OCR developers' resources

This page provides some links to open source software and projects related to OCR.

Open source OCR software

• Clara OCR
• GOCR
• GNU Ocrad
• Tesseract OCR (moved from SourceForge)
• kognition
• pattern-lab
• ocre: o.c.r. easy (and free/libre)
• HOCR - Hebrew character recognition c/c++ library
• NHocr: the Japanese OCR
• tomoe: Online handwriting recognition engine (in Japanese)
• Zinnia: Online hand recognition system with machine learning
• Plasma OCR - An omnifont OCR engine for recognizing formulas
• WordSnap OCR - An application for text input using camera on Android
• Eye :: Java-based text recognizer
• Ruby OCR gem
• gttext - Ground Truthing tool for Color Images with Text

Image processing tools specialized for OCR

• unpaper : post-processing scanned and photocopied book pages
• Tifftool : high-performance tool to clean scanned documents

Tools and libraries for document analysis and recognition

• Leptonica (Google Code)
• ocropus - open source document analysis and OCR system (Google Code)
• Project-O2 : various tools for layout analysis
• IUPR Research Group - Demos & Downloads
• Character Recognition API by NTT docomo. (in Japanese)
• KanjiVG
• Microsoft OCR Library Sample

Free OCR software

• TopOCR - Free OCR for Digital Cameras

Other link collections

• OCR and Text Recognition: Academic Research Projects. (SSI Division, Trentino Cultural Institute, Italy)
• Document Understanding and Character Recognition WWW Server (University of Maryland, US)
• Linux and OCR