Identifying and removing near-duplicate images using perceptual hashing.
-
Updated
Apr 25, 2025 - Python
Perceptual hashing is the use of an algorithm that attempts to fingerprint multimedia for identification and comparison. Perceptual hashes of two similar multimedia should be similar.
Identifying and removing near-duplicate images using perceptual hashing.
Python library to calculate the difference hash (perceptual hash) for a given image, useful for detecting duplicates
Fast Near-Duplicate Image Search and Delete using pHash, t-SNE and KDTree.
Tool to detect (and get rid of) similar images using perceptual hashing (pHash lib)
Calculate PhotoDNA hashes using Python
[FAccT 2022] Source code for our paper "Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash".
I thought it would be nice to get an email alert when a new job posting appears on a website, so I can use this to check for the newest job openings on various sites
Perceptual hashing library in python (with redis)
A humble collection of command line tools for managing photos. Includes a perceptual hash for finding near-duplicates, and some exiftool wrappers for handling metadata.
Perceptual Diff pdiff is an fast image comparison utility that makes use of a computational model of the human visual system to compare images.
高效的Python图像查重工具,支持百万级图片文件的重复检测。集成多种算法包括MD5哈希、感知哈希(dHash/pHash/aHash)和C++加速库,可识别完全相同、分辨率调整、部分截取和水印变更的重复图像。
A trivial approach for near-duplicate detection of audios
find similar/duplicate images
Near Duplicate Video Detection (Perceptual Video Hashing) - Get a 256-bit comparable hash value for any video.
Numerous converters and image tools combined into one simple CLI. Easily convert and refine large batches of images directly in your terminal. Fast, simple and easy.
Python bindings for the Czkawka Rust library, a fast image similarity engine
a python aplication that generates a fingerprint to audio file, by extracting spectrogram and some features from it.
Music Detection Application that uses audio fingerprinting and perceptual hashing. Users can add their custom database with one click.
Logo Similarity - Extract and group 3,416 websites by logo similarity without ML clustering. Achieves 97.28% extraction rate and ~98% grouping precision using Union-Find + LSH.