Top > JACIII > Deep Convolutional Neural Networks Based on Knowledge Distilla ...

single-jc.php

JACIII Vol.28 No.2 pp. 231-238
doi: 10.20965/jaciii.2024.p0231
(2024)

Research Paper:

Views over last 60 days: 501

Deep Convolutional Neural Networks Based on Knowledge Distillation for Offline Handwritten Chinese Character Recognition

Hongli He* ORCID Icon, Zongnan Zhu** ORCID Icon, Zhuo Li*** ORCID Icon, and Yongping Dan**,† ORCID Icon

*Rail Transit Institute, Henan College of Transportation
No.259 Tonghui Road, Baisha Vocational Education Park, Zhengdong New District, Zhengzhou 450061, China

**School of Electronic and Information, Zhongyuan University of Technology
No.41 Zhongyuan Road, Zhengzhou 450007, China

†Corresponding author

***Graduate School of Science and Engineering, Ritsumeikan University
1-1-1 Noji-higashi, Kusatsu, Shiga 525-8577, Japan

Received:
December 8, 2022
Accepted:
July 6, 2023
Published:
March 20, 2024
Creative Commons License
Keywords:
deep convolutional neural networks, handwritten Chinese character recognition, attention mechanism, knowledge distillation
Abstract

Deep convolutional neural networks (DNNs) have achieved outstanding performance in this field. Meanwhile, handwritten Chinese character recognition (HCCR) is a challenging area of research in the field of computer vision. DNNs require a large number of parameters and high memory consumption. To address these issues, this paper proposes an approach based on an attention mechanism and knowledge distillation. The attention mechanism improves the feature extraction and the knowledge distillation reduces the number of parameters. The experimental results show that ResNet18 achieves a recognition accuracy of 97.63% on the HCCR dataset with 11.25 million parameters. Compared with other methods, this study improves the performance for HCCR.

