Award-winning and driven by research and development, A2iA, Artificial Intelligence and Image Analysis, is recognized as the worldwide leading developer of handwritten and machine printed text recognition, information extraction and intelligent document classification. By operating the world’s largest research center dedicated to extracting information from everyday paper documents, A2iA has been proactive in its developments to meet the needs of the market place, and producing a visible ROI for its users for more than 25 years.
The digitization of these archives has been identified as a necessity to preserve their integrity and overcome the scarcity of space, as well as to make them available for public view once specific information has been removed, or declassified. But how can the content of these records be accessed once they are imaged? How can specific information be found quickly, and intelligence gained, once in digital format?
Difficult documents to automate. While ordinary documents today can be classified and indexed with relative ease, automating this process with hundred-year-old images in old-fashioned writing styles can be quite complex. These archives have characteristics that make them challenging to work with, and make them unsuitable for existing document management solutions: