Title :
Handwritten digit recognition: applications of neural network chips and automatic learning
Author :
Le Cun, Y. ; Jackel, L.D. ; Boser, B. ; Denker, J.S. ; Graf, H.P. ; Guyon, I. ; Henderson, D. ; Howard, R.E. ; Hubbard, W.
Author_Institution :
AT&T Bell Labs., Holmdel, NJ, USA
Abstract :
Two novel methods for achieving handwritten digit recognition are described. The first method is based on a neural network chip that performs line thinning and feature extraction using local template matching. The second method is implemented on a digital signal processor and makes extensive use of constrained automatic learning. Experimental results obtained using isolated handwritten digits taken from postal zip codes, a rather difficult data set, are reported and discussed.<>
Keywords :
digital signal processing chips; learning systems; neural nets; optical character recognition; automatic learning; character recognition; digital signal processor; feature extraction; handwritten digit recognition; line thinning; local template matching; neural network chips; pattern recognition; postal zip codes; Digital signal processors; Feature extraction; Handwriting recognition; Neural networks;
Journal_Title :
Communications Magazine, IEEE
