CuneiForm
CuneiForm (OpenOCR) is a text recognition software for printed templates. Manuscripts or PDF-files, the program can not recognize, however, but table structures. The language-model is applicable for 20 languages, and the results can be used as HTML, RTF or ASCII text to save, or export directly to Word or Excel. These fonts are, and the structure of the document unchanged.
CuneiForm has only recently made an open source software. It was developed by the Russian company Cognitive Technologies and means something like cuneiform (from the English cuneiform = wedge-shaped).
Only since April 2008, a commercial use is possible because the source code is available only since 2008. By Jussi Pakkanen exists a portable version of CuneiForm. Operating System: Linux, BSD, Mac OS X and Windows.
Support of 20 languages: English, German, French, Spanish, Italian, Portuguese, Dutch, Russian, Mixed Russian-English, Ukrainian, Danish, Swedish, Finnish, Serbian, Croatian, Polish and others.
