# lolishinshi/imsearch

基于特征点匹配的大规模相似图片搜索

Repository: https://github.com/lolishinshi/imsearch
Canonical: https://ross.abutalabs.com/products/imsearch
Language: Rust
License: GPL-3.0
License Family: copyleft
Last push: 2026-07-19T10:05:48+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 93, longevity 100
- inputs: {"age_days": 1819, "days_push": 45, "days_rel": 45, "gap_med": 19, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1074, forks 59 (observed 2026-08-28T04:03:29.018886+00:00)

## What it is
A Rust-based large-scale similar image search tool that uses feature point matching (ORB features with a FAISS-style index) to find full images from small screenshot crops. It offers a CLI for indexing and searching plus an HTTP API server.

## Use cases
- find the full source image from a small screenshot crop
- build a reverse image search engine over a large local image collection
- search anime/game screenshots to identify the original artwork
- index millions of images for feature-based similarity search
- run an image search HTTP API on my own server

## When to choose
- you need to match partial crops/screenshots to full images, which perceptual-hash tools handle poorly
- you have a large image corpus (thousands to millions) and need fast approximate search
- you want a self-hosted image search with both CLI and HTTP API

## When to avoid
- you only need simple duplicate detection - perceptual hashing is lighter
- you cannot install OpenCV/OpenBLAS native dependencies
- you need semantic image search by content description rather than visual feature matching

## Facets
- artifact type: cli-tool
- maturity: active
- function: search-engine, computer-vision, image-processing, cli, http-server
- domain: computer-vision, image-processing
- platform: cli, rust
- tags: reverse-image-search, feature-matching, faiss, opencv, similarity-search, screenshot-search, search, linux, docker

## Member repositories
- lolishinshi/imsearch (main) score 94

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:29.018886+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:53:32.265718+00:00, confidence not recorded.
  - readme: https://github.com/lolishinshi/imsearch (fetched 2026-08-28T04:03:29.018886+00:00, sha 99d03311ed4c)
- Data as of 2026-08-30T08:39:29.467469+00:00.