A Bayesian-based probabilistic model for unconstrained handwritten offline Chinese text line recognition
Nanxi Li, Lianwen Jin · 2010
A Bayesian-based probabilistic model is presented for unconstrained handwritten offline Chinese text line recognition. After pre-segmentation of a text line, plenty of invalid characters are produced which heavily interfere in the process of text line recognition. The proposed probabilistic model can incorporate isolated character recognition, character sample verification, and n-gram language model in a simple way, leading to more reliable recognition of a text line. When testing on HIT-MW database, experiments show that the proposed method can achieve character-level recognition accuracies of 63.19% without language model and 73.97% with bi-gram language model, respectively, outperforming the most recent results testing on the same dataset.