This paper presents a novel approach for classification of online handwritten sequences into text, equations, and plots. This classification helps in identifying the progress of student/learner while attempting different problems in context of classroom equipped with tablets, iPads. Furthermore, it serves as a feedback (for both students and instructors) to analyze the writing behavior and understanding capabilities of the student. The presented approach is based on an ensemble of different machine learning classifiers, where not only the individual sequences are classified but also the contextual information is used to refine the classification results. To train and test the system, a real-world dataset consisting up of 11,601 sequences was collected from 20 participants. Evaluation results on the real dataset shows that the presented system, when tested in person independent settings, is capable of classifying handwritten on-line sequences with an overall accuracy of 92%.
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
Tel.: +1 703 830 6300
Fax: +1 703 830 2300 firstname.lastname@example.org
(Corporate matters and books only) IOS Press c/o Accucoms US, Inc.
For North America Sales and Customer Service
West Point Commons
Lansdale PA 19446
Tel.: +1 866 855 8967
Fax: +1 215 660 5042 email@example.com