ABBYY FineReader Adds Support for Chinese, Japanese, Thai and Hebrew
New Recognition Language Support Renders ABBYY FineReader Accessible to the Widest International User Audience Ever
ABBYY, a leading provider of document recognition, data capture and linguistic software, today announced the newest release of its FineReader 9.0 optical character recognition (OCR) and document conversion application with added support for Chinese (both traditional and simplified), Japanese, Thai and Hebrew languages. ABBYY FineReader now recognizes a total of 184 languages and provides the broadest language support combining European, a range of Asian, African and Middle East languages in a single package.
“With the inclusion of support for these additional languages, ABBYY FineReader has now become available to nearly two billion more people from all over the world,” said Sergey Popov, director of the FineReader product department. “We are proud to offer our new customers a language-enriched product that delivers the traditionally high accuracy of ABBYY’s proprietary OCR technology, even with complex languages and writing systems.”
ABBYY FineReader 9.0 has been enhanced to accurately recognize both horizontal and vertical Chinese and Japanese script. Its user interface now includes intuitive options specifically adapted to handle and edit ideographic text (both horizontal and vertical). Its updated verification tool also allows users to easily verify recognized documents in Chinese and Japanese, with the ability to compare an uncertainly recognized character with its original image and to select the right character from a range of possible variants offered by the program. “Enabling recognition support for an ideographic language is a very challenging job for developers as it requires the creation of an enormous database of character patterns. For Chinese, we used millions of patterns to train FineReader to recognize tens of thousands of characters and their variants,” added Popov.
With its intelligent language detection algorithm, the program achieves exceptional results in recognizing multilingual documents with any combination of languages. It provides unmatched accuracy when processing documents with mixed ideographic and alphabetical languages (e.g. Chinese and English).
ABBYY FineReader 9.0 has been enhanced to process documents with “right-to-left” script and bi-directional text flow, such as those in Hebrew. Hebrew texts are written from right to left using the native characters, while numbers and foreign words are usually written in the opposite direction. ABBYY FineReader successfully performs OCR in both directions simultaneously within a single document and is on average 60 percent* more accurate processing Hebrew documents than competing OCR applications.
With this new release, ABBYY FineReader 9.0 also delivers powerful Thai OCR capabilities. “One of the main hurdles for Thai OCR is the multilevel structure of words and text lines,” explains Popov. “Text strings are composed of up to four levels of various character types and have no spaces between words. At present, ABBYY FineReader 9.0 is the only application in its class to provide professional-level Thai OCR.”
When processing Thai documents, the program detects individual characters and words, and separates text lines from each other to provide reliable recognition. ABBYY FineReader 9.0 also delivers dictionary support for Thai and Hebrew that helps to increase recognition accuracy even more. In addition to these language and technology enhancements, ABBYY FineReader 9.0 delivers a range of general improvements in product’s usability, including added Chinese interface language and faster application launch speed.
A comprehensive and easy-to-use OCR and document conversion application, ABBYY FineReader readily transforms scanned images, digital photographs of documents and PDF files into editable and searchable electronic files, providing a cost-effective and time-saving alternative to manual retyping. FineReader delivers precision accuracy in converting almost any type of documents, including books, magazine articles, tables and spreadsheets, contracts and faxes. With its breakthrough Adaptive Document Recognition Technology (ADRT™), ABBYY FineReader 9.0 is intelligent enough to recognize not just the text and basic layout, but the logical structure of a document and to automatically output editable files in native Microsoft® Office formatting. As a result, the headers and footers, page numbering, footnotes, line numbering, signatures, stamps, fonts and styles of the original are consistently retained across multiple pages.
ABBYY FineReader 9.0 with added Chinese, Japanese, Thai and Hebrew OCR support is available today through www.ABBYY.com and will be sold through ABBYY's worldwide distribution network. For more information, please contact your local ABBYY office or distributor.
Customers who purchased the previous release of ABBYY FineReader 9.0 will be able to upgrade their version free of charge from within the program interface (by using “Check for updates” option within the product) or through the ABBYY Web site. For more information about the product, visit http://www.abbyy.com/ or contact your local ABBYY office.
* Numbers quoted are based on internal ABBYY testing.