Deep Learning-Based Dzongkha Handwritten Digit Classification

Main Article Content

Yonten Jamtsho Pema Yangden Sonam Wangmo Nima Dema


In computer vision applications, pattern recognition is one of the important fields in artificial intelligence. With the advancement in deep learning technology, many machine learning algorithms were developed to tackle the problem of pattern recognition. The purpose of conducting the research is to create the first-ever Dzongkha handwritten digit dataset and develop a model to classify the digit. In the study, the 3 layer set of CONV → ReLU → POOL, followed by a fully connected layer, dropout layer, and softmax function were used to train the digit. In the dataset, each class (0-9) contains 1500 images which are split into train, validation, and test sets: 70:20:10. The model was trained on three different image dimensions: 28 by 28, 32 by 32, and 64 by 64. Compared to image dimensions 28 by 28 and 32 by 32, 64 by 64 gave the highest train, validation, and test accuracy of 98.66%, 98.9%, and 99.13% respectively. In the future, the sample of digits needs to be increased and use the transfer learning concept to train the model.


Download data is not yet available.

Article Details

How to Cite
Jamtsho, Y., Yangden, P., Wangmo, S., & Dema, N. (2024, March 31). Deep Learning-Based Dzongkha Handwritten Digit Classification. JITCE (Journal of Information Technology and Computer Engineering), 8(1), 1-7.


