Abstract
To recognize the Hindi characters using perceptron learning rule an algorithm is modeled and simulated in this paper. This model maps a matrix of pixels into characters on scanned images. In this paper perceptron learning rule is modeled based on mapping of input and output matrix of pixels. Perceptron learning rule uses an iterative weight adjustment that is more powerful than other learning rules. The perceptron uses threshold output function and the McCulloch–Pitts model of a neuron. Their iterative learning converges to correct weight vector, i.e., the weight vector that produces the exact output value for the training input pattern. For modeling and simulation, those Hindi characters are used which are similar to some of numeric numbers. To model and simulate the algorithm, Hindi characters are taken in form of the 5 × 3 matrix of pixels.
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
Hirwani, A., et al.: Character recognition using multilayer perceptron. (IJCSIT) Int. J. Comput. Sci. Inf. Technol. 5(1), 558–661 (2014)
Shih, F.T.: Image processing and pattern recognition fundamentals and techniques. Wiley Publications (2010)
El Bahi, H., Mahani, Z., Zatni, A., Saoud, S.: A robust system for printed and handwritten character recognition of images obtained by camera phone. Wseas Trans. signal Process. 11 (2015)
Hussain, J., Lalthlamuana: Unicode mizo character recognition system using multilayer neural network model. Int. J. Soft Comput. Eng. (IJSCE) 4(2) (2014). ISSN: 2231-2307
Jayanta Kumar, B., Debnath, B., Tai-hoon, K.: Use of artificial neural network in pattern recognition. Int. J. Softw. Eng. Appl. 4(2), 23–34 (2014)
Kanak, U., et al.: Handwritten character recognition system with Devanagari script. Int. J. Innov. Eng. Sci. Manage. 2(9) (2014)
Vasudeva, N., Parashar, H.J., Vijendra, S.: Offline character recognition system using artificial neural network. Int. J. Mach. Learn. Comput. 2(4) (2012)
Salouan, R., Safi, S., Bouikhalene, B.: Printed Arabic noisy characters recognition using the multi-layer perceptron. Int. J. Innov. Sci. Res. 9(1), 61–69 (2014)
Mehta, R., Kaur, R.: Neural network classifier for isolated character recognition. Int. J. Appl. Innov. Eng. Manage. (IJAIEM) 2(1) (2013)
Barve, S., Borawan, K.: Optical character recognition using artificial neural network. Int. J. Adv. Technol. Eng. Res. (IJATER) 2 (2), 139–142 (2012)
Kosbatwar, S.P., Pathan, S.K.: Pattern association for character recognition by back-propagation algorithm using neural network approach. Int. J. Comput. Sci. Eng. Survey (IJCSES) 3(1) (2012)
Pati, S., Bhagat, H.: Character recognition system using back prorogation network. Int. J. Adv. Res. Comput. Sci. Softw. Eng. 3(8) (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer Science+Business Media Singapore
About this paper
Cite this paper
Vaibhav Gupta, Sunita (2016). Printed Hindi Characters Recognition Using Neural Network. In: Pant, M., Deep, K., Bansal, J., Nagar, A., Das, K. (eds) Proceedings of Fifth International Conference on Soft Computing for Problem Solving. Advances in Intelligent Systems and Computing, vol 436. Springer, Singapore. https://doi.org/10.1007/978-981-10-0448-3_55
Download citation
DOI: https://doi.org/10.1007/978-981-10-0448-3_55
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-0447-6
Online ISBN: 978-981-10-0448-3
eBook Packages: EngineeringEngineering (R0)