Image analysis – Histogram processing – With pattern recognition or classification
Reexamination Certificate
1994-04-28
2001-07-03
Chang, Jon (Department: 2623)
Image analysis
Histogram processing
With pattern recognition or classification
C382S224000
Reexamination Certificate
active
06256408
ABSTRACT:
BACKGROUND OF THE INVENTION
The present invention is directed generally to optical character recognition, and more particularly, to automated methods and apparatus for reducing recognition errors, especially those resulting from an inability to distinguish between upper and lower case characters, or other characters of similar shape but dissimilar size or position.
Programmable computers and digital processing apparatus have proven useful for optical character recognition in which visual character indicia, such as printed text, are scanned, identified and assigned a character code value that can be stored electronically. A word processing “document” is one example of a data file containing character code values which a computer is able to interpret and reproduce in human-readable form on a CRT or as a printed document. There are many character code conventions in use today, the most common being the ASCII (American Standard Code for Information Interchange) code system.
Many existing optical character recognition systems make recognition errors between characters that are very similar in shape but are of different size or located at different positions. Upper and lowercase characters (S/s) and apostrophes and commas ('/,), for example, are prone to such errors. No matter how similar the shapes, their size or position is usually so different that this kind of error must be avoided.
Although some optical character recognition systems utilize information on size and position for discrimination, they still suffer from recognition errors, particularly when encountering the many kinds of electronic fonts currently in use. Thus, it would be desirable to provide a system that utilizes size and position information in a fashion that enhances the speed and recognition rate of optical character recognition.
SUMMARY OF THE INVENTION
In accordance with the foregoing objectives, an automated optical character recognition method of novel design is provided for use in conjunction with a programmable digital processing device. The method inputs a sequence of values representing one or more characters in an array of characters to be optically recognized. The input values define one or more dimensional characteristics of the characters. From the input values, a standard dimensional value is determined from a frequency distribution of a selected one of the character dimensional characteristics. For each of the input characters, a set of normalized values is determined from the standard dimensional value. The normalized values correspond to the one or more character dimensional characteristics. Optical character recognition is thereafter performed using the normalized values.
REFERENCES:
patent: 3781799 (1973-12-01), Robinson
patent: 3921136 (1975-11-01), Bar-Lev
patent: 4030068 (1977-06-01), Banz
patent: 4769851 (1988-09-01), Nishijima et al.
patent: 4860376 (1989-08-01), Tanka et al.
patent: 4897880 (1990-01-01), Wilber et al.
patent: 5060290 (1991-10-01), Kelly et al.
patent: 5138668 (1992-08-01), Abe
patent: 5253303 (1993-10-01), Nishijama et al.
patent: 5373566 (1994-12-01), Murdock
patent: 5396566 (1995-03-01), Bruce et al.
patent: 0 332 471 (1989-09-01), None
patent: 0 457 534 (1991-11-01), None
R.J. Baumgartner, “Upper/Lower Case Decision for Character Readers”, IBM Technical Disclosure Bulletin, vol. 14, No. 11 (Apr. 1972); pp. 3493-3494.
Casey Richard G.
Takahashi Hiroyasu
Baker Maxham Jester & Meador
Chang Jon
International Business Machines - Corporation
LandOfFree
Speed and recognition enhancement for OCR using normalized... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Speed and recognition enhancement for OCR using normalized..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speed and recognition enhancement for OCR using normalized... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2535458