Handwritten Tibetan Character Recognition Using Hidden Markov Model
Nyichak Dhondup1, Deepa V Jose2
1Nyichak Dhondup, Department of Computer Science, CHRIST (Deemed to be University), Bangalore, Karnataka, India.
2Deepa V Jose, Department of Computer Science, CHRIST (Deemed to be University), Bangalore, Karnataka, India.
Manuscript received on 20 April 2019 | Revised Manuscript received on 26 May 2019 | Manuscript published on 30 May 2019 | PP: 7 | Volume-8 Issue-1, May 2019 | Retrieval Number: A1386058119/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The Tibetan language which is one of the four oldest and most original languages of Asia is elemental to Tibetan identity, culture and religion and it convey very specific social and cultural behaviors, and ways of thinking. The annihilation of the Tibetan language will have tremendous consequences for the Tibetan culture and hence it is important to preserve it. Tibetan language is mainly used in Tibet, Bhutan, and also in parts of Nepal and India. Tibetan script is devised based on the Devanagari model and Sanskrit based grammars. In this paper, a method for Tibetan handwritten character recognition based on density and distance feature detection is presents. To get a better classification result, images are converted into binary and noise removal is done by using Otzso’s method. Features are extracted by normalizing the image based on distance and density of the pixel in the image. Finally, Hidden Markov Model is used for character classification.
Keywords: Tibetan Character, Distance, Density, Otzso, Hidden Markov Model.
Scope of the Article: Image Processing and Pattern Recognition