In-air handwritten Chinese character recognition with locality-sensitive sparse representation toward optimized prototype classifier

Locality-sensitive sparse representation based classification has been shown to be effective for in-air handwritten Chinese character recognition (IAHCCR). In this paper, we present a locality-sensitive sparse representation toward optimized prototype classifier (LSROPC) for IAHCCR. In the proposed LSROPC, the learned dictionary can not only preserve local data structures, but also require the reconstruction of a pattern to get as close as possible to the prototype optimized by the minimum classification error (MCE) approach. So the LSROPC can help improve the classification accuracy effectively. The experiments are carried out on the datasets of traditional handwritten Chinese characters and in-air handwritten Chinese characters and the datasets designed for face recognition. The experimental results demonstrate the effectiveness of the proposed method.