Docunext


Tesseract OCR and Ocropus

February 26th, 2009

I finally got around to trying out the tesseract optical character recognition software. It works way better than any other OCR software I've used, and I've used quite a bit.

There are debian packages for both tesseract and leptonica, but I wanted to try out Ocropus too because it has page layout capabilities. And so I had to download and install a few items, thankfully, this page supplied all the information I needed.

Ocroscript at the Docunext Wiki

Yearly Indexes: 2003 2004 2006 2007 2008 2009 2010 2011 2012 2013 2015 2019 2020 2022