O - line Digit Recognition with Time Delay

Automatic computer recognition of arbitrary handwritten characters remains as one of the more elusive targets for computer researchers. Methods incorporating knowledge of time-sequencing of data point inputs have achieved some success, but are not generally applicable to real-world applications where such time-dependency information is often not available. Using a simple algorithm for synthesizing time-dependent data progression, a method for identifying arbitrary handwritten numeric characters from bit-mapped data inputs with a neural network is proposed. Preliminary results using both a Time-Delay Neural Network (TDNN) and a Feed Forward Backprop Network indicate the temporal synthesis technique contributes signiicantly to producing an eecient numerical character recognizer.