CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2013 vol.35 Issue No.10 - Oct.

Subscribe

Issue No.10 - Oct. (2013 vol.35)

pp: 2413-2426

Xiang-Dong Zhou , Beijing Key Lab. of Human-Comput. Interaction, Inst. of Software, Beijing, China

Da-Han Wang , Nat. Lab. of Pattern Recognition (NLPR), Inst. of Autom., Beijing, China

Feng Tian , State Key Lab. of Comput. Sci., Inst. of Software, Beijing, China

Cheng-Lin Liu , Nat. Lab. of Pattern Recognition (NLPR), Inst. of Autom., Beijing, China

M. Nakagawa , Dept. of Comput. & Inf. Sci., Tokyo Univ. of Agric. & Technol., Koganei, Japan

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPAMI.2013.49

ABSTRACT

This paper proposes a method for handwritten Chinese/Japanese text (character string) recognition based on semi-Markov conditional random fields (semi-CRFs). The high-order semi-CRF model is defined on a lattice containing all possible segmentation-recognition hypotheses of a string to elegantly fuse the scores of candidate character recognition and the compatibilities of geometric and linguistic contexts by representing them in the feature functions. Based on given models of character recognition and compatibilities, the fusion parameters are optimized by minimizing the negative log-likelihood loss with a margin term on a training string sample set. A forward-backward lattice pruning algorithm is proposed to reduce the computation in training when trigram language models are used, and beam search techniques are investigated to accelerate the decoding speed. We evaluate the performance of the proposed method on unconstrained online handwritten text lines of three databases. On the test sets of databases CASIA-OLHWDB (Chinese) and TUAT Kondate (Japanese), the character level correct rates are 95.20 and 95.44 percent, and the accurate rates are 94.54 and 94.55 percent, respectively. On the test set (online handwritten texts) of ICDAR 2011 Chinese handwriting recognition competition, the proposed method outperforms the best system in competition.

INDEX TERMS

Lattices, Character recognition, Training, Handwriting recognition, Context, Text recognition, Context modeling,beam search, Character string recognition, semi-Markov conditional random field, lattice pruning

CITATION

Xiang-Dong Zhou, Da-Han Wang, Feng Tian, Cheng-Lin Liu, M. Nakagawa, "Handwritten Chinese/Japanese Text Recognition Using Semi-Markov Conditional Random Fields",

*IEEE Transactions on Pattern Analysis & Machine Intelligence*, vol.35, no. 10, pp. 2413-2426, Oct. 2013, doi:10.1109/TPAMI.2013.49REFERENCES