Streamline. Transform. Reduce. 

In today’s competitive environment, businesses must improve efficiency, reduce overhead, capture structured data and leverage it. Hybrid workflows that include paper documents are still a reality in most organizations, and often pose the greatest challenge in enterprise content management.

Extract’s Advanced Data Capture and Indexing for SharePoint streamlines high volume document workflows that include electronic content, paper documents, or both. Classifying and capturing content electronically ensures that your information is accurate, retrievable and auditable.

How does it work?



Document Recognition and Classification
As documents are scanned, Extract’s industry-leading OCR, ICR and MCR engines automatically recognize and classify documents based on visual appearance and textual content. Speckled (salt and pepper), skewed or otherwise low quality documents are processed with a full suite of image enhancement tools to improve readability.

Advanced Data Capture
Once a document is classified, data is extracted using predefined rules based on each organization’s business needs. Extract’s National Rule Set® is the most comprehensive set of logic, clues and algorithms designed for the electronic capture of any data type, from structured and unstructured documents. Automating the capture of all relevant data types from forms and documents dramatically reduces keystrokes, minimizing the need for expensive, error-prone data entry.

Scalable, Flexible and Innovative
Advanced Data Capture and Indexing for SharePoint is designed to handle projects of all sizes, workflow configurations and document types, including: invoices, purchase orders, loan applications and HR documents, as well as government and medical records/reports.

Key Features

• Robust, server-based enterprise content management tool
• Document Recognition and Classification
• Document Cleanup using the industry’s leading image enhancement tools
• Index using pre-configured rules based on SharePoint content types
• Batch processing and on-the fly metadata capture
• National Rule Set® - the most comprehensive set of logic, clues and algorithms designed for electronic data capture