ABBYY®, a leading provider of document recognition, document capture, and linguistic technologies and services, announced ABBYY FlexiCapture Engine 9.0, the next generation of the award-winning software development toolkit (SDK) for integrating data capture technology into third party applications. Key new functionality in version 9.0 includes support for mobile data capture (extraction of data from documents captured with mobile devices), enhanced document classification for automated pre-sorting and document routing, and processing via multi-threaded and 64-bit operating systems. The product also delivers enhancements in Optical Character Recognition (OCR) including support for new Asian languages. Developers will particularly benefit from a new extended API which enables greater access to core technologies and application customization.
ABBYY FlexiCapture Engine provides a comprehensive set of tools for rapidly developing intelligent solutions for automated processing of various types of forms and documents and extraction of key data for input into backend systems. It delivers powerful functions such as automated document classification and separation, template creation, and verification of output data that allows developers to create various custom and vertical solutions, as well as add value to their existing applications or processes.
"We've been impressed to discover the many different ways, including various industry and customer specific tasks, developers use our data capture SDK," said Andrey Isaev, director of the Technology Products Department at ABBYY. "With this latest release, we're giving developers deeper access to our core FlexiCapture technology and granting them even more freedom and flexibility for creating their own unique solutions."
The key new features of ABBYY FlexiCapture Engine 9.0 include:
Enhanced API for Access to the Core Technology
The Engine's new, enhanced API provides developers with direct access to FlexiCapture technology, allowing them to fine-tune the technology to suit a particular task in the most optimal way and ensure better performance of the whole system. With the new API, developers are no longer bound to the project and batch oriented processing. It is now possible to set up custom image sources (e.g. from memory) and to store the processing settings and interim data within the end-user application.
Support for Multi-Threaded Server Processing
ABBYY FlexiCapture Engine 9.0 delivers support for multi-threaded processing on a server, using its CPU to the full capacity. The product now supports both 32- and 64-bit operating systems. When processing multipage forms and documents on multi-core servers, FlexiCapture Engine 9.0 provides an up to 90 percent* increase in processing speed with each additional CPU core.
New Scenario: Mobile Data Capture
Version 9.0 offers enhanced recognition functionality to accurately capture data from photographs taken with camera phones. Combined with the powerful server processing, this enhancement makes FlexiCapture Engine an ideal tool to create B2B and B2C mobile data capture applications. Companies working in the mass market, including industries like finance, insurance and healthcare, will benefit from the new opportunities for service improvement, lead generation, and internal communications now available with an easy-to-use mobile data capture front-end.
Chinese, Japanese, Korean and Vietnamese OCR
In addition to Thai and Indonesian languages introduced in the previous version, ABBYY FlexiCapture Engine 9.0 reads forms and documents in a variety of Asian languages including newly added Chinese (both simplified and traditional), Japanese, Korean, and Vietnamese. Combined with the support of almost two hundred other languages, this provides a considerable advantage for developing applications and services for the global market.
New Multi-Level Document Classifier
The new Classifier allows developers to assign a Classification Tree with multiple logical levels (classes) and, therefore, speed up the overall processing of documents in a stream. It can identify individual pages and multipage documents, even without using separation sheets or barcodes. Additionally, the documents are classified by type — e.g. contract, invoice or reclamation.
Redaction of Sensitive Data
With the "redact" functionality built in, the technology can be used to "hide" sensitive information in documents by redacting required data fields on the document images before exporting. For each export location, developers can specify a different set of fields for automated redaction.
PDF Export with MRC Compression
The product supports Mixed Raster Content (MRC) Compression technology that enables users to considerably reduce the output PDF and PDF/A files while preserving the original visual quality. The Engine's MRC reduces output files up to 10 times as compared to JPEG compression.
Updated Developer's Documentation and Code Samples Library
FlexiCapture Engine 9.0 comes with a rich set of code samples to illustrate various aspects of programming with the FlexiCapture Engine. Each library section contains code snippets along with intuitive, step-by-step guidelines for developers.
ABBYY FlexiCapture Engine 9.0 is available immediately worldwide via a flexible, modular licensing policy. Developers may select the best combination of tools and pricing options for their projects. For information on licensing models and pricing, contact your local ABBYY office or ABBYY partner. For more information about the product, visit www.abbyy.com/flexicapture_engine.
* based on ABBYY's internal testing
ABBYY is a leading provider of document recognition, data capture, and linguistic technologies and services. Its products include the ABBYY FineReader line of optical character recognition (OCR) applications, ABBYY FlexiCapture line of data capture solutions, ABBYY Lingvo dictionary software, and development tools. ABBYY is headquartered in Moscow, Russia, with offices in Germany, the United States, Ukraine, the UK, Cyprus, Japan and Taiwan. For more information, visit www.ABBYY.com.