Johansson, O. (1989). An Experiment with a Neural Network for Handwritten Character Recognition. Technical Report LiTH-IDA-R-89-44, Department of Computer and Information Science, Linköping University, Sweden. (bibtex),
Abstract: This report shows some promising results in using neural networks for hand- written character recognition in real-time. The characters were input from a digitizer and preprocessed to extract different features. These were taken as input to a backpropagation network which was trained to recognize the 29 lowercase letters in the Swedish alphabet. Its configuration was 40 input nodes, 30 hidden nodes and 29 output nodes. It was trained with 4 different versions of each character in 15 000 iterations. After that it was able to recognize 100 percent of two other separately entered versions of the alphabet. The amount of computation needed for classifying a character with this kind of networks puts no restrictions on real-time performance.
CS Dept TR Overview