Method and means for enhancing optical character recognition of printed documents

作者: Daniel P. Lopresti , Jonathan S. Sandberg

DOI:

关键词:

摘要: A document marker, including first values dependent upon the layout and contents of assigned by generating or preprocessing software, is provided in machine-readable symbology on face a printed version document. The marker may include encoded information sequences original text, text-dependent decimation sequences, error correction codes check-sums. Upon optical character recognition scanning, other digitizing reproduction, also scanned. scanning computer, having corresponding assigns second reproduced comparison line errors can be detected some corrected, thereby re-aligned candidate sequences. Optional provide further correcting capabilities, as applied to sequences; and, an optional check-sum utilized verify accuracy are correct.

参考文章(10)
Hamburgen Arthur, Error detection and correction system ,(1960)
Chin-Long Chen, Douglas Craig Bossen, My-Yue Hsiao, Method and apparatus for providing error correction to symbol level codes ,(1990)
Stephen Smith Treadwell, Error detection/correction system ,(1975)
D.P. Lopresti, J.S. Sandberg, Certifiable optical character recognition Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93). pp. 432- 435 ,(1993) , 10.1109/ICDAR.1993.395701
G Gaebelein, R Dorr, K Cash, Method and apparatus for reading documents ,(1972)
O Patent Div. Toshiba Corp. Nagumo, Tadashi C, O Patent Div. Toshiba Corp. Kojima, O Patent Div. Toshiba Corp. Inagawa, Jun C, Masahide C, Error correction circuit ,(1984)