ONLINE HANDWRITING RECOGNITION USING PHYSICS-BASED SHAPE METAMORPHOSIS

We present a new technique based on shape metamorphosis for on-line re cognition of handwritten words and simple shapes in a user-dependent s etting. The approach includes a segmentation method that does not try to locate letters but instead performs the significantly easier task o f locating corners and some key low curvature points. This is part of the method's strategy to see the word as a generic on-line shape. The segmentation points are used to model a cursive word or a hand-drawn l ine figure by pieces of wire. Shape metamorphosis occurs through stret ching and bending of the artificial wire. The amount of energy spent i n morphing one shape to another is used as a dissimilarity measure. Fo r any two given shapes an optimal morph can be computed in quadratic t ime by constraining the metamorphosis to the segmentation points of th ese shapes. Experiments with multiple subjects indicate that the metho d can handle collectively cursive words and hand-drawn line figures, b oth useful forms of communication in pen-based computing. (C) 1998 Pat tern Recognition Society. Published by Elsevier Science Ltd. All right s reserved.