SIFT and it’s Variants: An Overview

Abstract

SIFT is a powerful feature description algorithm in the field of computer vision and pattern recognition. It finds its application in many real-world applications like object recognition, image retrieval, image matching,etc. due to its numerous robust properties. Since its inception, researchers are trying to improvise it in many ways and as a result, many variants of SIFT came into existence. In computer vision and pattern recognition literature, there are a good amount of reviews articles available on the earliest variants of SIFT like PCA-SIFT, SURF, etc. However,very limited literature is available that reviewed the latest variants. This paper comprehensively reviews some of the state of the art variants in SIFT family along with the popular old variants. It discusses the drawbacks in SIFT and how these drawbacks paved the way for the existence of different variants. A detailed description of each variant is presented and concluded with its pros and cons. The different variants reviewed in the paper are PCA-SIFT, SURF, GSIFT, CSIFT, ASIFT, VF-SIFT, and DSIFT.