New ABBYY FineReader 7.0 Continues to Set the Standard in Recognition Accuracy with 25 Percent Improvement
Moscow, Russia, September 02, 2003 - ABBYY Software House, the leader in document recognition and linguistic technologies, today announced the global availability of FineReader® 7.0 Corporate Edition. Packed with robust networking features, FineReader 7.0 Corporate Edition is geared toward corporations in networked environments that need to convert and repurpose a wide variety of paper documents and PDF files. This version of ABBYY's popular optical character recognition (OCR) application improves the process of converting paper documents into electronic ones by adding an average of 25 percent increased recognition accuracy over the previous version. As an OCR and document conversion application, FineReader 7.0 works to solve the problem of unlocking previously static documents, like hardcopy word processed documents or spreadsheets and PDF files, in order to convert these files into dynamic documents that can be repurposed for editing, updating, revising and archiving.
"As a starting point for workgroup collaboration, FineReader 7.0 allows the corporate community to edit, update, route, and essentially, revive otherwise static documents," said Sergey Andreyev, CEO of ABBYY Software House. "With FineReader 7.0 Corporate Edition, ABBYY continues to raise the bar in document conversion accuracy, thus further expanding the benefits of increased productivity and lowered costs of document conversion to the corporate environment."
FineReader 7.0 continues to help businesses in need of achieving greater productivity by introducing robust network capabilities on top of all the functionality in FineReader 7.0 Professional Edition, which delivers improved word accuracy and format retention, PDF conversion and XML output.
Robust Network Features for Networked Environments:
Many of the capabilities in FineReader 7.0 Corporate Edition are specific to networked environments and are designed to help businesses efficiently process OCR projects more quickly and easily. These new network features include:
FineReader 7.0 also includes the following features:
Improved Recognition Accuracy
FineReader 7.0 delivers an enhancement of an average of 25 percent accuracy improvement over the previous version through the incorporation of new algorithms and classifiers in the overall technology, adaptive binarization, and background removal. FineReader 7.0's recognition accuracy performs particularly well with text on colored or textured backgrounds.
English and German Legal and Medical Dictionaries. Specialized English and German dictionaries that include the most frequently used legal and medical terminology have been added for improved recognition of legal and medical text.
When converting PDF files, FineReader 7.0 delivers a significant increase in accuracy of an average of 45 percent through a process by which the underlaid text is extracted from the PDF files prior to recognition. In addition, FineReader also enhanced its PDF output capabilities and quality, making the program a true document conversion solution.
Linearized PDF. All PDF documents created by FineReader are now linearized, which is optimal for Web publishing. The PDF files are structured in a way that allows the first page of the PDF file to be displayed in a user's Web browser before the entire file is downloaded.
Edited PDF. Users can edit recognized PDF files (as well as all recognized files before saving to PDF) in the FineReader edit window. With this feature, users will be able to open an existing PDF document in FineReader, make changes, and save it back into any number of PDF formats.
FineReader supports output in any of the four standard PDF file formats (text and pictures only, text over image, text under image, and image only) with additional controls such as whether or not to replace suspect words with images. This gives users six PDF saving options - more PDF formats than any other OCR software.
In addition, FineReader 7.0 is the only OCR program that is able to create text over image PDF files, essentially eliminating the pixilated text outcome that often results without this capability. In order to preserve text and font characteristics, FineReader 7.0 first "paints" the original image, and then carefully layers the recognized text over the image, requiring flawless layout retention in the OCR program. The resulting document will have impeccable layout retention and crisp text, making it ideal for printing, web publishing and archiving.
Improved Layout Retention
FineReader 7.0 provides improved retention of documents with complex layouts, including tables without printed grid lines, tables with colored cells, and documents with bullets, separators and tables. Retention of complex formatting elements in HTML has also been improved.
