A perceptual hash is a fingerprint of a multimedia file derived from various features from its content. Unlike cryptographic hash functions which rely on the avalanche effect of small changes in input leading to drastic changes in the output, perceptual hashes are "close" to one another if the features are similar.

Android librarry (kotlin) : Image (JPEG, BMP) comparison (perceptual hash algorithm)

Finds the images in the directory that are most similar to the others and deletes the N most similar ones. Use to remove similar images before training stable diffusion models.

A parallelised perceptual-hash based CBIR system with OAuth2+WebAuthn security. Co-authored with @redeye-fang

Computer Vision: Searching Similar Images powered by PHP and pHashes

An Image Deduplicator (using CNN/PHash classification models) with AVIF support

Rust duplicate image detector using standard phash (perceptual image hash) and pdqhash implementations, includes phdupes app: rust GUI (egui) and TUI (ratatui) for viewing and interacting with found duplicates, multithreaded scanning and (also RAW) image processing, configurable preload of images, metadata caching, Search inside Exif tags