Keywords
Multi-feature fusion
Machine learning
Submitted : 2024-09-15
Accepted : 2024-09-30
Published : 2024-10-15
Abstract
This paper analyzes the progress of handwritten Chinese character recognition technology, from two perspectives: traditional recognition methods and deep learning-based recognition methods. Firstly, the complexity of Chinese character recognition is pointed out, including its numerous categories, complex structure, and the problem of similar characters, especially the variability of handwritten Chinese characters. Subsequently, recognition methods based on feature optimization, model optimization, and fusion techniques are highlighted. The fusion studies between feature optimization and model improvement are further explored, and these studies further enhance the recognition effect through complementary advantages. Finally, the article summarizes the current challenges of Chinese character recognition technology, including accuracy improvement, model complexity, and real-time problems, and looks forward to future research directions.
References
Li Y, 2022, Analysis on the Research Progress of Chinese Character Recognition Technology. Science Technology and Industry, 2022(004): 022.
Li LY, Zhou ZG, Chen DY, 2020, Offline Handwritten Chinese Character Recognition Based on DBN and CNN Fusion Model. Journal of Harbin University of Science and Technology, 25(3): 7. https://doi.org/10.15938/j.jhust.2020.03.021
Wang ZR, Du J, 2016, Writer Code Based Adaptation of Deep Neural Network for Offline Handwritten Chinese Text Recognition. 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), 2016: 548–553. https://doi.org/10.1109/ICFHR.2016.0106
Lin H, 2021, Offline Handwritten Chinese Character Recognition Based on Convolutional Neural Network. Journal of Hubei Polytechnic University, 2021(2019-2): 31–34.
Liu CL, Yin F, Wang DH, et al., 2013, Online and Offline Handwritten Chinese Character Recognition: Benchmarking on New Databases. Pattern Recognition, 46(1): 155–162. https://doi.org/10.1016/j.patcog.2012.06.021
Lecun Y, Bengio Y, 1998, Convolutional Networks for Images, Speech, and Time Series. The Handbook of Brain Theory and Neural Networks, MIT Press, Massachusetts.
Ren J, Li ZN, 2005, Application of Support Vector Machines in Classification and Recognition of Characters. Journal of Zhejiang University (Engineering Science), 39(8): 6. https://doi.org/10.3785/j.issn.1008-973X.2005.08.009
Jia Z, Han B, Gao X, 2015, 2DPCANet: Dayside Aurora Classification Based on Deep Learning. In Computer Vision, CCCV 2015, Communications in Computer and Information Science, vol 547. Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-662-48570-5_32
Zhou Q, Chen J, Ji P, 2016, The Technology of Multiple Features Handwritten Chinese Character Recognition Based on SVM. Electronic Sci. & Tech, 29(8): 4. https://doi.org/10.16180/j.cnki.issn1007-7820.2016.08.040
Yu J, 2018, Research on Original Handwriting Extraction and Chinese Character Recognition based on Computer Vision, thesis, Central China Normal University.
Tao XJ, Lu J, 2019, Chinese Character Recognition in Complex Images Based on Improved SURF Descriptor Features and Fuzzy Reasoning. Computers and Modernization, 2019(4): 4.
Gan H, Lai S, Zhang S, et al., 2022, A Study on Coarse Classification of Offline Handwritten Chinese Characters based on Optimized Binary Tree SVM. Electronic Technology & Software Engineering, 2022(008): 000.
Zhu Y, Zhao Y, Tang N, et al., 2023, The Role of Stroke Nodes in the Recognition of Handwritten Chinese Characters. Acta Psychologica Sinica, 55(12): 1903–1916. https://doi.org/10.3724/SP.J.1041.2023.01903
Tang S, Liang SJ, Dai F, et al., 2024, Graph Feature Extraction Method in Chinese Character Recognition. Science Technology and Engineering, 24(2): 658–664.
Wu C, Fan W, He Y, et al., 2014, Handwritten Character Recognition by Alternately Trained Relaxation Convolutional Neural Network. 14th International Conference on Frontiers in Handwriting Recognition, 2014: 291–296. https://doi.org/10.1109/ICFHR.2014.56
Li Z, Wang C, Song Z, et al., 2019, Enhanced Handwritten Chinese Characters Image Recognition Based on CNN Model. Fire Control & Command Control, 44 (4): 169–172.
Chen Z, Qiu W, Zhang L, 2020, Offline Handwritten Chinese Character Recognition based on Improved Inception. Application Research of Computers, 37(4): 4. https://doi.org/10.19734/j.issn.1001-3695.2018.09.0784
Cui Z, Bai Y, Han Y, et al., 2021, Handwritten Chinese Character Recognition System based on Hopfield Network. Journal of North China University of Science and Technology (Natural Science Edition), 043(002): 123–131.
Wang JH, Zhang YQ, Xiao BY, et al, 2023, Research on Handwritten Chinese Character Recognition Based on Improved Convolutional Neural Networ. Printing and Digital Media Technology Study, 2023(1): 45–56.
Yue Z, 2018, Offline Handwritten Chinese Character Recognition Algorithm Based on PSO and BP Neural Network. Informatization Research, 44(2): 3.
