Manchu handwritten character recognition post processing based on the combination language model

This paper presents a combination Manchu language model on post-processing optimization for handwritten Manchu characters recognition. The thinking of this model is take corpus as post-processing core and rule assistant correction. The model is based on a Manchu machine dictionary. The aim of work is to explore the language model in order to optimize the recognition accuracy rate. Present method focuses on the following tasks: a Manchu machine dictionary organization; rule description language; the contents of form grammar rule base; and corpus building. Experimental results are reported using the combination language model is efficient on the Manchu handwritten characters recognition post-processing.