Image analysis – Histogram processing – For setting a threshold
Patent
1986-10-29
1990-01-02
Boudreau, Leo H.
Image analysis
Histogram processing
For setting a threshold
382 25, 382 34, G06K 962
Patent
active
048917508
ABSTRACT:
An alphanumeric character is recognized by optically scanning that character, detecting the occurrence of predetermined geographical features in the scanned image, comparing the detected geographical features to a store of particlar geographical features which identify respective alphanumeric characters, and identifying the scanned image as the alphanumeric character having those geographical features to which the detected geographical features favorably compare. The aforementioned geographical features comprise lagoons (formed as enclosed areas) and bays (formed as open areas). A matrix representing the juxtapositions of the detected geographical features is generated and compared with stored predetermined matrices which, in turn, represent predetermined characters.
REFERENCES:
patent: 3541511 (1970-11-01), Genchi et al.
patent: 3605093 (1971-09-01), Parks et al.
patent: 3638188 (1972-01-01), Pincoffs et al.
patent: 3890596 (1975-06-01), Beun et al.
patent: 4193056 (1980-03-01), Morita et al.
patent: 4628532 (1986-12-01), Stone et al.
King-Sun Fu, "Synthetic Pattern Recognition" Chapter 4, Handbook of Pattern Recognition and Image Processing, Academic Press Inc., 1986, pp. 85-102.
Beun, "A Flexible Method for Automatic Reading of Handwritten Numerals", Philips Technical Review, vol. 33, 1973, No. 4, pp. 89-101.
Sakai et al., Extraction of Invarient Picture Sub-Structures by Computer, Computer Graphics and Image Processing, (1972), pp. 81-96.
Tour et al., "Recognition of Handwritten Characters by Topological Feature Extraction and Multilevel Categorization" IEEE Transactions on Computers, Jul. 1972, pp. 776-782.
Pastor Jose
Zemelman Evelina I.
Boudreau Leo H.
Pitchenik David E.
Pitney Bowes Inc.
Scolnick Melvin J.
Vrahotes Peter
LandOfFree
Optical character recognition by forming and detecting matrices does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Optical character recognition by forming and detecting matrices , we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Optical character recognition by forming and detecting matrices will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1387451