Abstract
Indian subcontinent is a birthplace of multilingual people, where documents such as job application form, passport, number plate identification, and so forth are composed of text contents written in different languages or scripts. These scripts consist of different Indic numerals in a single document page. Recently, deep convolutional neural networks (CNN) have achieved favorable result in computer vision problems, especially in recognizing handwritten digits but most of the works focuses on only one language, i.e., English or Hindi or Bangla, etc. However, developing a language-invariant method is very important as we live in a global village now. In this work, we have examined the performance of the ten state-of-the-art deep CNN methods for the recognition of handwritten digits using four most common languages in the Indian sub-continent that creates the foundation of a script invariant handwritten digit recognition system. Among the deep CNNs, Inception-v4 performs the best based on accuracy and computation time. Besides, it discusses the limitations of existing techniques and shows future research directions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Pal, U., Chaudhuri, B.B.: Indian script character recognition: a survey. Pattern Recogn. 37(9), 1887–1899 (2004)
Lopez, B., Nguyen, M.A., Walia, A.: Modified mnist (2019)
Chaudhary, M., Mirja, M.H., Mittal, N.: Hindi numeral recognition using neural network. Int. J. Sci. Eng. Res. 5(6), 260–268 (2014)
Pal, U., Chaudhuri, B.B.: Automatic recognition of unconstrained off-line Bangla handwritten numerals. In: International Conference on Multimodal Interfaces. Springer, Berlin, Heidelberg (2000)
Pal, U., Wakabayashi, T., Kimura, F.: A system for off-line Oriya handwritten character recognition using curvature feature. In: 10th International Conference on Information Technology (ICIT), pp. 227–229 (2007)
Bag, S., Chawpatnaik, G.: A modified parallel thinning method for handwritten Oriya character images. In: Proceedings of the 4th International Conference on Frontiers in Intelligent Computing: Theory and Applications (FICTA) 2015. Springer, New Delhi (2016)
Jena, O.P., Pradhan, S.K., Biswal, P.K., Tripathy, A.R.: Odia characters and numerals recognition using hopfield neural network based on Zoning features. Int. J. Recent Technol. Eng. 8(2), 4928–4937 (2019)
Pattanayak, Sudha, S., Pradhan, S.K., Mallik, R.C.: Printed Odia symbols for character recognition: a database study. In: Advanced Computing and Intelligent Engineering, pp. 297–397. Springer, Singapore (2020)
Vohra, U.S., Dwivedi, S.P., Mandoria, H.L.: Study and analysis of multilingual hand written characters recognition using SVM classifier. Oriental J. Comput. Sci. Technol. 9(2), 109–114 (2016)
Reddy, R., Kumar, V., Babu, U.R.: Handwritten Hindi character recognition using deep learning techniques. Department of CSE, Acharya Nagarjuna University, Guntur, India. Int. J. Comput. Sci. Eng. (2019)
Fujisawa, H.: Forty years of research in character and document recognition—an industrial perspective. Pattern Recogn. 41(8), 2435–2446 (2008)
Yadav, C., Bottou, L.: Cold case: the lost mnist digits. In: Advances in Neural Information Processing Systems (2019)
Baldominos, Alejandro, Saez, Y., and Pedro I.: A survey of handwritten character recognition with mnist and emnist. Applied Sciences 9.15, 3169, (2019).
.Alvear-Sandoval, R.F., Sancho-Gómez, J.L., Figueiras-Vidal, A.R.: On improving CNNs performance: the case of MNIST. Information Fusion. 52, 106–109 (2019)
Shamsuddin, M., Razif, S., Abdul-Rahman, Mohamed, A.: Exploratory analysis of MNIST handwritten digit for machine learning modelling. In: International Conference on Soft Computing in Data Science. Springer, Singapore (2018)
Alom, M., Sidike, P., Taha, T., Asari, V.: Handwritten Bangla Digit Recognition Using Deep Learning. ArXiv abs/1705.02680 (2017)
Rabby, Azad, AKM.S.: et al.: Bangla handwritten digit recognition using convolutional neural network. In: Emerging Technologies in Data Mining and Information Security, pp. 111–112. Springer, Singapore (2019)
Sufian, A., et al.: Bdnet: Bengali handwritten numeral digit recognition based on densely connected convolutional neural networks. J. King Saud Univ.-Comput. Inf. Sci. (2020)
Maity, S., et al.: Handwritten Bengali character recognition using deep convolution neural network. In: International Conference on Machine Learning, Image Processing, Network Security and Data Sciences. Springer, Singapore (2020)
Pias, M., Mutasim, A.K., Amin, M.A.: Bangladeshi number plate detection: cascade learning versus deep learning. In: Proceedings of the 15th International Workshop on Content-Based Multimedia Indexing (2017)
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Kienzle, W., Chellapilla, K.: Personalized handwriting recognition via biased regularization. In: Proceedings of the 23rd International Conference on Machine Learning (2006)
Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv: 1409.1556 (2014)
Mohd, S.S., et al.: Offline Signature Verification using Deep Learning Convolutional Neural Network (CNN) Architectures GoogLeNet Inception-v1 and Inception-v3. Procedia Comput. Sci. 161, 475–483 (2019)
Cheng, W., et al.: Pulmonary image classification based on inception-v3 transfer learning model. IEEE Access 7, 146533–146541 (2019)
Wen, L., Xinyu, L., Liang, G.: A transfer convolutional neural network for fault diagnosis based on ResNet-50. Neural Comput. Appl. 1–14 (2019)
Chollet, F.: Xception: Deep learning with depthwise separable convolutions. In:Â Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)
Sevilla, A., Glotin, H.: Audio Bird Classification with Inception-v4 extended with Time and Time-Frequency Attention Mechanisms. CLEF (Working Notes), (2017).
Chen, X., et al.: Visual crowd counting with improved inception-ResNet-A module. In: 2018 IEEE International Conference on Robotics and Biomimetics (ROBIO). IEEE (2018)
Qianqian, Z., Sen, L., Weiming, G.: Research on Vehicle Appearance Component Recognition Based on Mask R-CNN. In: Journal of Physics: Conference Series, vol. 1335, no. 1. IOP Publishing (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Haque, M.R., Azam, M.G., Milon, S.M., Hossain, M.S., Molla, M.AA., Uddin, M.S. (2021). Quantitative Analysis of Deep CNNs for Multilingual Handwritten Digit Recognition. In: Kaiser, M.S., Bandyopadhyay, A., Mahmud, M., Ray, K. (eds) Proceedings of International Conference on Trends in Computational and Cognitive Engineering. Advances in Intelligent Systems and Computing, vol 1309. Springer, Singapore. https://doi.org/10.1007/978-981-33-4673-4_2
Download citation
DOI: https://doi.org/10.1007/978-981-33-4673-4_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-4672-7
Online ISBN: 978-981-33-4673-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)