Image analysis – Editing – error checking – or correction – Correcting alphanumeric recognition errors
Patent
1997-01-13
1998-09-08
Mancuso, Joseph
Image analysis
Editing, error checking, or correction
Correcting alphanumeric recognition errors
382185, 382186, G06K 903
Patent
active
058057471
ABSTRACT:
In an optical character recognition (OCR) system an improved method and apparatus for recognizing the character and producing an indication of the confidence with which the character has been recognized. The system employs a plurality of different OCR devices each of which outputs a indicated (or recognized) character along with the individual devices own determination of how confident it is in the indication. The OCR system uses that data output from each of the different OCR devices along with other attributes of the indicated character such as the relative accuracy of the particular OCR device indicating the character to choose the select character recognized by the system and to produce a combined confidence indication of how confident the system is in its recognition.
REFERENCES:
patent: Re31692 (1984-10-01), Tyburski et al.
patent: 3764978 (1973-10-01), Tyburski et al.
patent: 3764980 (1973-10-01), Dansac et al.
patent: 3832682 (1974-08-01), Brok et al.
patent: 3876981 (1975-04-01), Welch
patent: 3895350 (1975-07-01), De Vries
patent: 3988715 (1976-10-01), Mullan et al.
patent: 4032887 (1977-06-01), Roberts
patent: 4180798 (1979-12-01), Komori et al.
patent: 4315246 (1982-02-01), Milford
patent: 4408342 (1983-10-01), Grabowski et al.
patent: 4876735 (1989-10-01), Martin et al.
patent: 5068664 (1991-11-01), Appriou et al.
patent: 5418864 (1995-05-01), Murdock et al.
patent: 5434932 (1995-07-01), Scott
patent: 5455872 (1995-10-01), Bradley
patent: 5459739 (1995-10-01), Handley et al.
Bradford et al., "Error Correlation in Contemporary OCR Devices," Proceedings, First Int'l. Conf. on Doc. Analysis and Recognition, St. Malo, France, 30 Sep.-2 Oct. 1991, pp. 516-524.
ScanWorX API Programmer's Guide, Version 2.0, (Jan. 04, 1993), pp. iii-ix and 1-1-1-29.
XDOC Data Format: Technical Specification, Version 2.0, (Jan. 04, 1993), pp. iii-vi, 1-1-1-2, 2-1-2-11, 3-1-3-3, 4-1-4-12, A-1-A-6, B-1-B-5, C-1-C-2, and I-1-I-7.
J.R. Ullman, "Pattern Recognition Techniques," Chapter 7, pp. 168-232 (1973).
Tsuji et al., "Character Image Segmentation," SPIE vol. 504 Applications of Digital Image Processing VII (1984), pp. 2-8.
Liang et al., "Segmentation of Touching Characters in Printed Document Recognition," IEEE Int'l. Conf. on Doc. Analysis and Recognition, pp. 569-572, Oct. 20-22, 1993.
Lu, "On the Segmentation of Touching Characters," IEEE Int'l. Conf. on Document Analysis and Recognition, pp. 440-443, Oct. 20-22, 1993.
Buchowski et al., "Omnirec: A Character Recognition System," pp. 1-61, Univ. of Texas at Austin, AI TR88-67, Feb. 1988.
Baird, "Feature Identification for Hybrid Structural/Statistical Pattern Classification," Computer Vision, Graphics and Image Processing 42, pp. 318-333 (1988).
Baird et al., "Components of an Omnifont Page Reader," IEEE Eighth Int'l. Conf. on Pattern Recognition, pp. 344-348, Paris, France, Oct. 27-31, 1986.
Impedovo et al., "Optical Character Recognition--A Survey," World Scientific Series in Computer Science, vol. 30 (1989), ed. PSP Wang, pp. 1-24.
Pavlidis et al., "Problems in the Recognition of Poorly Printed Text," Symposium on Document Analysis and Information Retrieval, pp. 162-173, Univ. of Nevada, Las Vegas, Mar. 16-18, 1992.
Rice et al., "The Third Annual Test of OCR Accuracy," 1994 UNLV/ISRI Annual Research Report, Univ. of Nevada, Las Vegas, Apr. 1994.
UNLV Information Science Research Institute, 1993 Annual Report, pp. 1-96 (Kevin O. Grover, ed., Information Science Research Institute).
Kimura et al., "An Integrated Character Recognition Algorithm," United States Postal Service, Advanced Technology Conference, vol. One, Nov. 5-7, 1990, pp. 605-619.
Gader et al., "Pipelined Systems for Recognition of Handwritten Digits in USPS Zip Codes," United State Postal Service, Advanced Technology Conference, vol. One, Nov. 5-7, 1990, pp. 539-548.
Matan et al., "Handwritten Character Recognition Using Neural Network Architectures," United States Postal Service, Advanced Technology Conference, vol. One, Nov. 5-7, 1990, pp. 1003-1011.
Hull et al., "A Blackboard-based Approach to Handwritten ZIP Code Recognition," United States Postal Service, Advanced Technology Conference, May 3-5, 1988, pp. 1018-1032.
Wagner et al., "The String-to-String Correction Problem," Journal of the Assoc. for Computing Machinery, vol. 21, No. 1, Jan. 1974, pp. 168-173.
Mancuso Joseph
Science Applications International Corporation
LandOfFree
Apparatus and method for OCR character and confidence determinat does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Apparatus and method for OCR character and confidence determinat, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Apparatus and method for OCR character and confidence determinat will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1291889