Skip to content

Making Box Files 4.0

Shreeshrii edited this page Dec 8, 2016 · 7 revisions

The required format for LSTM 4.0alpha is still the tiff/box file pair, except that the boxes only need to cover a textline instead of individual characters. 'Newline' boxes with tab as the character must be inserted between textlines to indicate the end-of-line.

The following are example of 4.0 box tiff pairs created as part of LSTM training tutorial.

As of 02/02/2020


These wiki pages are no longer maintained.

All pages were moved to tesseract-ocr/tessdoc.

The latest documentation is available at https://tesseract-ocr.github.io/.


Clone this wiki locally