The new version of the software development kit allows integrating text recognition, PDF conversion, and data capture into applications running in virtual and cloud environments, along with those running on premises

 ABBYY^®, a global provider of content intelligence services, today announced the launch of ABBYY FineReader Engine 12, a next-generation software development kit (SDK) that allows businesses to integrate text recognition, PDF conversion, and data capture functionalities into software applications running in the cloud, on premises or virtual machines.

FineReader Engine 12 is a powerful tool for software companies, system integrators, and enterprises to achieve new business goals. It enables businesses to broaden the spectrum of software applications and services they offer using modern cloud platforms like Amazon AWS and Microsoft Azure. Virtual environments, e.g. VMware Workstation and ESXi, Docker Containers and Oracle VM VirtualBox, are supported as well.

This version of the SDK also offers improved OCR of the Japanese language and introduces Farsi as a new recognition language. Its enhanced layout reconstruction is especially important for working with financial documents. The new classification module employs machine learning and natural language processing (NLP) in order to classify documents with precision, down to the smallest detail. These features, as well as the new output formats like PDF 2.0, PDF/UA, and HTML 5, will allow customers to increase the quality of their solutions or even offer new services and address new markets.

“ABBYY FineReader Engine 12 answers the growing demand for applications using OCR and data capture on virtual machines or in the cloud. This version of the SDK gives companies and organisations the freedom to build software that works best for their business goals and enter new markets by taking advantage of the advanced features and over 200 recognition languages,” comments Dr. Rainer Pausch, Senior Director of Global Product Marketing of SDKs at ABBYY.

The SDK provides applications with text recognition, PDF conversion, and data capture functionalities, for converting scans into searchable PDF, PDF/A, Word or Excel documents, and accessing data on photos, screenshots, industrial displays, or car instrument panels and infotainment systems. Using the toolkit, applications are able to convert TIFF libraries into PDF, PDF/A, Word or other formats and accurately extract field values.

ABBYY’s world-leading OCR technology sets the standard for quality and reliability. Powered by artificial intelligence, FineReader Engine 12 works with 208 languages, provides outstanding recognition accuracy even for multi-language documents and delivers searchable and editable digital copies that retain the original layout.

The SDK also significantly accelerates time-to-market as it offers easy integration, pre-configured tools, code samples and other components. This helps software companies to outperform the competition even in today’s fast-moving business environment.

 Availability and Supported Platforms

ABBYY FineReader Engine 12 for Windows is available worldwide immediately. The Linux and Mac versions will be released in June and July 2018 respectively. The SDK can be integrated into applications running on cloud platforms like Amazon AWS and Microsoft Azure. Virtual environments, e.g. VMware Workstation and ESXi, Docker Containers and Oracle VM VirtualBox, are supported as well.

For more information, please visit our website: https://www.abbyy.com/ocr-sdk/