Abstract
The automatic detection and recognition of characters in images are an important problem in various applications. The traditional shallow networks in machine learning have limitations in image classification due to their inability to effectively utilize the spatial relationships between the pixels of the image. But the incredible advances in deep learning methods and deep architecture in the recent years have opened doors to the possibility of employing these techniques. In this paper, a deep convolutional neural network (CNN) with minimal preprocessing for the effective classification of handwritten characters has been proposed. The application of this network yielded an accuracy of 99.50 and 94.66% on the test data of MNIST and EMNIST datasets, respectively.
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
T. Pavlidis, Recognition of printed text under realistic conditions. Pattern Recogn. Lett. 14, 317–326 (1993)
S.N. Srihari, Recognition of handwritten and machine-printed text for postal address interpretation. Pattern Recogn. Lett. 14, 291–302 (1993)
R. Seethalakshmi, T.R. Sreeranjani, T. Balachandar, A. Singh, M. Singh, R. Ratan, S. Kumar, Optical character recognition for printed Tamil text using unicode. J. Zhejiang Univ. Sci. A 6, 1297–1305 (2005)
H.A. Al-Muhtaseb, S.A. Mahmoud, R.S. Qahwaji, Recognition of off-line printed Arabic text using hidden Markov models. Signal Process. 88, 2902–2912 (2008)
R. Smith, An overview of the Tesseract OCR engine, in Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) 2007 Sep 23 (vol. 2, pp. 629–633). IEEE (2007)
R. Plamondon, S.N. Srihari, Online and off-line handwriting recognition, a comprehensive survey. IEEE Trans. Pattern Anal. Mach. Intell. 22, 63–84 (2000)
N. Shanthi, K. Duraiswamy, A novel SVM-based handwritten Tamil character recognition system. Pattern Anal. Appl. 13, 173–180 (2010)
N.A. Hamid, N.N. Sjarif, Handwritten recognition using SVM, KNN and neural network. arXiv preprint arXiv:1702.00723 (2017)
F. Jia, Y. Lei, J. Lin, X. Zhou, N. Lu, Deep neural networks, a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mech. Syst. Signal Process. 72–73, 303–315 (2016)
Y. LeCun, Deep learning & convolutional networks, in 2015 IEEE Hot Chips 27 Symposium (HCS) (2015)
C. Bailer, T. Habtegebrial, K. Varanasi, D. Stricker, Fast dense feature extraction with convolutional neural networks that have pooling or striding layers, in Proceedings of the British Machine Vision Conference 2017 (2017)
S.B. Driss, S. Ben Driss, M. Soua, R. Kachouri, M. Akil, A comparison study between MLP and convolutional neural network models for character recognition, in Real-Time Image and Video Processing (2017)
S.S. Girija, Tensorflow: large-scale machine learning on heterogeneous distributed systems. https://cse.buffalo.edu/~chandola/teaching/mlseminardocs/TensorFlow.pdf
Y. Lecun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)
P. Kumar, N. Sharma, A. Rana, Handwritten character recognition using different Kernel based SVM classifier and MLP neural network (a comparıson). Int. J. Comput. Appl. 53, 25–31 (2012)
A. Krizhevsky, I. Sutskever, G.E. Hinton, ImageNet classification with deep convolutional neural networks. Commun. ACM 60, 84–90 (2017)
K. Younis, A. Khateeb, Arabic hand-written character recognition based on deep convolutional neural networks. Jordanian J. Comput. Inf. Technol. 3, 186 (2017)
P. Vijayaraghavan, M. Sra, Handwritten tamil recognition using a convolutional neural network, in 2018 International Conference on Information, Communication, Engineering and Technology (ICICET) (2014)
W. Yang, L. Jin, Z. Xie, Z. Feng, Improved deep convolutional neural network for online handwritten Chinese character recognition using domain-specific knowledge, in 2015 13th International Conference on Document Analysis and Recognition (ICDAR) (2015)
S. Sen, D. Shaoo, S. Paul, R. Sarkar, K. Roy, Online handwritten Bangla character recognition using CNN, a deep learning approach. Adv. Intell. Syst. Comput. 413–420 (2018)
S. Lawrence, C.L. Giles, Overfitting and neural networks: conjugate gradient and backpropagation, in Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium 2000 Jul 27 (vol. 1, pp. 114–119). IEEE
K. Hara, D. Saito, H. Shouno, Analysis of function of rectified linear unit used in deep learning, in 2015 International Joint Conference on Neural Networks (IJCNN) (2015)
S. Ioffe, C. Szegedy, Batch normalization: accelerating deep network training by reducing internal covariate shift (2015)
N. Eikmeier, R. Westerkamp, E. Zelnio. Development of CNNs for feature extraction, in Algorithms for Synthetic Aperture Radar Imagery XXV, vol. 10647, p. 106470C. International Society for Optics and Photonics (2018)
M.D. Zeiler, R. Fergus, Visualizing and understanding convolutional networks, in European Conference on Computer Vsision, pp. 818–833. Springer, Cham (2014)
S. Liu, W. Deng. Very deep convolutional neural network based image classification using small training sample size, in 2015 3rd IAPR Asian conference on pattern recognition (ACPR), pp. 730–734. IEEE (2015)
G. Cohen, S. Afshar, J. Tapson, A. Schaik, EMNIST: Extending MNIST to handwritten letters, in 2017 International Joint Conference on Neural Networks (ICJNN), pp. 2921–2926 (2017)
K. He, X. Zhang, S. Ren, J. Sun, Delving deep into rectifiers: surpassing Human-level performance on ImageNet classification, in 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1026–1034 (2015)
B. Xu, N. Wang, T. Chen, M. Li, Empirical evaluation of rectified activations in convolutional network, in arXiv:1505.00853v2[cs.LG]
N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(56), 1929–1958 (2014)
P. Golik, P. Doetsch, H. Ney, Cross-entropy vs. squared error training: a theoretical and experimental comparison, in Interspeech, vol. 13, pp. 1756–1760 (2013)
S.J. Reddi, S. Kale, S. Kumar, On the convergence of adam and beyond. arXiv preprint arXiv:1904.09237. 2019 Apr 19
K.S. Younis, A.A. Alkhateeb, A new implementation of deep neural networks for optical character recognition and face recognition. Proceedings of the new trends in information technology. 2017 Apr 25 pp. 157–162
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Shashank, R., Adarsh Rai, A., Srinivasa Pai, P. (2022). Handwritten Character Recognition Using Deep Convolutional Neural Networks. In: Shetty D., P., Shetty, S. (eds) Recent Advances in Artificial Intelligence and Data Engineering. Advances in Intelligent Systems and Computing, vol 1386. Springer, Singapore. https://doi.org/10.1007/978-981-16-3342-3_21
Download citation
DOI: https://doi.org/10.1007/978-981-16-3342-3_21
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-3341-6
Online ISBN: 978-981-16-3342-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)