In this paper, a dynamic programming (DP) based approach is proposed to split a freehand stroke into the optimal number of line segments and elliptical arcs. Different from existing DP approaches, which often require a predefined fixed number and/or the templates of the result segments, our approach is actually a generic parameterized framework, which can be configured to some existing methods by fixing some of the parameters. Our key contribution is to avoid presetting of the number or templates of the segments and achieve the best tradeoff between the segment number and approximate error by using a suitable penalty function. Experiments show that our approach achieves high segmentation accuracy and can response to user?s stroke input in real-time.