On-line Recognition of Handwritten Mathematical Symbols

This paper presents a classification system which uses the pen trajectory to classify handwritten symbols. Five preprocessing steps, one data multiplication algorithm, five features and five variants for multilayer Perceptron training were evaluated using 166898 recordings. The evaluation results of 21 experiments were used to create an optimized recognizer. This improvement was achieved by supervised layer-wise pretraining (SLP) and adding new features.