Bigram-based post-processing for online handwriting recognition using correctness evaluation

An approach to bigram-based linguistic processing for online handwriting text recognition is described. A probability of correctness for each recognition result is derived from a feature set which consists of bigram probabilities and recognition scores. Using the probability of correctness, the number of candidates accepted to the post-processing step and the weight value balancing recognition scores with bigram scores are adaptively controlled. The proposed method is evaluated in experiments using the HANDS-kuchibue online handwritten character database. Results show that the method is effective in reducing candidates, improving accuracy, and saving computational costs.

[1]  Eiki Ishidera,et al.  A candidate reduction method for handwritten Kanji character recognition , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[2]  Kazuhiko Yamamoto,et al.  On-line handwritten character recognition method using directional features and clockwise/counterclockwise direction-change features , 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318).

[3]  Masaki Nakagawa,et al.  Robust and highly customizable recognition of online handwritten Japanese characters , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[4]  Takashi Matsumoto,et al.  A Bayesian bi-gram scheme for HMM online handwriting recognition algorithm , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[5]  Masaki Nakagawa,et al.  On-line handwritten character pattern database sampled in a sequence of sentences without any writing instructions , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.

[6]  Masaki Nakagawa,et al.  Precise Candidate Selection for Large Character Set Recognition by Confidence Evaluation , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  K. Yamada,et al.  A maximum-likelihood approach to segmentation-based recognition of unconstrained handwriting text , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.