| |
A2iA (Artificial Intelligence and Image Analysis), the worldwide leading developer of tools for document analysis and handwritten data extraction, announced that it excelled in the 2010 Open Handwriting Recognition and Translation Pilot Evaluation (OpenHaRT 2010). An evaluation of transcription and word recognition technologies for document images containing primarily Arabic script, OpenHaRT is an international evaluation organized by The National Institute of Standards and Technology (NIST), an agency within the U.S. Department of Commerce.
Working with image samples written by native Arabic scribes, A2iA submitted the recognition results of a prototype system that included the latest advanced technology developed in its research lab, one of the largest in the world focused on automatic document processing with a specialization in handwritten and unstructured data. Complete pilot evaluation results are available on the NIST results page.
“A2iA’s research and development team continues to prove it is among the best in the world,” said Jean-Louis Fages, A2iA President & Chairman of the Board. “We have always been a company focused on the core technology of our products, and our successes in the lab reiterate our organization’s dedication to the advancement and improvement of our proprietary toolkits.”
About A2iA
A2iA, Artificial Intelligence and Image Analysis (a2ia.com), is the worldwide leading developer of handwritten and machine printed text recognition, information extraction and intelligent document classification toolkits. By enhancing solutions from systems integrators and independent software vendors, A2iA allows complex and cursive data from all types of forms, documents and checks, including unstructured handwritten letters, to become part of a structured database, making it searchable and reportable, with the same level of flexibility as printed or digital data. The company’s proprietary OCR, ICR and IWR toolkits improve business process automation with a visible ROI, and are available in 23-country versions and 6-languages.
|
