate the importance of different attributes in an integrated content-based image retrieval. The system developed has been tested on a large image collection containing over 12,000 images. The results demonstrate that the proposed RF approaches and pseudo-object based color model are effective.