Abstract
Handwritten digital image recognition is a special problem in digital recognition, which is much more difficult due to uncertainties such as writer and writing environment. But the accuracy of handwritten digital recognition is particularly important in some critical areas such as public security and finance. In this paper, we used machine learning and deep learning technology, to identify MNIST handwritten digital data sets. And the support vector machine and convolutional neural network were used to image recognition, among them, the support vector machine compares the accuracy of the identification of the two kernel functions. Convolutional neural networks are improved based on the classic LeNet-5 model. The Experiments result shown that the identification accuracy of Gaussian kernel function model and linear kernel function model is 94.03% and 90.47% for support vector machines, respectively. In contrast, Gaussian kernel function performs better, but the overall accuracy is low. The best performance is based on the classic convolutional neural network LeNet-5 improved model, the test set recognition rate can reach 99.05%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bian, Z., Zhang, X.: Pattern Recognition, pp. 17–20. Tsinghua University Press, Beijing (2000)
Cao, D., Yang, C., Zhang, W.: Advance on handwritten digital recognition. Comput. Knowl. Technol. 5(03), 688–695 (2009)
Wang, Y., Xia, C., Dai, S.: Handwritten digital recognition optimization method based on LeNet-5 model. Comput. Dig. Eng. 47(12), 3177–3181 (2019)
Song, X., Wu, X., Gao, S., et al.: Simulation study on handwritten numeral recognition based on deep neural network. Sci. Technol. Eng. 19(05), 193–196 (2019)
Lu, H., Yang, Y., Su, J., Zhou, X.: Handwritten numerals recognition based on image processing. Instrum. Anal. Monit. 03, 13–15 (2005)
Gai, K., Qiu, M., Zhao, H: Security-aware efficient mass distributed storage approach for cloud systems in big data. In: 2016 IEEE 2nd International Conference on Big Data Security on Cloud (2016)
Meng, G., Fang, J.: System design of recognition of handwritten digits by support vector machine. Comput. Eng. Des. 06, 1592–1594+1598 (2005)
Wang, J., Cao, Y.: The application of support vector machine in classifying large namber of catalogs. J. BeiJing Inst. Technol. 02, 225–228 (2001)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. In: Proceedings of IEEE, pp. 2278–2324. IEEE, USA (1998)
Boureau, Y.L., Ponce, J., Lecun, Y.: Atheoretic alanalys is of feature pooling invisual recognition. In: International Conference on Machine Learning, vol. 32, no. 4, pp. 111–118 (2010)
Qiu, M., Jia, Z., Xue, C., Shao, Z., Sha, E.H.M.: Voltage assignment with guaranteed probability satisfying timing constraint for real-time multiproceesor DSP. J. VLSI Signal Process. Syst. Signal Image Video Technol. 46, 55–73 (2007)
Zhang, Q., Huang, T., Zhu, Y., Qiu, M.: A case study of sensor data collection and analysis in smart city: provenance in smart food supply chain. Int. J. Distrib. Sensor Netw. 9(11), 382132 (2013)
Chen, M., Zhang, Y., Qiu, M., Guizani, N., Hao, Y.: SPHA: smart personal health advisor based on deep analytics. IEEE Commun. Mag. 56(3), 164–169 (2018)
El-Sawy, A., EL-Bakry, H., Loey, M.: CNN for handwritten arabic digits recognition based on LeNet-5. In: Hassanien, A.E., Shaalan, K., Gaber, T., Azar, A.T., Tolba, M.F. (eds.) AISI 2016. AISC, vol. 533, pp. 566–575. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-48308-5_54
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Guo, Y., Zhang, X., Yang, Q., Guo, H. (2021). A Novel Image Recognition Method Based on CNN Algorithm. In: Qiu, M. (eds) Smart Computing and Communication. SmartCom 2020. Lecture Notes in Computer Science(), vol 12608. Springer, Cham. https://doi.org/10.1007/978-3-030-74717-6_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-74717-6_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-74716-9
Online ISBN: 978-3-030-74717-6
eBook Packages: Computer ScienceComputer Science (R0)