Image analysis – Learning systems
Patent
1994-11-15
1998-01-27
Johns, Andrew
Image analysis
Learning systems
382157, 364736, 395 24, G06K 962, G06F 738, G06F 1518
Patent
active
057129223
ABSTRACT:
A neural network based optical character recognition technique is presented for identifying characters in a moving web. Image acquisition means defines an imaging window through which the moving web passes such that the characters printed thereon can be imaged. Classification data is extracted and accumulated for each printed web character passing through the imaging window. A light source provides transmissive illumination of the web as it is being imaged. A neural network accelerator is coupled to the image acquisition means for intelligent processing of the accumulated classification data to produce therefrom printed character classification information indicative of each corresponding character imaged. A processor is coupled to the accelerator for converting the classification information into the appropriate ASCII character code. The technique is particularly useful for reading dot-matrix-type characters on a noisy, semi-transparent background at fast real-time rates. A neural network algorithm based recognition method is also described.
REFERENCES:
patent: H681 (1989-09-01), Weideman
patent: 4414685 (1983-11-01), Sternberg
patent: 4680805 (1987-07-01), Scott
patent: 4932065 (1990-06-01), Feldgajer
patent: 4974169 (1990-11-01), Engel
patent: 4994982 (1991-02-01), Duranton et al.
patent: 5014327 (1991-05-01), Potter et al.
patent: 5040229 (1991-08-01), Lee et al.
patent: 5048097 (1991-09-01), Gaborski et al.
patent: 5048100 (1991-09-01), Kuperstein
patent: 5052043 (1991-09-01), Gaborski
patent: 5054094 (1991-10-01), Barski
patent: 5060278 (1991-10-01), Fukumizu
patent: 5067164 (1991-11-01), Denker
patent: 5068799 (1991-11-01), Jarrett, Jr.
patent: 5105387 (1992-04-01), Childers et al.
patent: 5165009 (1992-11-01), Watnabe et al.
patent: 5194958 (1993-03-01), Pearman et al.
patent: 5204914 (1993-04-01), Mason et al.
patent: 5267185 (1993-11-01), Akabane et al.
patent: 5329630 (1994-07-01), Baldwin
patent: 5398300 (1995-03-01), Levey
patent: 5426745 (1995-06-01), Baji et al.
patent: 5434951 (1995-07-01), Kuwata
patent: 5465375 (1995-11-01), Thepaut et al.
patent: 5504838 (1996-04-01), Furuta et al.
patent: 5506915 (1996-04-01), Takstori et al.
patent: 5553196 (1996-09-01), Takatori et al.
J. Mody and C. Darken, "Learning with Localized Receptive Fields," Proceedings of the 1988 Connectionist Models Summer School, Jun. 1988.
Rumelhart, D.E. and McClelland, J.L., "Learning Internal Representations by Error Propagation," Parallel Distributed Processing: Explorations in the Microstructure ofCognition, I & II vol. I, 318-364, MIT Press, Cambridge, MA, 1986.
Hecht-Neilsen, R., "The Backpropagation Neural Network," Neurocomputing, 124-138, Addison-Wesley, Reading, MA, 1990.
Lippmann, R.P. "An Introduction to Computing with Neural Nets," IEEE ASSP Magazine, Apr. 1987.
R. Beale and T. Jackson, Neural Computing: An Introduction, Adam Hilger imprint by IOP Publishing, Ltd., pp. 7-74, 83-89, 219-221, (1990).
Gorman, C., "Putting Brainpower in a Box," TIME, p. 59, Aug. 3, 1988.
"Window on Silicon Valley," California Technology Stock Letter, pp. 10-15, Aug. 26, 1988.
Caudill, M., "Humanly Inspired," Unix Review, vol. 7 No. 5, 41-47, May 1989.
"A Neural Network Approach to Machine Vision Systems for Automated Industrial Inspection", Tai-Hoon Cho; International Joint Conference on Neural Networks, Jul. 8-12, 1991; pp. I-205-I-208.
Bryant Steven M.
Loewenthal Kenneth H.
Bailey, Sr. Clyde E.
Davis Monica S.
Eastman Kodak Company
Johns Andrew
Snee, III Charles E.
LandOfFree
Neural network optical character recognition system and method f 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 optical character recognition system and method f, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network optical character recognition system and method f will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-348320