A new distance measure for online character recognition

In online character recognition one can observe two kinds of intra-class variations: small geometric deformations and completely different writing styles. We propose a new approach to deal with these problems by defining an extension of tangent distance, well known in off-line character recognition. The system has been implemented with a k-nearest neighbor classifier and a so called diabolo classifier respectively. Both classifiers are invariant under transformations like rotation, scale or slope and can deal with variations in stroke order and writing direction. We have obtained error rates of about 1% on our digit database with more than 200 writers at a recognition speed of more than 100 characters per second