Handwritten Character Recognition Using

We have developeda neural-network architecture for recognizing handwritten digits. This network has 1% error rate with about 7% reject rate on handwritten zipcode digits provided by the U.S. Postal Service. In this paper, we discussimplementing this architecture in a real-world character recogmtion system. The main issue is the trade- off between cost and benefits such as accuracy and speed. A method for combiningindependentlytrained networks to achievehigher per- formance at relatively low cost is presented. Accurate estimatesof the probability of correct recognition, aswell as runner-upprobabilities, are of ever-increasing importanceasrecog- nition systems move out of the lab into the real world. Per-character probabilitiesgiveus the information necessary for calculatingper-field or multi-field probabilities. Wediscussa methodfor normalizingout- put activations levels,thus providing a normalizedscore,which (for our network at least) is a good estimate of the probability. We also find that using this normalizedscoreas a rejection thresholdgivessimilar performance to previous rejection schemes. We also discussthe important and complex relationship between rejection threshold, averagenumber of errors, and the cost of errors.