Globally Trained Handwritten Word Recognizer using Spatial Representation, Convolutional Neural Networks, and Hidden Markov Models

Part of Advances in Neural Information Processing Systems 6 (NIPS 1993)

Authors

Yoshua Bengio, Yann LeCun, Donnie Henderson

Abstract

We introduce a new approach for on-line recognition of handwrit(cid:173) ten words written in unconstrained mixed style. The preprocessor performs a word-level normalization by fitting a model of the word structure using the EM algorithm. Words are then coded into low resolution "annotated images" where each pixel contains informa(cid:173) tion about trajectory direction and curvature. The recognizer is a convolution network which can be spatially replicated. From the network output, a hidden Markov model produces word scores. The entire system is globally trained to minimize word-level errors.