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 parallely 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 classiﬁer is low. The outputs are then combined probabilistically resulting in a classi- ﬁer 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.