Case Study #1: Document Exploitation - Government Agencies

Important documents are usually only available in paper or image form. Searching and retrieving relevant documents or passages from large collections is a difficult task.

With ArborScript ES™™, documents are converted into digital images and transferred to a central repository. The documents are cleaned, deskewed, and automatically sorted based on their language content. Because ArborScript ES™ is able to discriminate between handwriting and machine-printed text, images containing handwriting can be automatically separated for manual interpretation while machine-printed characters are quickly converted into computer text. Extracted text is indexed and linked to its original document image for subsequent electronic searching and archiving.

The government is now able to access large collections of document images efficiently, thereby extending its overall knowledge management capability. Such capabilities lead to analysis reports that are more timely and comprehensive.