Image analysis – Histogram processing – For setting a threshold
Patent
1991-06-27
1993-08-17
Razavi, Michael T.
Image analysis
Histogram processing
For setting a threshold
382 25, 382 22, G06K 900
Patent
active
052376273
ABSTRACT:
Disclosed is a system of optical character recognition that first segments a page image into character images. A set of features is extracted and compared to proto-features from a template in order to classify a character, and convert it into a character code. This comparison is performed by comparing each feature of a character image to each proto-feature of each template to create a match rating list which is sorted in descending order. The top match rating and any close ratings are selected and output. To create the ratings, the angles and lengths of the features and proto-features are compared and then the result is normalized to a specific range of values.
REFERENCES:
patent: 4718102 (1988-01-01), Crane et al.
patent: 4764973 (1988-08-01), O'Hair
patent: 4860376 (1989-08-01), Tanaka et al.
patent: 4972499 (1990-11-01), Kurosawa
patent: 4987603 (1991-01-01), Ohnishi et al.
patent: 5034989 (1991-07-01), Loh
"Images to Outlines, Chain Link Coding and Segmentation for Raster Scan Devices", Cederberg, Computer Graphics and Image Processing, vol. 10, No. 3, 1979, pp. 224-234.
"Fast Polygonal Approximation of Digitized Curves", Gonzales and Sklansky, Pattern Recognition, vol. 12, 1981, pp. 327-331.
Johnson Dan S.
Seaman Mark D.
Couso Yon J.
Hewlett--Packard Company
Razavi Michael T.
LandOfFree
Noise tolerant optical character recognition system does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Noise tolerant optical character recognition system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Noise tolerant optical character recognition system will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2250767