Image analysis – Histogram processing – For setting a threshold
Patent
1990-05-07
1991-12-31
Moore, David K.
Image analysis
Histogram processing
For setting a threshold
382 9, 382 30, 382 34, G06K 900
Patent
active
050778056
ABSTRACT:
A feature-based character recognition identification and confidence level are determined for an unknown symbol. If the confidence level is within an intermediate range, the feature-based identification is confirmed by matching the unknown character with a reference template corresponding to the feature-based identification. If the confidence level is below the intermediate range, template matching character recognition is substituted in place of the feature-based identification. If the template matching recognition identifies more than one symbol, corresponding templates from a second set of templates having thicker character strokes are employed to resolve the ambiguity.
REFERENCES:
patent: 3165718 (1965-01-01), Fleisher
patent: 3382482 (1968-05-01), Greenly
patent: 3522586 (1970-08-01), Kiji et al.
patent: 4087790 (1978-05-01), Neff
patent: 4288781 (1981-08-01), Sellner et al.
patent: 4408342 (1983-10-01), Grabowski et al.
patent: 4441204 (1984-04-01), Hanna
patent: 4454610 (1984-06-01), Sziklai
patent: 4490850 (1984-12-01), Nally et al.
patent: 4523330 (1985-06-01), Cain
patent: 4545070 (1985-10-01), Miyagawa et al.
patent: 4654873 (1987-03-01), Fujisawa et al.
patent: 4710822 (1987-12-01), Matsunawa
patent: 4773099 (1988-09-01), Bokser
patent: 4817166 (1989-03-01), Gonzalez et al.
patent: 4833722 (1989-05-01), Morton et al.
patent: 4837842 (1989-06-01), Holt
Arndt Dennis R.
Couso Jose L.
Eastman Kodak Company
Moore David K.
LandOfFree
Hybrid feature-based and template matching optical character rec does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Hybrid feature-based and template matching optical character rec, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Hybrid feature-based and template matching optical character rec will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1515868