Archivista Box with Open Source OCR
Swiss vendor Archivista offers a document management solution comprising T2 Linux, OCR software, scanning software, archiving software and hardware. Version VIII of the GPL'd including the free OCR programs Ocrad 0.17 and Tesseract 2.0 is now available for downloading.
An ISO image of the software package is now available from the company website. Although the link for version VIII takes users to a slightly out of date Sourceforge page, the download link at Sourceforge will take you to the right version.
You can test the package by booting the live CD or installing on disk. The proprietary OCR software normally supplied with the product, Finereader by Abby is not included with the Open Source variant.
According to Archivista, the new Open Source OCR programs, Ocrad and Tesseract, achieve good recognition rates for normal correspondence. Digital cameras, SANE-compatible scanners and digital copiers are supported as input devices.
The vendors offers customers the Archivista box as a hardware and software bundle. Depending on the version, the box contains a PC and a scanner. The entry-level model starts at around 2000 euros.