Handwritten zip code recognition with multilayer networks
Yann LeCun, O. Matan, Bernhard E. Boser et al. · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · 2002
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.>
Cited by 198 works. doi:10.1109/icpr.1990.119325
Authors
- Yann LeCun
- O. Matan
- Bernhard E. Boser
- John S. Denker
- D. Henderson
- Richard E. Howard
- W. Hubbard
- L.D. Jacket
- Henry S. Baird
References
- Sn: A simulator for connectionist models
- Advances in Neural Information Processing Systems 37
- Learning Internal Representations by Error Propagation
- Generalization and network design strategies
- Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position
- A framework for object recognition in a visually complex environment and its application to locating address blocks on mail pieces
- Neural Network Recognizer for Hand-Written Zip Code Digits
- Connectionism in Perspective
- Learning Process in an Asymmetric Threshold Network
- Handwritten digit recognition: applications of neural network chips and automatic learning