MICR E-13B source and language files for Tesseract 3.01 / TesseractDotNet

This archive contains compiled language file (in the "tessdata" folder) and source files (in the "Source" folder) for the MICR E-13B font found on the bottom of cheques. You only need to copy the mcr.traineddata file to your Tesseract "tessdata" folder to use this. The source files are only if you wish to improve the training somehow.

Usage: tesseract image.tif outfile -l mcr

Included in this archive is also the source and compiled files for Tesseract 2 / TessNet 2. Read the readme.htm file in that zip for more information.

Special characters to note: (also in the OCR output, strip the spaces prior to parsing)
Character Symbol looks a bit like this Standard
Output char
Transit / Route |: [
On-US / Account ||# @
Dash lll -
Cheque Amount .l' $

License
 Public Domain. Acknowledgements requested.

Links:
Tesseract Forum Discussion
Tesseract
TesseractDotNet
MICR on wikipedia

If have any changes or improvements, let me know and i shall included them here for everyone.

Hunter Beanland
hunter @ beanland.net.au
http://www.beanland.net.au/programming/dotnet/