An Improved Relevance Feedback in CBIR

TL;DR

This paper introduces a novel relevance feedback method for Content-Based Image Retrieval that enhances retrieval accuracy by leveraging new techniques and information from feedback, including improvements to initial retrieval performance.

Contribution

It proposes a new relevance feedback approach that combines feature re-weighting, classification, and a novel method to improve initial retrieval accuracy using feedback information.

Findings

Enhanced retrieval accuracy over prior methods.

Improved 0-th iteration retrieval performance.

Demonstrated effectiveness through experimental results.

Abstract

Relevance Feedback in Content-Based Image Retrieval is a method where the feedback of the performance is being used to improve itself. Prior works use feature re-weighting and classification techniques as the Relevance Feedback methods. This paper shows a novel addition to the prior methods to further improve the retrieval accuracy. In addition to all of these, the paper also shows a novel idea to even improve the 0-th iteration retrieval accuracy from the information of Relevance Feedback.