Open Source Software for Document Recognition/Analysis

OCR Software

Clara OCR
GOCR
OOCR
Kognition
phpOCR
wxOCR
OCRchie
SimpleOCR free, but not open source



Document Analysis/OCR Libraries and Application Development Software

Lince (artificial vision library)
libGOCR
Illuminator
Gamera A tool for the development of document recognition applications


Document Annotation Software

TAT

Utilities

ISRI OCR Performance Evaluation Toolkit
Rover Based on TRUEVIZ, implemented in Java.
PinkPanther Tool for creating groundtruth and auto-evaluation of page segmentation
TRUEVIZ Groundtruth editing and visualization software
PSET Page segmentation evaluation toolkit
Distort tool for introduction of noise

Data Sets

ISRI Images and Groundtruth data from the Information Science Research Institute
MARG Medical Article Records Groundtruth
Links to several off-line handwriting databases
Links to info on some more (not all free) databases

Bibliography

eXEDRA: a complete Open Source Architecture for Paper Document recognition
The architecture of TRUEVIZ: A groundTRUth/metadata Editing and VIsualiZing toolkit
Ground truth data for document image analysis




Other Resources

Academic OCR and text recognition research projects
Stanford OCR Resource List
OCR FAQ
Document Understanding and Character Recognition WWW Server

Protein Calculator

Protein Calculator