JaidedAI/EasyOCR

Health v2 · maintenance only

Adoption not part of the score

29942 stars · 3602 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

library · maturity stable

ocr image-processing deep-learning machine-learning computer-vision image-processing machine-learning python cross-platform pytorch multilingual text-detection text-recognition scene-text document-processing natural-language-processing gpu docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="JaidedAI/EasyOCR")