Back to Newsroom

ABBYY Announces FineReader Engine 8.0 with Extended Platform Support

September 19, 2006

FineReader Engine 8.0 SDK has been extended with a new version designed specifically for developers working with Linux, FreeBSD® and the Mac OS X (Intel) platforms.

Award-Winning Document Recognition Technology Enhanced for Developers Working with Linux®, FreeBSD®, and Mac OS® X (Intel®)

ABBYY, a world leader in the development of document recognition, data capture and linguistic technologies, today announced that it has extended its FineReader Engine 8.0 Software Development Kit (SDK) with a new version designed specifically for developers working with Linux, FreeBSD® and the Mac OS X (Intel) platforms. With the release of the SDK, ABBYY’s powerful document recognition and PDF conversion technologies are available to a wider audience than ever before.

“Today’s developers have a variety of powerful options to choose from when developing their applications,” said Alexander Rylov, ABBYY Chief Product Manager. “FineReader Engine 8.0 is a powerful recognition and conversion platform with a variety of specialized functions for creation of searchable PDF files for archiving, processing of digital camera images, capture of field and zone data, and recognition of barcodes. With this new version, developers working with Linux or BSD platforms can now take advantage of this functionality.”

Powerful Document Recognition, PDF Conversion, and Barcode Recognition

ABBYY FineReader Engine provides an efficient and flexible way to integrate OCR, barcode recognition and PDF conversion technologies into a wide variety of applications including: archiving and storage, content/document management, control and verification, document conversion and data capture. By converting scanned documents or PDF files into editable and searchable file formats, it enables document searching, republishing, and information capture for input into databases.

ABBYY FineReader Engine provides crucial key benefits that include:

Superior Accuracy with Advanced Document Analysis – Based on ABBYY’s latest recognition and document analysis technology, this new SDK is by far the most accurate OCR engine ever developed for the Linux platform. Version 8.0 delivers a 30% boost in accuracy compared with previous versions from ABBYY, and is over 60% more accurate then other OCR SDKs commercially available for the Linux*. In addition, this SDK includes advanced document analysis capabilities specifically optimized for different recognition tasks, such as invoice pre-processing and full-text indexing. Users can choose different document analysis algorithms for each particular task.

Advanced PDF Conversion – The SDK offers powerful PDF conversion features such as: support for all types of PDF files including «text and image», «text over image», «text under image», and «image only»; extraction and re-creation of internal links and hyperlinks; advanced PDF security setting and encryption support; output in tagged PDF format; and the ability to add document metadata to PDF outputs.

Multilingual and Multifont Support – FineReader technology recognizes up to 189 OCR languages (more than any other existing OCR software), including Chinese, Japanese and Korean languages. In addition, it supports a broad array of fonts, including dot matrix print texts, old European fonts (such as Fraktur) and most Gothic fonts, as well as specialized fonts used by the finance industry, such as OCR-A, OCR-B, and MICR (E13B).

Multiplatform Support – ABBYY FineReader Engine 8.0 with Extended Platform Support has been tested to work with operating environments from leading vendors including RedHat® Linux, Fedora™ Core, SUSE® Linux Enterprise, FreeBSD, and Mac OS X (Intel). In addition, ABBYY’s technical team offers special services for porting FineReader technology to other platforms.

Flexible Architecture and Licensing Scheme – The FineReader technology can be used to build applications of any scale and complexity – from simple client applications to server-based, distributed projects. The flexible, modular architecture and pricing model allow developers to choose only functions and features they need, while maintaining the ability to extend the current functionally of applications as needed.

What’s New in FineReader Engine 8.0 with Extended Platform Support**

ABBYY FineReader Engine first supported development on the Linux platform in 2003. Since then, ABBYY development teams have been working with a variety of companies and developers working on various platforms to offer the best combination of functionality and platform support. In addition, the SDK offers the following enhancements:

  • Image pre-processing. FineReader Engine 8.0 delivers enhancements in image pre-processing technologies for higher accuracy, especially on documents that are typically difficult to read such as newsprint, magazine pages, faxes, copies and text printed on color or textured background. Pre-processing technologies include adaptive binarization and background filtering and image pre-processing for digital camera images, which corrects specific image distortions which are typically associated with digital photographs.
  • Multilevel document analysis and special document analysis modes. To meet the demands of indexing and archiving solutions, ABBYY FineReader Engine 8.0 supports special document-oriented processing modes to analyze and extract data from documents during document processing tasks such as document conversion, full-text indexing and invoice pre-processing.
  • Barcode recognition. The SDK provides the ability to quickly find and extract barcodes at any angle. It supports more than 18 1D and 2D PDF 417 barcodes.
  • Field level/zonal recognition. FineReader 8.0 Engine offers powerful recognition at the field or “zone” level. By recognizing key information from snippets of text, this feature enables processing tasks like keyword indexing and keyword classification. Field Level capabilities support multilingual and barcode recognition, as well as advanced functionality including definition of field content, detection of in-filed spacing, processing of blocks with intersecting parts and lines, recognition of text words and symbols completely located within block borders, and text block despeckle. Recognition tuning allows developers to influence the recognition ranking criteria.
  • Enhanced PDF conversion. ABBYY FineReader 8.0 Engine provides superior accuracy on PDF files created by scans (Image PDFs) and PDFs with special encoding through the use of two-step “intelligent PDF processing”. This process determines the appropriate method for extracting PDF text data and either pulls information from the text layer or performs recognition on the image itself. Additional PDF conversion capabilities include replication of internal PDF links and hyperlinks and security setting compliance. Adobe® PDF Library technology further ensures high recognition rates.
  • Enhanced PDF output. The new PDF output options include: support for PDF security and encryption settings, output in Tagged PDF format, and the addition of PDF file metadata.
  • Variety of output and export formats. In addition to PDF and searchable PDF, FineReader technology supports output of recognized texts in a variety of formats including: RTF, TXT, HTML, XML, and XLS. Key formatting such as bullet points and special picture shapes, as well as general formatting, can be preserved in output documents, In addition, developers can also choose to retain character information (detailed information about formatting, word/character varieties, etc. via API and XML output). Document-related properties can be set in key document output formats.
  • Throughput management. FineReader Engine 8.0 allows integrators to achieve optimal recognition accuracy and processing speed for their applications. The balance processing mode and «ready-to-load profiles» reduce time spent choosing proper parameters for common usage scenarios (e.g. conversion to searchable PDF, field-level recognition, archiving, and indexing).

Specifications, Availability and Pricing

ABBYY FineReader Engine 8.0 consists of a set of libraries that makes the core OCR functionality easily accessible for developers via an API or the Command Line Interface. The SDK is sold in Developer Licenses and Run Time Licenses, with special Add-on modules for certain functionality. A special time-limited trial version is also available for test. The full product is scheduled to be available in the fourth quarter of 2006. Information on licensing models, pricing, and other technical information is available from your local ABBYY office. For additional product and sales information, please visit

* According to internal tests.
** The functionality varies a little depending on the operating system. For details, contact your local ABBYY office.

Connect with us