Javanese Character Recognition Using Hidden Markov Model

Hidden Markov Model (HMM) is a stochastic method which has been used in various signal processing and character recognition. This study proposes to use HMM to recognize Javanese characters from a number of different handwritings, whereby HMM is used to optimize the number of state and feature extraction. An 85.7 % accuracy is obtained as the best result in 16-stated vertical model using pure HMM. This initial result is satisfactory for prompting further research.

Authors:

• Anastasia Rita Widiarti
• Phalita Nari Wastu

Keywords:

• Character recognition
• off-line handwritingrecognition
• Hidden Markov Model.

References:

[1] T.E. Behren, A. S─ørat Jatiswara: Struktur dan Perubahan di dalam
Puisi Jawa 1600-1930. Jakarta: Indonesian-Netherlands Cooperation in
Islamic Studies (INIS), 1995.
[2] Sam Muharto, and W. Nataatmaja, Trampil Basa Jawa 5: Jilid 5
kangge Kelas V SD/ MI. Solo: PT. Tiga Serangkai Pustaka Mandiri,
2008.
[3] Roongroj Nopsuwanchai, and Dan Povey, "Discriminative Training for
HMM-Based Offline Handwritten Character Recognition". IEEE in the
Seventh International Conference on Document Analysis and
Recognition (ICDAR 2003).
[4] Teresa M. Przytycka, Encyclopedia of The Human Genome: Hidden
Markov Models. USA: Nature Publishing Group, 2007.
[5] T. Theeramunkong, C. Wongtapan, and S. Sinthupinyo, "Off-line
Isolated Handwritten Thai OCR Using Islandbased Projection with Ngram
Models and Hidden Markov Models," IEEE. 2001.
[6] L. R. Rabiner, "A Tutorial on Hidden Markov Models and Selected
Applications in Speech Recognition," Proceeding of the IEEE, vol 77,
pp. 257-286, 1989.
[7] R. Ngabehi Yasadipura I, Menak China II. Bantanisentrem: Bale
Pustaka, 1934.
[8] R. Ngabehi Yasadipura I, Menak Sorangan. Batavia: Bale Pustaka,
1936.