AI summary

This paper introduces a neural network system for recognizing hand-printed digits using classical and neural-net techniques on real-world U.S. Mail zip code data, achieving low error rates and comparing favorably to state-of-the-art recognizers, using a combination of a custom analog neural network VLSI chip, skeletonization, feature maps, and classifiers (Parzen Windows, K-Nearest Neighbors, and layered networks).

Abstract

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 zipcodes 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.