KBookOCR is an easy to use graphical user interface wich allows you to recognize PDF or DJVU books and save it as a text file. Also it allows to recognize images from your scanner too.

Saturday, September 3, 2011


Rubuquet+ is out. This is 2 in 1 version of Rubuquet which uses CuneiForm or Tesseract OCR engine for recognition. Now, you don't need to run two different programs for different OCR engines.

Rubuquet+ web site.

Friday, July 22, 2011

Roadmap for version 2.2

  • Multi OCR engine support (add Tessaract OCR support)
  • Drag-n-Drop support
  • Fix broken native image size in viewer
  • Many other small improvements of KDE integration and small bug fixses

Sunday, July 17, 2011

Monday, June 27, 2011

Rubuquet Tesseract edition

This version has the same functionality as a standard edition but it uses Tesseract engine to recognize files. Now you can choose between CuneiForm or Tesseract OCR engine to use with Rubuquet.

Visit Rubuquet Tesseract edition page →

Thursday, June 23, 2011

Rubuquet for console fans

Hi guys! If you prefer console more than GUI applications, you should try Rubuquet — Ruby powered script. It has less features than KBookOCR however it was created to provide a simple and fast way to convert PDFs or DJVu-files in TXT.

Visit Rubuquet homepage →

Wednesday, June 22, 2011

KBookOCR 2.0

New KBookOCR 2.0 is out!

  • new GUI;
  • kernel system rewrited from scratch (project save/load; integration with cuneiform);
  • Skanlite integration for rich image scanning options.

Wednesday, June 8, 2011

KBookOCR 1.4.1

We released a new version of KBookOCR 1.4.1

  • ability to save the project file to open project next time and continue working from the last saved step
P.S: the next KBookOCR version number will be 2.0

Download from openDesktop.org →

Bugreports are wellcome! →