Writer adaptation for on-line handwritten character recognition.

N. Matic , I. Guyon, J. Denker, and V. Vapnik.
In Second International Conference on Pattern Recognition and Document Analysis , pages 187--191, Tsukuba, Japan, IEEE Computer Society Press.

We have designed a writer-adaptive character recognition system for on-line characters entered on a touch-terminal. It is based on a Time Delay Neural Network (TDNN) that is first trained on examples from many writers to recognize digits and uppercase letters. The TDNN without its last layer serves as a preprocessor to an Optimal Hyperplane classifier, that can be easily retrained to peculiar writing styles. This combination allows for fast writer dependent learning of new letters and symbols. The adaptation module is memory and speed efficient.

[ next paper ]