Cite this article as:
H. He, Z. Zhu, Z. Li, and Y. Dan, “Deep Convolutional Neural Networks Based on Knowledge Distillation for Offline Handwritten Chinese Character Recognition,” J. Adv. Comput. Intell. Intell. Inform., Vol.28 No.2, pp. 231-238, 2024.
Data files:
References
  1. [1] C.-L. Liu, “High Accuracy Handwritten Chinese Character Recognition Using Quadratic Classifiers with Discriminative Feature Extraction,” 18th Conf. on Pattern Recognition (ICPR’06), Vol.2, pp. 942-945, 2006. https://doi.org/10.1109/ICPR.2006.624
  2. [2] T. H. Hildebrandt and W. Liu, “Optical Recognition of Handwritten Chinese Characters: Advances Since 1980,” Pattern Recognition, Vol.26, pp. 205-225, 1993. https://doi.org/10.1016/0031-3203(93)90030-Z
  3. [3] X. Zhang, Y. Bengio, and C. Liu, “Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark,” Pattern Recognition, Vol.61, pp. 348-360, 2016. https://doi.org/10.1016/j.patcog.2016.08.005
  4. [4] R. Dai, C. Liu, and B. Xiao, “Chinese Character Recognition: History, Status and Prospects,” Frontiers of Computer Science in China, Vol.1, No.2, pp. 126-136, 2007. https://doi.org/10.1007/s11704-007-0012-5
  5. [5] C.-L. Liu, F. Yin, D.-H. Wang, and Q.-F. Wang, “Online and Offline Handwritten Chinese Character Recognition: Benchmarking on New Databases,” Pattern Recognition, Vol.46, No.1, pp. 155-162, 2013. https://doi.org/10.1016/j.patcog.2012.06.021
  6. [6] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet Classification with Deep Convolutional Neural Networks,” Communications of the ACM, Vol.60, No.6, pp. 84-90, 2017. https://doi.org/10.1145/3065386
  7. [7] K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” arXiv:1409.1556, 2015. https://doi.org/10.48550/arXiv.1409.1556
  8. [8] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going Deeper with Convolutions,” 2015 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 1-9, 2015. https://doi.org/10.1109/CVPR.2015.7298594
  9. [9] K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” 2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 770-778, 2016. https://doi.org/10.1109/CVPR.2016.90
  10. [10] H. Li, Z. Wang, X. Yue, W. Wang, T. Hiroyuki, and L. Meng, “A Comprehensive Analysis of Low-Impact Computations in Deep Learning Workloads,” Proc. of the 2021 on Great Lakes Symp. on VLSI (GLSVLSI’21), pp. 385-390, 2021. https://doi.org/10.1145/3453688.3461747
  11. [11] W. Park, D. Kim, Y. Lu, and M. Cho, “Relational Knowledge Distillation,” Proc. of the IEEE/CVF Conf. on Computer Vision and Pattern Recognition, pp. 3967-3976, 2019. https://doi.org/10.1109/CVPR.2019.00409
  12. [12] R. Z. Tan, X. Chew, and K. W. Khaw, “Neural Architecture Search for Lightweight Neural Network in Food Recognition,” Mathematics, Vol.9, No.11, Article No.1245, 2021. https://doi.org/10.3390/math9111245
  13. [13] G. Hinton, O. Vinyals, and J. Dean, “Distilling the knowledge in a neural network,” arXiv:1503.02531, 2015. https://doi.org/10.48550/arXiv.1503.02531
  14. [14] Z. Huang and N. Wang, “Like What You Like: Knowledge Distill via Neuron Selectivity Transfer,” arxiv:1707.01219, 2017. https://doi.org/10.48550/arXiv.1707.01219
  15. [15] S. Zagoruyko and N. Komodakis, “Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer,” Int. Conf. on Learning Representations, pp. 24-26, 2017.
  16. [16] J. Yim, D. Joo, J. Bae, and J. Kim, “A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning,” Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, pp. 4133-4141, 2017. https://doi.org/10.1109/CVPR.2017.754
  17. [17] H. Bagherinezhad, M. Horton, M. Rastegari, and A. Farhadi, “Label Refinery: Improving ImageNet Classification Through Label Progression,” arXiv:1805.02641, 2018. https://doi.org/10.48550/arXiv.1805.02641
  18. [18] S. Lai, L. Jin, and W. Yang, “Toward high-performance online HCCR: A CNN approach with DropDistortion, path signature and spatial stochastic max-pooling,” Pattern Recognition Letters, Vol.89, pp. 60-66, 2017. https://doi.org/10.1016/j.patrec.2017.02.011
  19. [19] R. Sharma and B. Kaushik, “Offline Recognition of Handwritten Indic Scripts: A State-of-the-Art Survey and Future Perspectives,” Computer Science Review, Vol.38, Article No.100302, 2020. https://doi.org/10.1016/j.cosrev.2020.100302
