Title :
Handwritten zip code recognition with multilayer networks
Author :
Le Cun, Y. ; Matan, O. ; Boser, B. ; Denker, J.S. ; Henderson, D. ; Howard, R.E. ; Hubbard, W. ; Jacket, L.D. ; Baird, H.S.
Author_Institution :
AT&T Bell Lab., Holmdel, NJ, USA
Abstract :
An application of back-propagation networks to handwritten zip code recognition is presented. Minimal preprocessing of the data is required, but the architecture of the network is highly constrained and specifically designed for the task. The input of the network consists of size-normalized images of isolated digits. The performance on zip code digits provided by the US Postal Service is 92% recognition, 1% substitution, and 7% rejects. Structured neural networks can be viewed as statistical methods with structure which bridge the gap between purely statistical and purely structural methods
Keywords :
mailing systems; neural nets; optical character recognition; US Postal Service; back-propagation networks; handwritten zip code recognition; isolated digits; multilayer networks; size-normalized images; statistical methods; structural neural networks; Computer networks; Data mining; Feature extraction; Handwriting recognition; Neural networks; Nonhomogeneous media; Pattern recognition; Postal services; Spatial databases; Testing;
Conference_Titel :
Pattern Recognition, 1990. Proceedings., 10th International Conference on
Conference_Location :
Atlantic City, NJ
Print_ISBN :
0-8186-2062-5
DOI :
10.1109/ICPR.1990.119325