[1] U. Sherpa, D. Pemo, D. Chhoeden, A. Rugchatjaroen, A. Thangthai, and C. Wutiwiwatchai, ‘Pioneering Dzongkha Text-to-Speech Synthesis’, p. 5, 2008.
[2] M. A. Abuzaraida, A. M. Zeki, and A. M. Zeki, ‘Online Recognition System for Handwritten Hindi Digits Based on Matching Alignment Algorithm’, in 2014 3rd International Conference on Advanced Computer Science Applications and Technologies, Dec. 2014, pp. 168–171. doi: 10.1109/ACSAT.2014.36.
[3] E. Rani. G, Sakthimohan. M, A. Reddy. G, Selvalakshmi. D, T. Keerthi, and R. Sekar. R, ‘MNIST Handwritten Digit Recognition using Machine Learning’, in 2022 2nd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), Apr. 2022, pp. 768–772. doi: 10.1109/ICACITE53722.2022.9823806.
[4] D. Beohar and A. Rasool, ‘Handwritten Digit Recognition of MNIST dataset using Deep Learning state-of-the-art Artificial Neural Network (ANN) and Convolutional Neural Network (CNN)’, in 2021 International Conference on Emerging Smart Computing and Informatics (ESCI), Mar. 2021, pp. 542–548. doi: 10.1109/ESCI50559.2021.9396870.
[5] L. Mookdarsanit and P. Mookdarsanit, ‘ThaiWritableGAN: Handwriting Generation under Given Information’, Int. J. Comput. Digit. Syst., May 2021, doi: 10.12785/ijcds/100165.
[6] S. Gonwirat and O. Surinta, ‘Improving Recognition of Thai Handwritten Characters with Deep Convolutional Neural Networks’, in Proceedings of the 3rd International Conference on Information Science and Systems, in ICISS ’20. New York, NY, USA: Association for Computing Machinery, Apr. 2020, pp. 82–87. doi: 10.1145/3388176.3388181.
[7] B. Nyaupane, R. Sah, and K. Dahal, ‘SVM, KNN, Random Forest, and Neural Network based Handwritten Nepali Barnamala Recognition’, J. Innov. Eng. Educ., vol. 4, pp. 64–70, Dec. 2021, doi: 10.3126/jiee.v4i2.38254.
[8] Md. M. Hasan, A. Y. Srizon, A. Sayeed, and Md. A. M. Hasan, ‘Handwritten Numerals Recognition by Employing a Transfer Learned Deep Convolution Neural Network for Diverse Literature’, in 2020 11th International Conference on Electrical and Computer Engineering (ICECE), Dec. 2020, pp. 431–434. doi: 10.1109/ICECE51571.2020.9393079.
[9] R. Ameri, A. Alameer, S. Ferdowsi, V. Abolghasemi, and K. Nazarpour, ‘Classification of Handwritten Chinese Numbers with Convolutional Neural Networks’, in 2021 5th International Conference on Pattern Recognition and Image Analysis (IPRIA), Apr. 2021, pp. 1–4. doi: 10.1109/IPRIA53572.2021.9483557.
[10] Z. Li, Q. Wu, Y. Xiao, M. Jin, and H. Lu, ‘Deep Matching Network for Handwritten Chinese Character Recognition’, Pattern Recognit., vol. 107, p. 107471, Nov. 2020, doi: 10.1016/j.patcog.2020.107471.
[11] 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, no. 5, pp. 20–24, 2021.
[12] K. Khunratchasana and T. Treenuntharath, ‘Thai digit handwriting image classification with convolutional neural networks’, Indones. J. Electr. Eng. Comput. Sci., vol. 27, no. 1, p. 110, Jul. 2022, doi: 10.11591/ijeecs.v27.i1.pp110-117.
[13] J. Mukhoti, S. Dutta, and R. Sarkar, ‘Handwritten Digit Classification in Bangla and Hindi Using Deep Learning’, Appl. Artif. Intell., vol. 34, no. 14, pp. 1074–1099, Dec. 2020, doi: 10.1080/08839514.2020.1804228.
[14] A. Sufian, A. Ghosh, A. Naskar, F. Sultana, J. Sil, and M. M. H. Rahman, ‘BDNet: Bengali Handwritten Numeral Digit Recognition based on Densely connected Convolutional Neural Networks’, J. King Saud Univ. - Comput. Inf. Sci., Mar. 2020, doi: 10.1016/j.jksuci.2020.03.002.
[15] R. S. Alkhawaldeh, M. Alawida, N. F. F. Alshdaifat, W. Z. Alma’aitah, and A. Almasri, ‘Ensemble deep transfer learning model for Arabic (Indian) handwritten digit recognition’, Neural Comput. Appl., vol. 34, no. 1, pp. 705–719, Jan. 2022, doi: 10.1007/s00521-021-06423-7.
[16] R. Hasan Finjan, A. Salim Rasheed, A. Abdulsahib Hashim, and M. Murtdha, ‘Arabic handwritten digits recognition based on convolutional neural networks with resnet-34 model’, Indones. J. Electr. Eng. Comput. Sci., vol. 21, no. 1, p. 174, Jan. 2021, doi: 10.11591/ijeecs.v21.i1.pp174-178.
[17] J. Li, G. Sun, L. Yi, Q. Cao, F. Liang, and Y. Sun, ‘Handwritten Digit Recognition System Based on Convolutional Neural Network’, in 2020 IEEE International Conference on Advances in Electrical Engineering and Computer Applications( AEECA), Aug. 2020, pp. 739–742. doi: 10.1109/AEECA49918.2020.9213619.
[18] F. Siddique, S. Sakib, and Md. A. B. Siddique, ‘Recognition of Handwritten Digit using Convolutional Neural Network in Python with Tensorflow and Comparison of Performance for Various Hidden Layers’, in 2019 5th International Conference on Advances in Electrical Engineering (ICAEE), Sep. 2019, pp. 541–546. doi: 10.1109/ICAEE48663.2019.8975496.
[19] D. Chamling, Y. Jamtsho, and Y. Jamtsho, ‘A Paper on Preparation of Dataset for Handwritten Dzongkha Alphabets’, vol. 9, pp. 105–109, Dec. 2021.
[20] N. Otsu, ‘A Threshold Selection Method from Gray-Level Histograms’, presented at the IEEE Transactions on Systems, Man, and Cybernetics, IEEE, 1979, pp. 62–66.
[21] G. Bradski, ‘The OpenCV Library’, Dr. Dobb’s Journal of Software Tools, 2000.
[22] Chollet, Francois, and others, ‘Keras’. GitHub, 2015. [Online]. Available: