Neural network for character recognition and verification

Image analysis – Learning systems – Neural networks

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

382309, G06K 962

Patent

active

057427020

ABSTRACT:
A neural network is used to recognize characters from a character set. Based upon the character recognized, a smaller neural network is used for verification of the character recognized. The smaller neural network is trained to recognize only a single character of the set and provides a "yes" or "no" type verification of correct identification of the character.

REFERENCES:
patent: 3050711 (1962-08-01), Harmon
patent: 3701098 (1972-10-01), Acker
patent: 3967243 (1976-06-01), Kawa
patent: 4040009 (1977-08-01), Kadota et al.
patent: 4267573 (1981-05-01), Chaikin et al.
patent: 4395699 (1983-07-01), Sternberg
patent: 4491960 (1985-01-01), Brown
patent: 4748676 (1988-05-01), Miyagawa et al.
patent: 4893346 (1990-01-01), Bishop
patent: 4922543 (1990-05-01), Ahlbom et al.
patent: 4933872 (1990-06-01), Vandenberg et al.
patent: 4965725 (1990-10-01), Rutenberg
patent: 4970819 (1990-11-01), Mayhak
patent: 4972499 (1990-11-01), Kurosawa
patent: 5046020 (1991-09-01), Filkin
patent: 5048097 (1991-09-01), Gaborski et al.
patent: 5052043 (1991-09-01), Gaborski
patent: 5054094 (1991-10-01), Barski
patent: 5060276 (1991-10-01), Morris et al.
patent: 5060278 (1991-10-01), Fukumizu
patent: 5067164 (1991-11-01), Denker et al.
patent: 5077805 (1991-12-01), Tan
patent: 5091965 (1992-02-01), Kobayashi et al.
patent: 5093899 (1992-03-01), Hiraiwa
patent: 5105468 (1992-04-01), Guyon et al.
patent: 5119438 (1992-06-01), Ueda et al.
patent: 5129039 (1992-07-01), Hiraiwa
patent: 5146512 (1992-09-01), Weideman et al.
patent: 5157738 (1992-10-01), Carpenter et al.
patent: 5161204 (1992-11-01), Hutcheson et al.
patent: 5214746 (1993-05-01), Fogel et al.
1990 Int'l. Conf. on Acoustics Speech & Signal Processing, vol. 4, pp. 2125-2128, "Chinese Char. Regog. w/Neural Nets Class.", Jeng et al.
Int'l Conf. on Pattern Recognition, pp. 35-40, Jun. 16-21/90, "Handwritten Zip Code Recog. w/Multilayer Networks ", Cun et al.
2nd Int'l. Conf. on Artificial Neural Networks, pp. 214-218, 18-20/ Nov. /91, Segmentation & Recog. of Calligraphic Text, Bruyne et al.
IEEE Int'l. Conf. on Neural Nets, pp. 125-132, vol. 1, 24-27/Jul./88, "Invariant Pattern Recog. by Means of Fast Synap. Plast,", Buhmann.
IEEE Int'l. Conf. on Neural Nets, pp. 625-632, vol. 1,24-27/Jul./88, "Dist. Invar. Char. Recog. by Multi-Layer Per.", Khotanzad et al.
Cognex Corp., Board-Level Machine Vision Systems, 2000/3000/4000 Technical Descript., 1990, USA.
IJCNN-Int'l. Joint Conf. on Neural Nets, 17-21/Jun./90, pp. 733-738, "Adaptive Input Field Neural Network", M. Asogawa.
Dr. Dobb's Journal, pp. 139-143, "Graphics Programming--Fast Antialiasing", Jun. 1992. Abrash.
Hakim et al. "Cursive Script Ouline Character Recognition with a Recurrent Neural Network Model." IJCNN, vol. 3, Jun. 1992, pp. 711-716.
Cho et al., "Hierarchically Structured Neural Networks for Printed Haugul Character Recognition." Int. Joint Conf. Neural Net., vol. 1, pp. 265-270, Jun. 1990.
Hirai et al. "Position Independent Neuro Pattern Matching and its Application to Handwritten Numerical Character Recognition." Int. Joint Conf. Neural Net. vol. 3, pp. 695-701, Jun. 1990.
Kertesz "Dynamically Connected Neural Network for Character Recognition", Jun. 1992, IEEE IJCNN 676-676.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Neural network for character recognition and verification does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Neural network for character recognition and verification, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network for character recognition and verification will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-2066555

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.