# hiroi-sora/Umi-OCR

OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。

Repository: https://github.com/hiroi-sora/Umi-OCR
Canonical: https://ross.abutalabs.com/products/umi-ocr
Language: Python
License: MIT
License Family: permissive
Topics: paddleocr, ocr, ocr-python, umi-ocr, qml, qt, screenshot
Last push: 2025-11-20T14:58:13+00:00

## Health v2 (maintenance only)
Score: 47/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 53, release rhythm 8, longevity 100
- inputs: {"age_days": 1619, "days_push": 286, "days_rel": 526, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 46882, forks 4586 (observed 2026-08-28T04:12:11.139498+00:00)

## What it is
Umi-OCR is a free, open-source, fully offline OCR application for Windows and Linux with a Qt/QML GUI. It supports screenshot OCR, batch image recognition, PDF text extraction and searchable PDF generation, QR code scanning/generation, and CLI/HTTP interfaces for external calls.

## Use cases
- extract text from screenshots offline
- batch OCR a folder of images
- convert scanned PDFs to searchable PDFs
- recognize text without sending data to the cloud
- scan or generate QR codes
- call OCR from scripts via command line or HTTP API
- ignore watermarks and headers/footers when recognizing documents

## When to choose
- you need offline, privacy-preserving OCR on Windows or Linux
- you want batch processing of images or PDFs with layout handling
- you need an HTTP or CLI OCR service for automation

## When to avoid
- you need a library to embed in your own Python/JS code rather than a standalone app
- you need macOS or mobile support
- you need cloud-scale or GPU-cluster OCR throughput

## Facets
- artifact type: application
- maturity: stable
- function: ocr, image-processing, pdf, gui, cli
- domain: computer-vision, image-processing, pdf, developer-tools
- platform: windows, cli
- tags: offline-ocr, screenshot-ocr, batch-ocr, qrcode, paddleocr, searchable-pdf, http-api, linux, desktop

## Member repositories
- hiroi-sora/Umi-OCR (main) score 47

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:11.139498+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 2026-08-29T16:21:36.072902+00:00, confidence not recorded.
  - readme: https://github.com/hiroi-sora/Umi-OCR (fetched 2026-08-28T04:12:11.139498+00:00, sha ece77b53895a)
- Data as of 2026-08-30T08:39:29.467469+00:00.