Abstract
At present, the handwritten digit recognition the problem has received more attention because it has a large standard and easy-to-use mature data set such as the MNIST data set, simple 0–9 digit recognition has been regarded as an entry problem in the field of computer vision. The paper Introduce the characteristics and applications of handwritten digit recognition at first. Then, the traditional research methods and their shortcomings is pointed out; the concept of deep learning are introduced. Taking the convolutional neural network as an example, the key technical characteristics of the convolutional neural network in detail is introduced. Finally, an example explain the application of convolutional neural network in handwritten digit recognition.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Wang, Y.S., Wang, X.K.: A contraband detection system and deployment method based on convolutional neural network. Technol. Innov. Appl. 23, 136–138 (2020)
Cao, H.J., Wu, Z.M.: Linear filtering analysis and simulation of noisy images. Inf. Technol. Inform. 8, 50–52 (2017)
Yan, T., Zhou, Q.: Deep Learning Algorithm Practice (Based on Theano and TensorFlow). Electronic Industry Press, Beijing (2020)
Lai, X.W.: Application of TensorFlow reading data in simple image recognition. Mod. Inf. Technol. 3(12), 98–99 (2019)
He, S.: Application of convolutional neural network in handwritten digit recognition. Comput. Knowl. Technol. 16(21), 13–15 (2020)
Wei, F., Shan, L.: Research on handwritten digit recognition technology based on CNN optimization
Zhang, T., Yang, J., Song, W., et al.: Improved convolutional neural network model design method. Comput. Eng. Des. 40(7), 1885–1890 (2019)
Ma, Y.Y., Shi, J.R.: Convolutional neural network and its application in handwritten digit recognition. J. Hubei Inst. Technol. 37(6), 66–72 (2017)
Yin, X.W., Wang, Z.Z., Meng, Q.L., et al.: Research on handwritten digit recognition based on improved LeNet-5. Inf. Commun. 32(3), 17–18 (2019)
Lv, H.: Design of handwritten digit recognition system based on convolutional neural network. Intell. Comput. Appl. 9(2), 54–56 (2019). 62
Xing, M.: Design and implementation of handwritten digit recognition model based on TensorFlow. Electron. Technol. Softw. Eng. 2, 56 (2019)
Dai, H., Chen, H.M., Li, Z.S.: Digital recognition based on convolutional neural network. J. Guizhou Normal Univ. (Nat. Sci. Ed.) 35(5), 96–101 (2017)
Chen, Y., Li, Y.Y., Yu, L., et al.: Handwritten digit recognition system based on convolutional neural network. Microelectron. Comput. 35(2), 71–74 (2018)
Zhang, Q.H., Wan, C.X.: Overview of convolutional neural networks. J. Zhongyuan Inst. Technol. 28(3), 82–90 (2017)
Zheng, Y.P., Li, G.Y., Li, Y.: A review of application research of deep learning in image recognition. Comput. Eng. Appl. 55(12), 20–36 (2019)
Zhang, Q., Zhang, R.M., Chen, B.: Overview of research on image recognition based on deep learning. J. Hebei Acad. Sci. 3(15), 28–36 (2019)
Liu, J.W., Xie, H.J., Luo, X.L.: Research progress in the application of generative confrontation networks in various fields. Acta Autom. Sin. 45(10), 1–38 (2019)
Zhang, P., Cui, M.T., Xie, Q., et al.: Research on plant image recognition method based on deep convolution generative adversarial network. J. Southwest Univ. Natl. (Nat. Sci. Ed.) 45(2), 185 (2019)
Author information
Authors and Affiliations
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
Zhang, Q., Xu, S., Xu, Z. (2022). Handwritten Digit Recognition Application Based on Fully Connected Neural Network. In: Liu, Q., Liu, X., Chen, B., Zhang, Y., Peng, J. (eds) Proceedings of the 11th International Conference on Computer Engineering and Networks. Lecture Notes in Electrical Engineering, vol 808. Springer, Singapore. https://doi.org/10.1007/978-981-16-6554-7_9
Download citation
DOI: https://doi.org/10.1007/978-981-16-6554-7_9
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-6553-0
Online ISBN: 978-981-16-6554-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)