A fast HMM algorithm based on stroke lengths for on-line recognition of handwritten music scores

The hidden Markov model (HMM) has been successfully applied to various kinds of on-line recognition problems including, speech recognition, handwritten character recognition, etc. In this paper, we propose an on-line method to recognize handwritten music scores. To speed up the recognition process and improve usability of the system, the following methods are explained: (1) The target HMMs are restricted based on the length of a handwritten stroke, and (2) Probability calculations of HMMs are successively made as a stroke is being written. As a result, recognition rates of 85.78% and average recognition times of 5.19 ms/stroke were obtained for 6,999 test strokes of handwritten music symbols, respectively. The proposed HMM recognition rate is 2.4% higher than that achieved with the traditional method, and the processing time was 73% of that required by the traditional method.

[1]  Greg Watkins.  A Fuzzy Syntactic Approach to Recognising Hand-written Music , 1994, ICMC.

[2]  Uri Shimony,et al.  Computerized Recognition of Hand-Written Musical Notes , 1992, ICMC.

[3]  Jianying Hu,et al.  HMM Based On-Line Handwriting Recognition , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Uri Shimony,et al.  Recognition of handwritten musical notes by a modified Neocognitron , 1996, Machine Vision and Applications.

[5]  Minoru Maruyama,et al.  An online handwritten music score recognition system , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[6]  David Cooper,et al.  Embracing the Composer: Optical Recognition of Handwritten Manuscripts , 1999, International Conference on Mathematics and Computing.

[7]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[8]  Shigeki Matsuda,et al.  Context-dependent substroke model for HMM-based on-line handwriting recognition , 2002, Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition.

[9]  Horst Bunke,et al.  A new combination scheme for HMM-based classifiers and its application to handwriting recognition , 2002, Object recognition supported by user interaction for service robots.