# antimatter15/ocrad.js

OCR in Javascript via Emscripten

Repository: https://github.com/antimatter15/ocrad.js
Canonical: https://ross.abutalabs.com/products/ocradjs
Homepage: http://antimatter15.github.io/ocrad.js/demo.html
Language: JavaScript
License: GPL-3.0
License Family: copyleft
Last push: 2020-09-02T20:34:54+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4629, "days_push": 2191, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3517, forks 379 (observed 2026-08-28T04:08:07.874621+00:00)

## What it is
Ocrad.js is a pure-JavaScript port of the Ocrad OCR engine, compiled to JavaScript via Emscripten, that converts scanned images of text back into text entirely in the browser. It exposes a simple global OCRAD() function accepting canvas, Context2D, or ImageData inputs with no server or large training-data dependencies.

## Use cases
- extract text from images in the browser
- add handwriting input to a tablet app offline
- build a browser extension to copy text from images
- run OCR client-side without a server
- recognize text in an offline note-taking app

## When to choose
- you need lightweight (~1MB) client-side OCR with no server round-trip
- you want offline-capable text recognition in a web app or extension
- you need low-latency OCR on touchscreen devices

## When to avoid
- you need high accuracy on real-world scanned documents - Tesseract is far more accurate
- you need modern maintained OCR - the project has seen little activity since 2020
- you need handwriting or multi-language recognition at production quality

## Facets
- artifact type: library
- maturity: maintenance
- function: ocr, image-processing, nlp
- domain: computer-vision, image-processing, web-development, frontend
- platform: browser, wasm, cross-platform
- tags: emscripten, client-side-ocr, text-recognition, offline-capable, gpl-3.0, javascript

## Member repositories
- antimatter15/ocrad.js (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:07.874621+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 2026-08-29T18:35:34.291349+00:00, confidence not recorded.
  - readme: https://github.com/antimatter15/ocrad.js (fetched 2026-08-28T04:08:07.874621+00:00, sha e01ef896b9b1)
  - homepage: http://antimatter15.github.io/ocrad.js/demo.html (fetched 2026-08-29T09:29:40.557804+00:00, sha 758bf1dac5f1)
- Data as of 2026-08-30T08:39:29.467469+00:00.