Abstract
Character recognition from handwritten images is of great interest in the pattern recognition research community for their good application in many areas. To implement the system, it requires two steps, viz., feature extraction followed by character recognition based on any classification algorithm. Convolutional neural network (CNN) is an excellent feature extractor and classifier. The performance of a CNN for a particular application depends on the parameters used in the network. In this article, a CNN is implemented for the MNIST dataset with appropriate parameters for training and testing the system. The system provides accuracy up to 98.85%, which is better with respect to others. It also takes very low amount of time for training the system.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Arica N, Vural FTY (2001) An overview of character recognition focused on offline handwriting. IEEE Trans Syst Man Cybern—Part C: Appl Rev 31(2):216–233
Epshtein B, Oyek E, Wexler Y (2010) Detecting text in natural scenes with strokes width transform. In: IEEE conference on computer vision and pattern recognition, pp 1–8
Yang JB, Shen KQ, Ong CJ, Li XP (2009) Feature selection for MLP neural network: the use of random permutation of probabilistic outputs. IEEE Trans Neural Netw 20(12):1911–1922
Lee H, Grosse R, Ranganath R, Ng AY (2009) Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: 26th Annual international conference on machine learning. ACM, pp 609–616
LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
Hanmandlu M, Murthy OVR (2007) Fuzzy model based recognition of handwritten numerals. Pattern Recogn 40(6):1840–1854
Graves A, Schmidhuber J (2009) Offline handwriting recognition with multidimensional recurrent neural networks. In: Advances in neural information processing systems NIPS’22, vol 22. MIT Press, Vancouver, pp 545–552
Pal A, Singh D (2010) Handwritten english character recognition using neural network. Int J Comput Sci Commun 1(2):141–144
Neves RFP, Filho, ANGL, Mello CAB, Zanchettin C (2011) A SVM based off-line handwritten digit recognizer. In: International conference on systems, man and cybernetics, IEEE Xplore, Brazil, 9–12, October 2011. pp 510–515
Younis KS, Alkhateeb, AA (2017) A new implementation of deep neural networks for optical character recognition and face recognition. In: Proceedings of the new trends in information technology, Jordan, April 2017. pp. 157–162
Dutt A, Dutt A (2017) Handwritten digit recognition using deep learning. Int J Adv Res Comput Eng Technol 6(7):990–997
Ghosh MMA, Maghari AY (2017) A comparative study on handwriting digit recognition using neural networks. In: International conference on promising electronic technologies, pp 77–81
Acknowledgements
The authors are grateful to IT department, RCC Institute of Information Technology (RCCIIT), Kolkata for providing the requisite infrastructure for the research work. The authors are also grateful to Prof. (Dr.) Ajoy Kumar Roy, Chairman, RCCIIT for his constant inspiration.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Jana, R., Bhattacharyya, S. (2019). Character Recognition from Handwritten Image Using Convolutional Neural Networks. In: Bhattacharyya, S., Pal, S., Pan, I., Das, A. (eds) Recent Trends in Signal and Image Processing. Advances in Intelligent Systems and Computing, vol 922. Springer, Singapore. https://doi.org/10.1007/978-981-13-6783-0_3
Download citation
DOI: https://doi.org/10.1007/978-981-13-6783-0_3
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-6782-3
Online ISBN: 978-981-13-6783-0
eBook Packages: EngineeringEngineering (R0)