AI summary

This paper introduces a Space Displacement Neural Network (SDNN) architecture, coupled with a Viterbi algorithm, for recognizing unconstrained handwritten multi-digit strings using feature map segmentation rather than pixel space segmentation; it achieves 70% accuracy on a training set and 66% on a test set of 5-digit ZIP codes.

Abstract

We present a feed-forward network architecture for recognizing an unconstrained handwritten multi-digit string. This is an extension of previous work on recognizing isolated digits. In this architecture a single digit recognizer is replicated over the input. The output layer of the network is coupled to a Viterbi alignment module that chooses the best interpretation of the input. Training errors are propagated through the Viterbi module. The novelty in this procedure is that segmentation is done on the feature maps developed in the Space Displacement Neural Network (SDNN) rather than the input (pixel) space.