Multilingual OCR
Imaged and paper documents (see imaging) can be converted into editable text through the use of Optical Character Recognition (OCR) software. This software takes the scanned files, which are simple images of text from the original documents, and reads them in a similar way to the human eye. It then converts the text into digital characters (such as can be found in a Word document). The output can be in any standard form of coding required by the client.
TransPerfect can also insert an index function, which permits clients to perform text searches on their scanned paper documents.
What sets us apart is the ability to leverage our in-house technology and expertise to perform all of these processes on documents in over 100 languages. Multilingual OCR is an extension of this facility, which allows for character recognition in a wide range of non-latin scripts, including Arabic, Bengali and Chinese (Traditional/Simplified). |
