Image Retrieval And Classification Using Local Feature Vectors

TL;DR

This paper analyzes and enhances a Content Based Image Retrieval system using local feature vectors, proposing methods to reduce response time and improve retrieval accuracy through a Two-Step Matching process and Meta-Learning framework.

Contribution

It introduces a Two-Step Matching process to decrease response time and a Meta-Learning framework to significantly boost retrieval performance in CBIR systems.

Findings

Two-Step Matching reduces response time significantly.

Meta-Learning improves retrieval performance by over two times.

Analysis of various image classification methods using local features.

Abstract

Content Based Image Retrieval(CBIR) is one of the important subfield in the field of Information Retrieval. The goal of a CBIR algorithm is to retrieve semantically similar images in response to a query image submitted by the end user. CBIR is a hard problem because of the phenomenon known as $\textit {semantic gap}$. In this thesis, we aim at analyzing the performance of a CBIR system build using local feature vectors and Intermediate Matching Kernel. We also propose a Two-Step Matching process for reducing the response time of the CBIR systems. Further, we develop a Meta-Learning framework for improving the retrieval performance of these systems. Our results show that the Two-Step Matching process significantly reduces response time and the Meta-Learning Framework improves the retrieval performance by more than two fold. We also analyze the performance of various image classification systems that use different image representations constructed from the local feature vectors.