Nonlinear shape normalization (NSN) approaches based on line density equalization have been the most popular choice for both offline and online handwritten Chinese character recognition (HCCR). However, in a recent study of using 8-directional features for online HCCR, we discovered that an NSN approach based on dot density equalization achieved a much better performance than that of an NSN approach based on line density equalization. In this paper, we present the details of the NSN approaches we studied for online HCCR, and report the comparative experimental results using an in-house developed Chinese handwriting corpus as well as the popular Nakayosi and Kuchibue Japanese character databases. We also present an improved NSN approach based on the equalization of dot densities derived from blurred character image that can be used for offline HCCR.
展开▼
