Image Retrieval based on Bag-of-Words model

TL;DR

This survey reviews the use of the bag-of-words model in large-scale image retrieval, highlighting its effectiveness with local descriptors like SIFT and various system-building strategies.

Contribution

It provides a comprehensive overview of the bag-of-words model in image retrieval and discusses different strategies for system construction.

Findings

BoW model effectively uses local descriptors like SIFT for image retrieval

Scalable textual indexing schemes are employed in large-scale systems

Various strategies exist for building BoW-based image retrieval systems

Abstract

This article gives a survey for bag-of-words (BoW) or bag-of-features model in image retrieval system. In recent years, large-scale image retrieval shows significant potential in both industry applications and research problems. As local descriptors like SIFT demonstrate great discriminative power in solving vision problems like object recognition, image classification and annotation, more and more state-of-the-art large scale image retrieval systems are trying to rely on them. A common way to achieve this is first quantizing local descriptors into visual words, and then applying scalable textual indexing and retrieval schemes. We call this model as bag-of-words or bag-of-features model. The goal of this survey is to give an overview of this model and introduce different strategies when building the system based on this model.