Multi-Digit Recognition Using a Space Displacement Neural Network

We present a feed-forward network architecture for recognizing an uncon(cid:173) strained handwritten multi-digit string. This is an extension of previous work on recognizing isolated digits. In this architecture a single digit rec(cid:173) ognizer 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.