Tesseract

Tesseract Open Source OCR Engine was originally developed at Hewlett Packard Laboratories Bristol and at Hewlett Packard Co, Greeley Colorado between 1985 and 1994.

The Tesseract OCR engine was one of the top 3 engines in the 1995 UNLV Accuracy test. Between 1995 and 2006 it had little development done on it, but it is probably one of the most accurate open source OCR engines available.

Please note that this software has no page layout analysis, no output formatting, and no graphical user interface. 

Tesseract runs from the command line. It can only process an image of a single column and create text from it. It can detect fixed pitch vs proportional text. Tesseract handles image files in TIFF format (with filename extension .tif); other file formats need to be be converted to TIFF before being submitted to Tesseract.

Tesseract 2.03

Price Free to download Size 1.0MB License Apache License 2.0 Developer Ray Smith, Phil Cheatle, Simon Crouch, Dan Johnson, Mark Seaman, Sheelagh Huddleston, Chris Newton, and several others Website code.google.com System Requirements Support Sites: Forums, OCRopus, Hacking Tesseract, HowtoForge Selected Reviews: Linux Journal, Linux.com

Features include:

• Suitable for use as a backend, and can be used for more complicated OCR tasks including layout analysis by using a frontend such as OCRopus
• Scripts to test accuracy against the original 1995 tests run by UNLV
• Ability to train in other languages and scripts
• Support for English, French, Italian, German, Spanish, Dutch

Last Updated Sunday, September 14 2008 @ 09:29 AM EDT