Speeding up Online Character Recognition

Online handwriting recognition has gained interest due to increase in usage of hand held devices. Nonparametric methods has recognition time proportionate to the training set size, uses all points per stroke for calculating the similarity measurement. In this paper, we have shown a pruning method that selectively removes some of points in a stroke, and hence, it reduces the recognition time greatly without degrading the performance.

[1]  Anil K. Jain,et al.  Online handwriting recognition using multiple pattern class models , 2000 .

[2]  Erkki Oja,et al.  Speeding up on-line recognition of handwritten characters by pruning the prototype set , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[3]  Eamonn J. Keogh,et al.  Derivative Dynamic Time Warping , 2001, SDM.