摘要 |
A method according to one embodiment includes performing optical character recognition (OCR) on an image of a first document; generating a list of hypotheses mapping the first document to a complementary document using: textual information from the first document, textual information from the complementary document, and predefined business rules; at least one of: correcting OCR errors in the first document, and normalizing data from the complementary document, using at least one of the textual information from the complementary document and the predefined business rules; determining a validity of the first document based on the hypotheses; and outputting an indication of the determined validity. Additional systems, methods and computer program products are also presented.
|