A hierarchical deformation model for online cursive script recognition

The authors propose a hierarchical deformation model to describe the deformation of cursive Chinese characters for online character recognition. This approach consists of two levels of match processes. First, the attributed string editing algorithm determines the stroke correspondence between the input and the reference pattern. Next, the constrained parabola transformation is used to reduce the difference between the matched strokes appropriately. Experimental results show that the hierarchical deformation model provides a robust distance measure between patterns, and obtains a quite accurate approximation to the deformation of cursive Chinese characters with much lower computational cost