Comparison and Analysis of Chinese and English Handwriting Recognition Algorithms in Deep Learning

Xinyue Qu

doi:10.54097/t9f6xd17

Authors

Xinyue Qu

DOI:

https://doi.org/10.54097/t9f6xd17

Keywords:

Handwriting recognition, deep learning, neural network, Simple RNN, LSTM.

Abstract

Handwriting recognition is an important topic of current research on image recognition. This technology provides convenience for production and life, as well as guarantees for us in some aspects of safety. The author hopes to help people get a preliminary understanding of English handwriting recognition by summarizing and comparing two commonly used models in deep learning. This paper focuses on two models of widely used English handwriting recognition, which are the simple Recurrent Neural Network (RNN) model and the Long Short-Term Memory (LSTM) model. Firstly, the principles of the two models are introduced, and then gradient problems, fitting problems, training difficulty, and accuracy, as well as the reasons for these problems are all discussed and compared within the two models. Nowadays, the accuracy rate of English handwriting recognition is relatively high using deep learning methods and models. With the development of deep learning models, if more accurate string segmentation can be achieved, the accuracy rate of handwriting recognition can also be further improved.

Downloads

Download data is not yet available.

References

He Juan. Application Research of Handwritten English Automation Recognition Model Based on Deep Learning Network in Machine Translation between English and Chinese. Automation and Instrumentation, 2023.

Zhang Zhenwei, Wang Hongcheng. Handwritten Digit Recognition Method Based on Improved Convolutional Neural Network and SVM. Journal of Dongguan University of Technology, 2021, (05), 57-61+86.

Xiao Bin. Research on Commercial Bank Cash Reserve Demand Prediction Model with Fusion of Spatiotemporal Features. Shanghai University of Finance and Economics, 2023.

Zhang Xinfeng, Yan Kunpeng, Zhao Xun. Research on Handwritten Text Recognition Technology Based on Bidirectional LSTM. Journal of Nanjing Normal University (Natural Science Edition), 2019, 42(03): 64-70.

Xie Zilin. Oil Well Production Prediction Model Based on Improved Particle Swarm Algorithm and Long Short-Term Memory Neural Network. China National Petroleum Corporation Xinjiang Oilfield Branch (Xinjiang Lixian Oilfield Laboratory), Xi'an Petroleum University, Shaanxi Petroleum Society. Proceedings of the 2022 International Conference on Oil and Gas Field Exploration and Development III, 2022, 11.

Li Guangyan, Wang Xiuhui. Handwritten Character Recognition Method of Lightweight Residual Network with Multiple Branches. Computer Engineering and Applications, 2023.

Gao Tao, Shao Qian, Zhang Yanan, Zhang Sai. Research on Facial Expression Recognition Based on Deep Residual Network. Electronic Design Engineering, 2020, 28(23): 4.

Heng Hongjun, Hu Gang. Aircraft Airworthiness Named Entity Recognition Method Based on BiGRU-LAN. China Highway Society, World Traffic Transportation Conference Executive Committee, Xi'an Municipal People's Government, Shaanxi Association for Science and Technology. Proceedings of the World Traffic Transportation Engineering Technology Forum (WTC2021) (Volume I). People's Communications Press Co., Ltd., 2021, 7.

Yang Yixin. Research on Remote Sensing Image Fault Detection Method Based on Deep Learning. China University of Petroleum (Beijing), 2023.

Zhang Yudong, Wu Lenan, Wei Geng. Research on Neural Network Generalization Enhancement Technology. Science Technology and Engineering, 2009, 9(17): 4997-5002.