Abstract
Due to the different writing habits, it is difficult to achieve the recognition of handwritten numbers. The artificial neural network has been widely used in character recognition because of its strong self-learning ability, adaptive ability, classification ability, fault tolerance and fast recognition. BP neural network is used to identify handwritten numerals in this paper. In order to obtain a higher correct rate, this paper improves the traditional BP neural network and experiments with the MNIST data set on the MATLAB simulation platform. The experimental results show that the improved network converge faster and the classification is more accurate.
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
Shuying Y. Image recognition and project practice. Beijing: Publishing House of Electronics Industry; 2014.
Basu S, Das N, Sarkar R, et al. Recognition of Numeric postal codes from multi-script postal address block. In: International conference on pattern recognition and machine intelligence. Springer; 2009. p. 381–6.
Impedovo S, Pirlo G, Modugno R, et al. Zoning methods for hand-written character recognition: an overview. In: International Conference on Frontiers in Handwriting Recognition. IEEE Computer Society;2010. p. 329–34.
Chenglong Y. Features selection algorithm based on PCA. Comput Technol Dev. 2011;4:123–5.
Feiyan Z. A research on the improvement of artificial fish algorithm and its optimization on BP neural network. Hunan: Hunan University of Science and Technology; 2015.
Meixian W, Xueliang Z, Shuhua W. Guo qin. Double self-adaptive learning rate algorithm for BPNN. Modern Manuf Eng. 2005;10:29–32.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Hou, Y., Zhao, H. (2018). Handwritten Digit Recognition Based on Improved BP Neural Network. In: Jia, Y., Du, J., Zhang, W. (eds) Proceedings of 2017 Chinese Intelligent Systems Conference. CISC 2017. Lecture Notes in Electrical Engineering, vol 460. Springer, Singapore. https://doi.org/10.1007/978-981-10-6499-9_7
Download citation
DOI: https://doi.org/10.1007/978-981-10-6499-9_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-6498-2
Online ISBN: 978-981-10-6499-9
eBook Packages: EngineeringEngineering (R0)