Optical Character Recognition (OCR) Tool for Georgian and mixed-language documents

It is anticipated that the International Criminal Court (hereafter referred to as the ICC) located in The Hague, The Netherlands, will shortly be issuing a solicitation for an Optical Character Recognition (OCR) Tool for Georgian and mixed-language documents In this connection, the ICC is requesting expression of interest from qualified firms.

Description

ICC is looking to acquire a solution that will meet the following high level requirements:

• The tool must have the the ability to generate text for documents in the Georgian (Kartvelian) language.

• The tool must be delivered as a standalone package;

• The input format for the tool is PDF, other formats are considered optional;

• The output of the tool should be either a searchable PDF or a separate txt file that represents the OCR layer of the original document. Other output formats are optional;

• Preferably, the tool should be able to generate OCR-ed layer for mixed language documents that contain   text in the following languages: Georgian, Russian, and English. Support for additional languages is optional;

• Preferably, the software should allow for batch OCR-ing of multiple documents at once instead of providing a capability to OCR a single document at a time;

• Preferably, the tool should allow for adjustments in OCR quality (lower quality setting should produce an OCR faster, higher quality setting would produce a potentially better OCR layer more slowly);

Interested firms/organizations should forward their Expression of Interest by facsimile or e-mail to the attention of Mrs. Kent Foster at fax no. +31 70 515 8336 or by e-mail kent.foster@icc-cpi.int.