FineReader 7.0 allows users to export recognized document as native XML using Microsoft® Word 2003 defined schema, a widely anticipated emerging standard for file use. This allows users to take advantage of the Word XML file format which can be manipulated and searched using any program that can process industry standard XML. In addition, it provides the basis for data reporting, publishing and submitting data to business processes.
Improved Integration with Microsoft® Office Applications
Hyper-Threading Technology Support
When running FineReader 7.0 on computers with Hyper-Threading Technology in background mode, the program will launch as many processes as there are virtual processors, which increases the speed of operation. This technology can greatly increase productivity when recognizing large numbers of documents.
Distributed Document Processing
Businesses with multiple licenses and multiple workstations can share OCR processes allowing multiple users on the network to scan, recognize, and proofread the same batch of documents simultaneously - essentially creating an OCR production line. To support the needs of a busy office environment, FineReader Corporate Edition takes advantage of additional processors on multiprocessor PCs. The multiprocessing support increases the recognition speed in direct proportion to the number of processors installed. In addition, businesses working with FineReader also benefit from the ability to share custom languages and dictionaries across a network simultaneously.
Shared Languages and Dictionaries.
ABBYY FineReader 7.0 Corporate Edition allows multiple users to simultaneously access the same set of user languages and dictionaries available on the network. In addition, Corporate Edition enables users to add words like names, acronyms, and industry lingo to shared dictionaries. The added words help expand the spell check capabilities and also increase the recognition quality, since FineReader uses the dictionaries during the OCR process.
When scanning a two-sided document using a duplex scanner, FineReader 7.0 automatically provides separate images for each side of the document.
FineReader 7.0 Corporate Edition supports Intel® Pentium®, Celeron®, and Xeon™, and AMD K6, Athlon™, Duron™, or compatible 200MHz or higher processor. Microsoft® Windows XP, Windows 2000, Windows NT® 4.0 with Service Pack 6 or later, Windows ME/98 operating systems. The software requires 64 MB of RAM for Windows XP/2000/NT 4.0, 32 MB of RAM for Windows ME/98, plus 16 MB of RAM for each additional processor, and 220 MB of hard-disk space for typical installation and program operation. Additional hardware requirements include TWAIN-compliant scanner, digital camera, fax-modem (optional). Super VGA (800x600) or higher-resolution video adapter and monitor. Product requires activation by the user via Internet or e-mail. For information about ABBYY activation procedures and policies, please visit www.abbyy.com/activation.
ABBYY FineReader 7.0 Corporate Edition is available now from select retail stores, resellers, and online outlets. A free 15-day Try&Buy software version of ABBYY FineReader 7.0 Professional Edition will be available for download at the http://www.abbyy.com/ Web site. For additional information on resellers carrying FineReader 7.0 Corporate Edition, visit the http://www.abbyy.com/.
ABBYY Software House is a leading Russian developer of linguistic and Artificial Intelligence (AI) software providing a line of OCR and text-processing programs and solutions. ABBYY's products include: FineReader OCR systems - a family of programs for recognition of printed texts, tables and PDFs; FormReader - an ICR program for recognition and processing of hand-printed forms; FineReader Bank - a program for automated input of bank payment orders; ABBYY Retrieval & Morphology Engine - a set of developer's tools for integration of full-text search and linguistic capabilities into external applications; and ABBYY Lingvo - a powerful dictionary system. ABBYY's programs have gained universal acclaim and become popular with the users worldwide for their excellent performance and ease of use. ABBYY FineReader OCR systems have won more than 100 awards from the leading IT magazines. The ABBYY Group's headquarters are located in Moscow with offices in Ukraine (ABBYY Ukraine), the USA (ABBYY USA, Fremont, CA), the UK (ABBYY UK, Bishops Stortford, England), and Germany (ABBYY Europe, Munich).
For more information about ABBYY, please visit the company's website at http://www.abbyy.com/
ABBYY and FineReader names and logos are registered trademarks of ABBYY Software House. Other product names mentioned herein may be trademarks and/or registered trademarks of their respective companies and are hereby recognized.
Press contacts you may find at this page.