KIT | KIT-Bibliothek | Impressum | Datenschutz

On-line Recognition of Handwritten Mathematical Symbols

Thoma, Martin; Kilgour, Kevin; Stüker, Sebastian; Waibel, Alexander


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.

Volltext §
DOI: 10.5445/IR/1000048047
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Forschungsbericht/Preprint
Publikationsjahr 2015
Sprache Deutsch
Identifikator ISSN: 2194-1629
KITopen-ID: 1000048047
Verlag Karlsruher Institut für Technologie (KIT)
Umfang 8 S.
Serie KIT Scientific Working Papers ; 32
Schlagwörter Recognition; machine learning; neural networks; symbols; multilayer perceptron
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page