Fusion of Complementary Online and Offline Strategies for Recognition of Handwritten Kannada Characters

Rakesh Rampalli (Indian Institute of Science, India)

Angarai Ganesan Ramakrishnan (Indian Institute of Science, India)

Abstract: This work describes an online handwritten character recognition system working in combination with an offline recognition system. The online input data is also converted into an offline image, and in parallel recognized by both online and offline strategies. Features are proposed for offline recognition and a disambiguation step is employed in the offline system for the samples for which the confidence level of the classier is low. The outputs are then combined probabilistically resulting in a classier out-performing both individual systems. Experiments are performed for Kannada, a South Indian Language, over a database of 295 classes. The accuracy of the online recognizer improves by 11% when the combination with offline system is used.

Keywords: Kannada script, Mahalanobis distance, Pen direction angle, Re-sampling, classifier fusion, directional distance distribution, nearest stroke pixel, offline handwriting recognition, online handwriting recognition, principal component analysis, projection proles, spline curve, support vector machine, transition count

Categories: I.2.1, I.4.9, I.5.4, J.6