Software

• TRUEVIZ ground-truth editing software

• Open Source Software for Document Recognition/Analysis

• https://github.com/tesseract-ocr/tesseract

• http://gamera.informatik.hsnr.de/

• https://github.com/Early-Modern-OCR

• Hacker News discussion

• unpaper

Projects

Medical Article Record System

• Communications Engineering Branch
  • Communications Engineering Branch
• Ground Truth Data for Document Image Analysis
• Medical Article Record System - U.S. National Library of Medicine

Datasets

• Datasets List - TC11

Problems

Handwriting

Data

• IAM Handwriting Database
• IAM On-Line Handwriting Database