Document Capture and OCR

Document Capture refers to uploading documents in digital format or by scanning paper documents to an electronic document repository where relevant data can be extracted. For instance, invoices can be scanned, uploaded and data such as client number, Company name, date etc can be read by the OCR system.

OCR (Optical Character Recognition) or text recognition uses intelligent algorithms to convert scanned document images into editable text. This operation can be performed in specific areas of a form.

Optical Character Recognition diagram
For most Document Management solutions this usually involves separate systems a number of steps but our solution reduces costs and man power by deploying one integrated cost-effective system. Using RecoStar as the powerful embedded OCR engine we can handle any type of forms processing at extremely high volumes.
Optical Character Recognition processing diagram

OCR Features:

• Outstanding performance with hand block letters and machine character sets
• Wide range of search and control options
• High speed and recognition accuracy
• Integration with all major data capture systems
• Voting by the Experts: combining the strengths of leading recognition engines
• Multiple-Expert Voting: application of contextual knowledge
• Machine print and handwriting recognition for all major languages
• Sophisticated image pre-processing and form processing
• Adaptable, learning dictionaries
• Design Studio for creating batch classes