A Paper on Preparation of Dataset for Handwritten Dzongkha Alphabets

Deewas Chamling¹ , Yeshi Jamtsho² , Yonten Jamtsho³

Section:Research Paper, Product Type: Journal-Paper
Vol.9 , Issue.6 , pp.105-109, Dec-2021

Online published on Dec 31, 2021

Copyright © Deewas Chamling, Yeshi Jamtsho, Yonten Jamtsho . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
 

View this paper at   Google Scholar | DPI Digital Library

XML View     PDF Download

How to Cite this Paper

Abstract :
In this paper, we present the complete methodology of preparing a dataset for handwritten Dzongkha alphabets of Bhutan to promote the development of the Handwritten Dzongkha Alphabet Recognition System (HanDARS). The dataset consists of 30 classes, each representing a character of the Dzongkha language with 500 images in each class amounting to a total of 15000 images. The images were manually collected from different individuals and were then augmented to add more varieties to the dataset. The alphabet images were converted to binary format. This dataset can be utilized as a basis for further research and development in the field of optical character recognition for the Dzongkha language. In the future, a greater number of handwritten alphabets needs to be collected to introduce variations in the dataset.

Key-Words / Index Term :
Deep Learning; Convolutional Neural Networks; Dzongkha, Bhutanese dataset

References :
[1] D. Chamling, Y. Jamtsho, and Y. Jamtsho, “Handwritten Dzongkha Alphabet Recognition System using Convolutional Neural Network,” Int. J. Sci. Res. Comput. Sci. Eng., Vol. 9, Issue. 5, pp. 20–24, 2021.
[2] S. K. Dasari, S. Mehta, and D. Steffi D.D, “Optical Character Recognition of Devanagari Script Using Machine Learning- A Survey,” J. Xian Univ. Archit. Technol., Vol. 12, Issue. 8, pp. 593–599, 2020.
[3] L. Deng, “The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web],” IEEE Signal Process. Mag., Vol. 29, Issue. 6, pp. 141–142, 2012.
[4] W. Zhu, “Classification of MNIST Handwritten Digit Database using Neural Network,” Aust Natl Univ, p. 7, 2012.
[5] U. Bhattacharya and B. B. Chaudhuri, “Databases for research on recognition of handwritten characters of Indian scripts,” in Eighth International Conference on Document Analysis and Recognition (ICDAR’05), pp. 789–793, 2005.
[6] U. Bhattacharya, M. Shridhar, S. K. Parui, P. K. Sen, and B. B. Chaudhuri, “Offline recognition of handwritten Bangla characters: an efficient two-stage approach,” Pattern Anal Applic, Vol. 15, Issue. 4, pp. 445–458, 2012.
[7] L. Ma, H. Liu, and J. Wu, “MRG-OHTC Database for Online Handwritten Tibetan Character Recognition,” in 2011 International Conference on Document Analysis and Recognition, pp. 207–211, 2011.
[8] N. Otsu, “A Tlreshold Selection Method from Gray-Level Histograms,” pp. 62–66, 1979.
[9] G. Bradski, “The OpenCV Library,” Dr. Dobb’s Journal of Software Tools, 2000.