rhsimplex/image-match

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

2978 stars · 404 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python library for computing image signatures and searching for near-duplicate images across corpora of billions of images, backed by Elasticsearch. It is based on the Wong et al. image signature algorithm, similar to pHash, and is intended for duplicate detection rather than conceptual similarity.

Use cases

• find near-duplicate images in a large corpus
• detect copyright violations of images
• build a reverse image search engine
• deduplicate an image dataset
• search billions of images quickly
• compute perceptual image signatures in python

When to choose

• you need to find nearly identical or slightly modified images at very large scale
• you want a pHash-like alternative with a scalable database backend
• you need high-rate image insertion into a searchable index

When to avoid

• you want conceptually or semantically similar image search (e.g. deep learning embeddings)
• you need actively maintained software - the repo is explicitly unmaintained
• you cannot run Elasticsearch as a dependency

Facets

library · maturity abandoned

search-engine image-processing database image-processing computer-vision python cross-platform image-signatures duplicate-detection perceptual-hashing elasticsearch reverse-image-search search

Member repositories

For agents

markdown · JSON · MCP: product_card(name="rhsimplex/image-match")