ABBYY Recognition Server provides a set of key functions for making text-based information locked in static images easily discoverable and turning it into a valuable asset. They include:

PDF out of any document

ABBYY Recognition Server automatically converts paper, image and electronic documents and saves them as compressed archive compliant files, such as PDF or PDF/A. A wide range of input formats is supported, including DOCX, XLSX, ODT,PPT and more.

Support of Various Conversion Scenarios

ABBYY Recognition Server can process image documents acquired directly from scanners and MFPs, or imported from network or FTP folders, Microsoft® SharePoint®libraries, or mailboxes. It also offers an API for submitting tasks programmatically from client applications. Converted documents can be delivered to destination folders, SharePoint libraries or email addresses as well as returned to the client via API or routed to the target business system by a scripted rule. For “read-only” archives of image documents, a special mode is available that allows replicating the entire structure of the archive in searchable format without altering the original images.

Integration with Microsoft SharePoint

Images can be processed via OCR and converted into searchable files in a consistent way before they are uploaded to the Microsoft SharePoint site. Image documents that are already stored in SharePoint libraries can be converted in searchable PDF right within the library. Scanned PDF files can be enhanced with a text layer and stored under a new version number tracking the document’s history. All newly arriving images will be detected and converted automatically. For TIFF archives within SharePoint, an IFilter is available for background content extraction.

OCR and Barcode Recognition

At the core of ABBYY Recognition Server is a powerful OCR engine that can process documents in over 190 languages. It is supplemented by a barcode recognition engine that reads 1D and 2D barcodes such as PDF417, QR Code and others. Barcodes can be used to perform document separation or as a source of metadata for documents.

Assigning Document Types and Metadata

Document types can be detected automatically by scripted rules or assigned manually by an operator. Index values (metadata) can be captured from the content of the document via a convenient point-and-click tool and assigned to each document according to its type.

Additional Functionalities

Scanned PDF files can be turned into searchable PDF and PDF/A documents by automatic injection of a text layer. PDF files that already contain searchable text (e.g., digitally born PDFs) can be moved to the destination as they are, or turned into PDF/A files with preserved bookmarks, attachments, metadata and the original image quality.
ABBYY Recognition Server produces PDF files of small size and high visual quality using sophisticated MRC compression technology. The optimal size/quality ratio of MRC-compressed PDFs is achieved by applying different compression methods to each individual layer of the created PDF file.
Built-in load balancing mechanisms ensure that the server utilizes all available hardware resources in the most efficient way. Queued tasks are dynamically distributed among processing stations and their CPUs for parallel processing. Additional load balancing tools are available to the administrator in the form of scheduling and priorities.
ABBYY Recognition Sever can be used as an independent standalone service, as well as an integral part of a larger business system. It offers diverse tools for integration including COM-based API, Web Service API, scripting and directive XML files (XML-Tickets).