For companies processing large volumes of documents (i.e., 1,000 or more a day), template-based data extraction simply isnt feasible -- or it creates more work than it saves. Moreover, intelligent features cannot be reverseengineered into a data-capture solution that was initially designed as a template-driven, keyword-based extraction tool. Two key features include:
Its ability to recognize and classify documents and data automatically, regardless of layout or format
Its ability to "auto-learn" new classifications and extraction procedures based on earlier examples
According to the company, these attributes cannot be retrofitted onto older, template-based technologies.
Brainware, Inc.'s IDC-distiller is an automated solution that uses intelligent data capture (IDC) and template-free extraction from any document. IDC-distiller enables template-free access to data within any type of document, however its formatted or stored. addition, IDC-distiller's table extraction capabilities automatically cull data from complex, extensive line-item tables found in large (i.e., 100-page) invoices, purchase orders, etc.