Xerox Corporation

Eric H Kuo

Daniel H Greene

Leslie T Niles

A system encodes a separate assist channel that carries only a small amount of additional information in a hardcopy document to compensate for failure of an OCR system to accurately reconstruct a scanned electronic version of the hardcopy document. The assist channel is encoded by mapping data from a primary channel of the document into a plurality of groups. The plurality of groups is used to classify the symbols of the primary channel by the likelihood that a character will occur and the likelihood that the symbols of the primary channel will be confused during OCR processing.

Assist channel coding with character classifications

A system encodes a separate assist channel that carries only a small amount of additional information in a hardcopy document to compensate for failure of an OCR system to accurately reconstruct a scanned electronic version of the hardcopy document. The assist channel protects symbols printed on the hardcopy document by computing Reed-Solomon error correcting codes for vertical columns of symbols. Decoding is synchronized along a line of text at each symbol block. When an error correcting code corrects an error produced during OCR processing, the remainder of the line containing the error is revised.

Growing community of inventors

Cambridge, MA, United States of America

Eric H Kuo