Neural Network Recognizer for Hand-Written Zip Code Digits
John S. Denker, William R. Gardner, Hans Peter Graf et al. · 1988
This paper describes the construction of a system that recognizes hand-printed digits, using a combination of classical techniques and neural-net methods. The system has been trained and tested on real-world data, derived from zip codes seen on actual U.S. Mail. The system rejects a small percentage of the examples as unclassifiable, and achieves a very low error rate on the remaining examples. The system compares favorably with other state-of-the art recognizers. While some of the methods are specific to this task, it is hoped that many of the techniques will be applicable to a wide range of recognition tasks.
Cited by 141 works.
Authors
- John S. Denker
- William R. Gardner
- Hans Peter Graf
- D. Henderson
- Richard E. Howard
- W. Hubbard
- L. D. Jackel
- Henry S. Baird
- Isabelle Guyon
References
- Pattern classification and scene analysis
- Receptive fields, binocular interaction and functional architecture in the cat's visual cortex
- A framework for object recognition in a visually complex environment and its application to locating address blocks on mail pieces
- Algorithms for Graphics and Image Processing
- On the Recognition of Printed Characters of Any Font and Size
- Automatic recognition of handprinted characters—The state of the art
- Moment Normalization of Handprinted Characters
- Algorithms for Graphics and Imag
- Pattern Recognition: Human and Mechanical
- SPTA: A proposed algorithm for thinning binary patterns