Education, Science, Technology, Innovation and Life
Open Access
Sign In

The Recognition of Tibetan Handwritten Numbers Based on Federated Learning

Download as PDF

DOI: 10.23977/jaip.2020.040101 | Downloads: 34 | Views: 820

Author(s)

Zhuofan Mei 1

Affiliation(s)

1 Jilin University Lambton College, Changchun, 130012, China

Corresponding Author

Zhuofan Mei

ABSTRACT

Numeral recognition is closely related to individual lives, involving postal codes and bank checks. In recent years, despite many researches focusing on handwritten recognition, there were few on the identification of Tibetan handwritten numerals; and related to privacy protection. This paper proposed a recognition system based on lightweight CNN and federated learning, aiming to reduce the total calculating resource consumption and secure sensitive information. Besides, pre-processed TibetanMNIST dataset were adopted as the training samples for case study. This cases eventually obtained nearly 96% accuracy, and the expected time required to process a single image was approximately 0.017ms. The proposed system can be used for the recognition of Tibetan handwritten numbers.

KEYWORDS

Convolutional Neural Network, Federated Learning, Handwritten Recognition, Pattern Recognition, Privacy Protection

CITE THIS PAPER

Zhuofan Mei, The Recognition of Tibetan Handwritten Numbers Based on Federated Learning. Journal of Artificial Intelligence Practice (2021) Vol. 4: 1-12. DOI: http://dx.doi.org/10.23977/jaip.2020.030101

REFERENCES

[1] Konečný, J., McMahan, H. B., Ramage, D., & Richtárik, P. (2016). Federated optimization: Distributed machine learning for on-device intelligence. arXiv:1610.02527.
[2] Howard, A., Sandler, M., Chu, G., Chen, L. C., Chen, B., Tan, M., ... & Adam, H. (2019). Searching for mobilenetv3. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 1314-1324.
[3] Ashiquzzaman, A., & Tushar, A. K. (2017). Handwritten Arabic numeral recognition using deep learning neural networks. In 2017 IEEE International Conference on Imaging, Vision & Pattern Recognition (icIVPR), 1-4. IEEE.
[4] Sufian, A., Ghosh, A., Naskar, A., Sultana, F., Sil, J., & Rahman, M. H. (2020). Bdnet: Bengali handwritten numeral digit recognition based on densely connected convolutional neural networks. Journal of King Saud University-Computer and Information Sciences.
[5] Prabhu, V. U. (2019). Kannada-MNIST: A new handwritten digits dataset for the Kannada language. arXiv: 1908.01242.
[6] Prashanth, D. S., Mehta, R. V. K., & Sharma, N. (2020). Classification of Handwritten Devanagari Number–An analysis of Pattern Recognition Tool using Neural Network and CNN. Procedia Computer Science, 167, 2445-2457.
[7] Kayumov, Z., Tumakov, D., & Mosin, S. (2020). Hierarchical convolutional neural network for handwritten digits recognition. Procedia Computer Science, 171, 1927-1934.
[8] Chandiramani, K., Garg, D., & Maheswari, N. (2019). Performance analysis of distributed and federated learning models on private data. Procedia Computer Science, 165, 349-355.
[9] Chen, Y., Luo, F., Li, T., Xiang, T., Liu, Z., & Li, J. (2020). A training-integrity privacy-preserving federated learning scheme with trusted execution environment. Information Sciences, 522, 69-79.
[10] Yang, D., Xu, Z., Li, W., Myronenko, A., Roth, H. R., Harmon, S., ... & Xu, D. (2021). Federated semi-supervised learning for COVID region segmentation in chest CT using multi-national data from China, Italy, Japan. Medical image analysis, 70, 101992.
[11] LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324.
[12] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25, 1097-1105.
[13] Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., ... & Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv: 1704.04861.
[14] Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, 4510-4520.
[15] Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., & Le, Q. V. (2019). Mnasnet: Platform-aware neural architecture search for mobile. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2820-2828.
[16] Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019). Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology (TIST), 10(2), 1-19.
[17] Cheng, Y., Wang, D., Zhou, P., & Zhang, T. (2017). A survey of model compression and acceleration for deep neural networks. arXiv: 1710.09282.
[18] Yang, T. J., Chen, Y. H., & Sze, V. (2017). Designing energy-efficient convolutional neural networks using energy-aware pruning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5687-5695.
[19] Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., ... & Zheng, X. (2016). Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv: 1603.04467.
[20] Yuan, M. Q., Cai, R. X. M., & Tang, J. A. (2018). TibetanMNIST - Tibetan handwritten digital dataset. https://www.kesci.com/mw/dataset/5bfe734a954d6e0010683839/content
[21] Gupta, D., & Bag, S. (2021). CNN-based multilingual handwritten numeral recognition: A fusion-free approach. Expert Systems with Applications, 165, 113784.

Downloads: 1272
Visits: 68260

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.