Lector

A graphical ocr solution for GNU/Linux based on Python, Qt4 and tessaract OCR.

Author: Davide Setti

Introduction

Lector can help you to scan your tons of paper and create text document!

Lector lets you select areas on which you want to do OCR (Optical Character Recognition). Then you can run tesseract-ocr simply clicking a button. The resulting text can be proofread, formatted and edited directly in Lector.

Features:

scanning (available only on Linux)
OCR via tesseract (with support for more than 30 languages!)
selection areas for OCR
rotating of images
text editing
text formatting including Cap operations
white space display
spellchecking
Personal word list based on dictionary
export (via Save as) to odt (default), txt, html, pdf
translations

If you are interesting to translate Lector to your language, please check transifex.net

Please check out wiki pages especially requirements, changelog screenshots

Installation

There is no installer at the moment. Just download package, uncompress it and run:

lector.pyw

(if you downloaded source and you have installed required dependencies) or if you downloaded win32 package:

lector.exe

Help

Patches, code improvement, new features implementation are welcomed!

Do you need help? Join the Lector Users mailing list!