Ocrad

Ocrad

Developer(s)	Antonio Diaz Diaz
Stable release	0.21 / January 11, 2011; 9 months ago (2011-01-11)
Operating system	Unix-like
Type	Optical character recognition
License	GNU General Public License
Website	http://www.gnu.org/software/ocrad/

Ocrad is an optical character recognition program, developed as part of the GNU Project. Like all GNU software it is free software, and is licensed under the GNU GPL.

Based on a feature extraction method, it reads images in portable pixmap formats known collectively as PNM (PBM, PGM and PPM; each of these formats comes with two versions: "plain" or "raw") and produces text in byte (8-bit) or UTF-8 formats. Also included is a layout analyzer, able to separate the columns or blocks of text normally found on printed pages.

The source code is 10,000 lines of C++.

User interface

Ocrad can be used as a stand-alone command-line application, or as a back-end to other programs.

Kooka, which was the KDE environment's default scanning application until KDE 4, can use Ocrad as its OCR engine^[1]. Because development of the programme ceased in 2007, current versions of the KDE deskop environment no longer contain Kooka. Ocrad can be also used as an OCR engine in OCRFeeder^[2].

History

Ocrad has been developed by Antonio Diaz Diaz since 2003. Version 0.7 was released in February 2004, 0.14 in February 2006 and 0.18 in May 2009.

Archives of the bug-ocrad mailing list go back to October 2003^[3].

References

1. ^ "Kooka home page". http://kooka.kde.org/. Retrieved 19 July 2010. 
2. ^ "GNOME GIT source code repository". http://git.gnome.org/browse/ocrfeeder/tree/README. Retrieved 3 February 2010. 
3. ^ "bug-ocrad Archives". http://lists.gnu.org/archive/html/bug-ocrad/. Retrieved 20 July 2010. 

External links

• Ocrad GNU Project Homepage
• Peter Selinger's Review of Linux OCR software
• Andreas Gohr Linux OCR Software Comparison
• Online OCR server powered by Ocrad
• Tesseract & Ocrad comparison, Linux Journal