# JaidedAI/EasyOCR

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Repository: https://github.com/JaidedAI/EasyOCR
Canonical: https://ross.abutalabs.com/products/easyocr
Homepage: https://www.jaided.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ocr, deep-learning, crnn, pytorch, lstm, machine-learning, scene-text, scene-text-recognition, optical-character-recognition, cnn, data-mining, image-processing, python, easyocr, information-retrieval
Last push: 2025-12-05T12:23:12+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 55, release rhythm 8, longevity 100
- inputs: {"age_days": 2363, "days_push": 271, "days_rel": 708, "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 29942, forks 3602 (observed 2026-08-28T04:11:53.763808+00:00)

## What it is
EasyOCR is a ready-to-use Python OCR library built on PyTorch that extracts text from images, supporting 80+ languages and popular writing scripts like Latin, Chinese, Arabic, and Devanagari. It handles both natural scene text and dense document text, returning bounding boxes, recognized text, and confidence scores.

## Use cases
- extract text from images in python
- read text from photos of street signs
- ocr scanned documents with multiple languages
- recognize chinese and english text in one image
- get bounding boxes around detected text
- alternative to tesseract for multilingual ocr
- build a receipt or invoice text extractor

## When to choose
- you need multilingual OCR with 80+ languages out of the box
- you want a simple pip-installable API with minimal setup
- you need to read text from natural scene images, not just clean scans
- you want GPU acceleration with a PyTorch backend

## When to avoid
- you need handwritten text recognition (not yet supported)
- you need extremely lightweight CPU-only deployment without deep learning dependencies
- you need maximum accuracy on specialized documents where fine-tuned commercial OCR is required

## Facets
- artifact type: library
- maturity: stable
- function: ocr, image-processing, deep-learning, machine-learning
- domain: computer-vision, image-processing, machine-learning
- platform: python, cross-platform
- tags: pytorch, multilingual, text-detection, text-recognition, scene-text, document-processing, natural-language-processing, gpu, docker

## Member repositories
- JaidedAI/EasyOCR (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:53.763808+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 2026-08-29T16:52:48.979702+00:00, confidence not recorded.
  - readme: https://github.com/JaidedAI/EasyOCR (fetched 2026-08-28T04:11:53.763808+00:00, sha d74f937a6d67)
  - homepage: https://www.jaided.ai (fetched 2026-08-29T07:49:54.672533+00:00, sha 5d250a640d60)
  - site_page: https://www.jaided.ai/aboutus (fetched 2026-08-29T07:49:54.675545+00:00, sha 3965d055a246)
  - site_page: https://www.jaided.ai/easyocr/install (fetched 2026-08-29T07:49:54.679367+00:00, sha 4d712c78412b)
  - site_page: https://www.jaided.ai/easyocr/documentation (fetched 2026-08-29T07:49:54.681159+00:00, sha 02fb14f34481)
  - registry_pypi: https://pypi.org/pypi/easyocr/json (fetched 2026-08-29T07:49:54.683263+00:00, sha b13f7e230634)
  - site_page: https://www.jaided.ai/easyocr (fetched 2026-08-29T07:49:54.677495+00:00, sha 054b349d3faf)
- Data as of 2026-08-30T08:39:29.467469+00:00.