Research on Residual Convolutional Neural Network for Handwritten Digit Recognition
DOI: 10.23977/jeis.2023.080306 | Downloads: 19 | Views: 447
Author(s)
Sizhe Zou 1
Affiliation(s)
1 Institute of Computer and Information Technology, Beijing Jiaotong University, Beijing, 100044, China
Corresponding Author
Sizhe ZouABSTRACT
The technology of handwritten digit recognition has been widely applied in various situations and has significant practical significance. However, the morphological features of handwritten numbers are very complex, and achieving accurate recognition of handwritten numbers relies on efficient and accurate recognition techniques. This article proposes a residual convolutional network model to address the issues of inaccurate feature extraction and weak model generalization ability in convolutional neural networks. By introducing residual blocks into the network, the problem of vanishing and exploding network gradients is effectively eliminated. At the same time, the Batch Normalization and Dropout layers are introduced to accelerate the network training process and reduce the risk of overfitting. Finally, the k-fold cross validation method was used to select the optimal parameter configuration of the model. The experimental results show that residual convolutional neural networks have the characteristics of high recognition accuracy and strong model generalization ability.
KEYWORDS
Residual Convolution; Handwritten Digit Recognition; Neural NetworksCITE THIS PAPER
Sizhe Zou, Research on Residual Convolutional Neural Network for Handwritten Digit Recognition. Journal of Electronics and Information Science (2023) Vol. 8: 50-59. DOI: http://dx.doi.org/10.23977/10.23977/jeis.2023.080306.
REFERENCES
[1] Huang Rui, Lu Xuming, Wu Yilin. Cursive number recognition and application based on Tensor Flow deep learning [J]. Electron Technology Applications, 2018, 44(10):6-10. DOI:10.16157/j.issn.0258-7998.182249.
[2] He Ping, Liu Ziyan. Handwritten digit recognition based on improved multi-layer perceptron [J]. Communication Technology, 2018, 51(09):2075-2080.
[3] Tan Shuai. Research on handwritten digit recognition based on deep residual networks [D]. Xi'an University of Electronic Science and Technology, 2019.
[4] Chen Yan, Li Yangyang, Yu Le, Wang Yao, Wu Chao, Li Yangguang. Cursive number recognition system based on convolutional neural network [J]. Microelectronics and computer, 2018, 35(02):71-74. DOI:10.19304/j. cnki. issn1000-7180. 2018.02.015.
[5] Song Xiaoru, Wu Xue, Gao Song, Chen Chaobo. Simulation research on handwritten digit recognition based on deep neural networks [J]. Science Technology and Engineering, 2019, 19(05):193-196.
[6] Bu Lingzheng, Wang Hongdong, Zhu Meiqiang, Dai Wei. Multi source number recognition algorithm based on improved convolutional neural network [J]. Computer Application, 2018, 38(12):3403-3408.
[7] Huang Yitian, Chen Zhitong. Recognition of handwritten digits based on convolutional neural network in the Pytorch framework [J]. Electronic Technology and Software Engineering, 2018(19):147.
[8] Hu Junping, Fu Kexue. Research on handwritten digit recognition based on improved KNN algorithm [J]. Journal of Wuhan University of Technology (Information and Management Engineering Edition), 2019, 41(01):22-26.
[9] Yang Gang, He Dongge, Dai Lizhen. Research on handwritten digit recognition based on CNN and particle swarm optimization SVM [J]. Journal of East China Jiaotong University, 2020, 37(04):41-47. DOI:10. 16749/j. cnki. Jecjtu .2020.04.007.
[10] Lv Hong. Design of handwritten digit recognition system based on convolutional neural network [J]. Intelligent Computers and Applications, 2019, 9(02):54-56+62.
[11] He K., Zhang X., Ren S., & Sun J. Deep residual learning for image recognition [J]. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2019:770-778.
[12] Kulkarni S.R. and Rajendran B. Spiking neural networks for handwritten digit recognition—Supervised learning and network optimization [J]. Neural networks, 2018, 103:118-127. DOI:10.1016/j.neunet. 2018.03.019.
[13] Zhang A. et al. Dive into Deep Learning [M]. 2021. doi:10.48550/arxiv.2106.11342.
[14] Kusetogullari H. et al. Digitnet: A deep handwritten digit detection and recognition method using a new historical handwritten digit dataset [J]. Big data research, 2021, 23:100-182. DOI:10.1016/j.bdr. 2020.100182.
Downloads: | 6471 |
---|---|
Visits: | 252416 |
Sponsors, Associates, and Links
-
Information Systems and Signal Processing Journal
-
Intelligent Robots and Systems
-
Journal of Image, Video and Signals
-
Transactions on Real-Time and Embedded Systems
-
Journal of Electromagnetic Interference and Compatibility
-
Acoustics, Speech and Signal Processing
-
Journal of Power Electronics, Machines and Drives
-
Journal of Electro Optics and Lasers
-
Journal of Integrated Circuits Design and Test
-
Journal of Ultrasonics
-
Antennas and Propagation
-
Optical Communications
-
Solid-State Circuits and Systems-on-a-Chip
-
Field-Programmable Gate Arrays
-
Vehicular Electronics and Safety
-
Optical Fiber Sensor and Communication
-
Journal of Low Power Electronics and Design
-
Infrared and Millimeter Wave
-
Detection Technology and Automation Equipment
-
Journal of Radio and Wireless
-
Journal of Microwave and Terahertz Engineering
-
Journal of Communication, Control and Computing
-
International Journal of Surveying and Mapping
-
Information Retrieval, Systems and Services
-
Journal of Biometrics, Identity and Security
-
Journal of Avionics, Radar and Sonar