Qin C, Zheng P, Zhang X, 2020, Offline Handwritten Chinese Character Recognition based on MQDF-DBM Model. Computer Engineering and Applications, 56(7): 141–146.
Xu Q, 2022, Handwritten Chinese Character Recognition based on Improved Convolutional Neural Network. Electronic Technology & Software Engineering, 2022(009): 000.
Cheng R, Zhou H, Liu L, et al., 2022, Offline Handwritten Chinese Character Recognition based on Improved MobileNetV3. Intelligent Computer and Applications, 12(7): 5.
Guo X, Zhao X, Zou S, 2024, Handwritten Words Image Character Extraction Adaptive Algorithm Based on the Multi-branch Structure. Advanced Engineering Sciences, 2024: 1–11. https://doi.org/10.15961/j.jsuese.202300579
Mao X, Cheng Z, Zhou X, 2018, Offline Handwritten Chinese Character Recognition Based on Concatenated Feature Maps. Journal of Zhengzhou University (Nat. Sci. Ed.), 50(3): 5. https://doi.org/10.13705/j.issn.1671-6841.2017314
Wei B, Xie H, Deng X, 2019, Handwritten Chinese Character Recognition based on Multimodel Hypergraph. Computer Applications and Software, 36(7): 6. https://doi.org/10.3969/j.issn.1000-386x.2019.07.032
Li G, Zhou He, Ma K, et al., 2020, Feature Grouping Extraction Fusion of Deep Network Offline Handwritten Chinese Character Recognition. Computer Engineering and Applications, 56(12): 163–168.
Zheng Y, Han M, Fan W, 2020, Handwritten Chinese Character Recognition based on Two Dimensional Principal Component Analysis and Convolutional Neural Network. Journal of Computer Applications, 40(8): 7.
Wu ZY, Liu LL, Zhang ZY, 2018, Chinese Character Recognition of Convolutional Neural Network of Integration Attention Layer. Computer Technology and Development, 28(8): 4. https://doi.org/10.3969/j.issn.1673-629X.2018.08.021
Yang J, 2018, Research on Handwritten Chinese Character Recognition based on Convolutional Neural Network. Information Technology and Informatization, 2018(12): 3.
Ren X, Wang T, Li J, et al., 2019, Research on Handwritten Chinese Character Recognition based on Deep Learning with Different Noise. Application Research of Computers, 36(12): 4. https://doi.org/10.19734/j.issn.1001-3695.2018.06.0579
Huang Y, Tan Q, Shi X, 2019, Recognition of Similar Handwritten Chinese Characters Based on Eight-Direction Gradient Features and CNN. Information & Communications, 2019(4): 4. https://doi.org/10.3969/j.issn.1673-1131.2019.04.002
Zhou Y, Zhang S, 2020, Research on Chinese Character Recognition Based on Regionally Weighted LeNet-5 Network. Computer & Digital Engineering, 48(11): 6. https://doi.org/10.3969/j.issn.1672-9722.2020.11.029
Zhu CH, Shen F, Wang JP, et al., 2020, Approach for Off-Line Handwritten Chinese Characters Recognition based on Knowledge Transfer with Feedback. Transducer and Microsystem Technologies, 39(5): 5.
Zhou YC, Tan QH, Xi CL, 2021, Offline Handwritten Chinese Character Recognition of SqueezeNet and Dynamic Network Surgery. Journal of Chinese Computer Systems, 2021(042-003).
Tu C, Yi Y, Wang K, et al., 2023, Adaptive Multi-level Feature Fusion Based Scene Ancient Chinese Text Recognition. Geomatics and Information Science of Wuhan University. https://doi.org/10.13203/j.whugis20230176
Chen C, Jiang M, Zhang M, 2024, A Chinese Character Recognition Solution Based on Multidimensional Representation. Software Engineering, 27(08): 24–29.
Chen Y, Huang Z, 2018, Offline Handwritten Chinese Character Recognition based on Coarse and Fine-Grained Deep Learning. Journal of Wuzhou University, 28(3): 8.
Zhang XL, Zhou KX, Wei Q, et al., 2019, Multi-channel Cross Fusion Deep Resnet for Offline Handwritten Chinese Character Recognition. Journal of Chinese Computer Systems, 40(10): 4.
Hou J, Ni JC, 2020, Handwritten Chinese Characters Recognition based on GoogleNet. Communications Technology, 53(05): 1127–1132.
Wang T, 2021, Research on Text Recognition based on Dense Convolutional Network. Heilongjiang Science and Technology Information, 000(020): 89–90.
Guan X, Ding L, 2021, Handwritten Chinese Character Recognition based on the Fusion Model of Capsule Network and Deep Belief Network. Software Engineering, 24(10): 5.
Yang K, Huang S, 2021, Chinese Character Recognition Algorithm Based on K-means and RBF Neural Network. Computer & Digital Engineering, 49(7): 5. https://doi.org/10.3969/j.issn.1672-9722.2021.07.002
Zhang Z, Zhang X, 2022, Handwritten Chinese Character Recognition Algorithm based on Maximum Entropy Principle and Fusion Machine Learning. Electronic Technology and Software Engineering, 2022(016): 000.
Ma SL, Xu Y, 2024, Calligraphy character recognition method driven by Stacked Model. Acta Auto Matica Sinica, 50(5): 947–957.