image-deduplication 开源项目推荐（63 个）

idealo /imagededup

😎 Finding duplicate images made easy!

umbertogriffo /fast-near-duplicate-image-search

Fast Near-Duplicate Image Search and Delete using pHash, t-SNE and KDTree.

vitali-fedulov /images4

Image similarity in Golang. Version 4 (LATEST)

mk-fg /image-deduplication-tool

Tool to detect (and get rid of) similar images using perceptual hashing (pHash lib)

InexplicableMagic /photodedupe

A utility for locating near duplicate photos irrespective of image resolution, compression settings or file format.

SeanWong17 /Image-Deduplicator

高性能图像去重工具：基于深度学习特征与余弦相似度，从海量图片中定位重复项

khasinski /phash-rb

Phash ruby implementation, compatible with Phashion

shashankag14 /similar-images-remover

A Python tool to identify and remove similar-looking images from a dataset. Utilizes image preprocessing and hashing techniques for efficient comparison.

nickname21kmr /emaki

本地运行的二次元插画整理工具：自动认角色、按角色 / 作品归类、查重。Local-first anime illustration organizer for Windows: character recognition, grouping by character and series, duplicate finder.

Rukario /Schande

Downloader with custom wildcard system: cherry-picking internet with asterisks for HTML or right-carets for API, whether it's for time-critical website moments or just for laziness. Features directory listing and serve, alarm (essentially in-stock tracker), file sorter (organizer), image duplicate finder and tools for naked eyes.

ayumilove /xImageDuplicateChecker

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。

Paulogb98 /DupFile-Analyzer

Interactive Rust CLI to find duplicate files (SHA-256) and visually similar images (perceptual hashing) — fast, parallel with Rayon, safe dry-run deletion.

loveFirefly-26710 /ImgDedup

Windows 本地图片去重工具，可查找完全重复、感知近似和语义相似图片。每组由用户审阅；删除的文件会移入回收站或指定目录，并可撤销。Local Windows app for finding exact, perceptually similar, and semantically similar images. Review every group yourself; deletions go to the Recycle Bin or a chosen folder and can be undone.

Lewickiy /blackhole-eh

Client-side lossless image deduplication engine using block-level content-addressable storage

HQarroum /piaggio

🏍️ A clustering tool providing exact and near de-duplication of images using vector embeddings.

jamjamjon /ilytix

A CLI tool for images analysis: checking image integrity, images deduplication, image retrieval.

blackmonk13 /similar_images

a Python command-line tool that identifies and groups similar images using average hashing. It supports single-level and recursive directory scanning, adjustable similarity threshold, and presents results in JSON format. Ideal for image deduplication, organization, and content-based retrieval tasks.

ad-si /idup

CLI tool to identify duplicate images and photos

roper120nzt /DupeGem

Fast, local duplicate-image finder for Windows using perceptual hashes and exact MD5 matching.

nicolasleal570 /duosift

Local, private duplicate-image finder for the desktop (Tauri 2 + React 19 + Rust)