ABBYY enhances data capture SDK
ABBYY enhances data capture SDK
April 27, 2009:Data capture specialist ABBYY has unveiled a new software development kit (SDK) for integrating its technologies in Windows-based applications.
ABBYY FlexiCapture Engine 8.0 combines technologies and tools for processing forms, semi-structured and unstructured documents, data verification, document classification, and export forbackend processing and archiving in a single developer environment.
“With the release of data capture SDK, we are happy to provide developers with powerful and flexible instrument to smoothly integrate ABBYY’s technologies that have an impressive history of success in various markets,” said AndreyIsaev, director of the technology products department at ABBYY."The need for data capture is continually growing and expanding into a wide number of new segments and opportunities across many vertical markets.FlexiCapture Engine is designed to address this growing audience by giving developers the tools to easily customise their solutions according to vertical market needs."With its ability to extract data from forms and documents of any type and complexity, the SDK is an instrument for developing vertical solutions such as those intended for processing invoices, medical forms, insurance applications, examination tests, ID cards and many more. It can be also used for creating customised data capture applications for various scanning devices and terminals.FlexiCapture Engine delivers intelligent document separation and classification capabilities which eliminate the need for manual pre-sorting and separation and enable the processing of all document types in a single stream. As a result, the SDK can be used for high-load projects or integrated into enterprise management and workflow systems. The new product also offers broad language support so it can be integrated into international document management systems.The product provides a powerful set of ABBYY’s core recognition technologies including Intelligent Character Recognition (ICR) for hand-printed text, Optical Character Recognition (OCR) for printed text, barcode recognition, Optical Mark Recognition (OMR), and PDF conversion. It also includes technology to process semi-structured and unstructured documents including invoices, price lists, waybills, contracts and other documents where the location of data fields is not fixed.It additionally provides flexible descriptions called FlexiLayouts for analysis and processing of semi-structured and unstructured documents. Using logic and a sequence of hypotheses, FlexiLayouts allow the program to accurately locate fields to capture relevant data despite their varied locations on different documents. The same technology also simplifies the processing of long tables that span across multiple pages.FlexiLayouts also enable automatic document separation and classification. They automatically identify document types in a processing stream, including multi-page documents with varied number of pages. As a result, all types of forms and documents (including appendices and attachments) can be automatically processed in a single batch without the need for manual presorting or use of blank separation pages, patch codes, orbarcodes.FlexiCapture Engine 8.0 supports the ability to automatically index documents with relevant data for improved searchability and convert them to PDF and PDF/A formats for long-term archiving.It offers powerful data validation and verification instruments and methods such as checking captured values against databases, checking data formats, data validation via scripts and special API for effective manual verification.