Captiva 6.5 Extracts Data While Digitizing Documents

EMC's new Captiva 6.5 classifies and extracts business information as documents are scanned. EMC's goal for Captiva 6.5 is to speed up the document-capture process for invoices, claims and other documents by learning their properties. The new Captiva feature is called Production Auto Learning. User interfaces can be localized.

EMC has rolled out the latest version of its solution that digitizes paper documents in the enterprise Relevant Products/Services. Captiva 6.5 offers new capabilities that allow it to learn document properties while processing.

Dubbed Production Auto Learning, the new Captiva automatically classifies and extracts business information from documents as they are scanned. The goal is to speed up the capture process for invoices, loan documents, policy claims, and other documents. Analysts are bullish on the innovation.

"IDC continues to see strong interest in document-capture solutions -- especially solutions that help organizations automate their paper-based business processes," said Melissa Webster, program vice president for content and digital-media technologies at IDC. "And in this regard, enterprises have two key requirements. First, the solution must offer very high performance. Second, it must be self-learning, to reduce implementation time and cost, as well as ongoing application maintenance costs."

Manipulating Images

Captiva can process more than 10 million images a day and offers new drag-and-drop processes that aim to help deploy capture solutions more quickly. The new version also helps global Relevant Products/Services companies with localized user interfaces in various languages, including French, Spanish and simplified Chinese.

Erica Boudreau, archivist for the John F. Kennedy Presidential Library in Boston, said the new version of Captiva lets his team compress scanned images using a lossless method, saving storage Relevant Products/Services space and costs while maintaining high-quality images from historical documents.

"The ability to quickly manipulate images and to process them using Captiva's latest optical-character-recognition engine produces more accurate results and saves our staff significant time," Boudreau said.

The All-Digital Enterprise

Charles King, principal analyst at Pund-IT Relevant Products/Services, noted that the IT industry loves digital information, and with good reason -- it serves as the foundation for thousands of business computing solutions and hundreds of billions of dollars in annual sales. But while the "all-digital enterprise" is a lovely utopian notion, he added, most companies in the real world utilize both digital and physical documents and records that cohabitate in a sometimes-uneasy or even uncomfortable manner.

As King sees it, virtually every private and public organization manages a delicate balance between physical and digital records, between traditional and technological business processes -- and EMC's Captiva 6.5 is designed to help organizations effectively address this imbalance.

"The new features -- Production Auto Learning, performance enhancements, and additional language support -- all tweak a mature, well-established and innovative solution, speeding setup and deployment processes and significantly improving overall performance," King said.

"Captiva 6.5 is obviously aimed at global enterprises, but those are the organizations that have the greatest need for comprehensive, intelligent capture solutions," he said. "They are also likely to be most aware of the potential costs they face -- in legal fees and fines, wasted time and revenues, and lost confidence and trust among customers and partners -- should the unthinkable ever occur."