State of the Art: Image Hashing

TL;DR

This paper reviews current perceptual image hashing techniques, both traditional and deep learning-based, highlighting the most effective methods for robust image similarity detection in large-scale applications.

Contribution

It provides a comprehensive overview of state-of-the-art perceptual image hashing methods, comparing traditional and deep learning approaches to identify the best practices.

Findings

Deep learning methods outperform traditional hashing in robustness.

Traditional methods are faster but less accurate.

Deep learning approaches achieve higher similarity detection accuracy.

Abstract

Perceptual image hashing methods are often applied in various objectives, such as image retrieval, finding duplicate or near-duplicate images, and finding similar images from large-scale image content. The main challenge in image hashing techniques is robust feature extraction, which generates the same or similar hashes in images that are visually identical. In this article, we present a short review of the state-of-the-art traditional perceptual hashing and deep learning-based perceptual hashing methods, identifying the best approaches.