  20. [20] Q. Hao, X. Wu, S. Zhang, P. Zhang, X. Ma, and J. Jiang, “Research on Offline Handwritten Chinese Character Recognition Based on Deep Learning,” 2019 9th Int. Conf. on Formation Science and Technology (ICIST), pp. 470-474, 2019. https://doi.org/10.1109/ICIST.2019.8836833
  21. [21] W. Luo and S. I. Kamata, “Radical Region-Based CNN for Offline Handwritten Chinese Character Recognition,” Proc. of the 2017 4th IAPR Asian Conf. on Pattern Recognition (ACPR), pp. 542-547, 2017. https://doi.org/10.1109/ACPR.2017.76
  22. [22] Y. Ge, Q. Huo, and Z.-D. Feng, “Offline Recognition of Handwritten Chinese Characters Using Gabor Features, CDHMM Modeling and MCE Training,” Proc. of the Conf. on Acoustics, Speech and Signal Processing (CASSP’02), pp. I-1053-I-1056, 2002. https://doi.org/10.1109/ICASSP.2002.5743976
  23. [23] C.-L. Liu, “Normalization-Cooperated Gradient Feature Extraction for Handwritten Character Recognition,” IEEE Trans. on Pattern Analysis and Machine Int., Vol.29, No.8, pp. 1465-1469, 2007. https://doi.org/10.1109/TPAMI.2007.1090
  24. [24] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, Vol.521, Article No.7553, pp. 436-444, 2015. https://doi.org/10.1038/nature14539
  25. [25] Z. Zhong, X.-Y. Zhang, F. Yin, and C.-L. Liu, “Handwritten Chinese Character Recognition with Spatial Transformer and Deep Residual Networks,” 2016 23rd Int. Conf. on Pattern Recognition (ICPR), pp. 3440-3445, 2016. https://doi.org/10.1109/ICPR.2016.7900166
  26. [26] N. Bi, J. Chen, and J. Tan, “The Handwritten Chinese Character Recognition Uses Convolutional Neural Networks with the GoogLeNet,” J. of Pattern Recognition and Artificial Intelligence, Vol.33, No.11, Article No.1940016, 2019. https://doi.org/10.1142/S0218001419400160
  27. [27] P. Melnyk, Z. You, and K. Li, “A High-Performance CNN Method for Offline Handwritten Chinese Character Recognition and Visualization,” Soft Computing, Vol.24, No.11, pp. 7977-7987, 2020. https://doi.org/10.1007/s00500-019-04083-3
  28. [28] Z. Li, Q. Wu, Y. Xiao, M. Jin, and H. Lu, “Deep Matching Network for Handwritten Chinese Character Recognition,” Pattern Recognition, Vol.107, Article No.107471, 2020. https://doi.org/10.1016/j.patcog.2020.107471
  29. [29] Y. Dan and Z. Li, “Particle Swarm Optimization-Based Convolutional Neural Network for Handwritten Chinese Character Recognition,” J. Adv. Comput. Intell. Intell. Inform., Vol.27, No.2, pp. 165-172, 2023. https://doi.org/10.20965/jaciii.2023.p0165
  30. [30] M. H. Sadi and A. Mahani, “Accelerating Deep Convolutional Neural Network Base on Stochastic Computing,” Integration, Vol.76, pp. 113-121, 2021. https://doi.org/10.1016/j.vlsi.2020.09.008
  31. [31] N. Passalis and A. Tefas, “Training Lightweight Deep Convolutional Neural Networks Using Bag-of-Features Pooling,” IEEE Trans. on Neural Networks and Learning Systems, Vol.30, No.6, pp. 1705-1715, 2019. https://doi.org/10.1109/TNNLS.2018.2872995
  32. [32] C. Buciluǎ, R. Caruana, and A. Niculescu-Mizil, “Model Compression,” Proc. of the 12th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD’06), pp. 535-541, 2006. https://doi.org/10.1145/1150402.1150464
  33. [33] J. Ba and R. Caruana, “Do Deep Nets Really Need to Be Deep?,” Advances in Neural Information Processing Systems, Vol.3, pp. 2654-2662, 2014.
  34. [34] Z. Xu, Y.-C. Hsu, and J. Huang, “Training Shallow and Thin Networks for Acceleration via Knowledge Distillation with Conditional Adversarial Networks,” arXiv:1709.00513, 2017. https://doi.org/10.48550/arXiv.1709.00513
  35. [35] S. Sun, Y. Cheng, Z. Gan, and J. Liu, “Patient Knowledge Distillation for BERT Model Compression,” arXiv:1908.09355, 2019. https://doi.org/10.48550/arXiv.1908.09355
  36. [36] G. Ros, S. Stent, P. F. Alcantarilla, and T. Watanabe, “Training Constrained Deconvolutional Networks for Road Scene Semantic Segmentation,” arXiv:1604.01545, 2016. https://doi.org/10.48550/arXiv.1604.01545
  37. [37] P. Luo, Z. Zhu, Z. Liu, X. Wang, and X. Tang, “Face Model Compression by Distilling Knowledge from Neurons,” Proc. of the AAAI Conf. on Artificial Intelligence, Vol.30, No.1, 2016. https://doi.org/10.1609/aaai.v30i1.10449
  38. [38] G. Chen, W. Choi, X. Yu, T. Han, and M. Chandraker, “Learning Efficient Object Detection Models with Knowledge Distillation,” Proc. of the 31st Int. Conf. on Neural Information Processing Systems, pp. 742-751, 2017.
  39. [39] J. Shen, N. Vesdapunt, V. N. Boddeti, and K. M. Kitani, “In Teacher We Trust: Learning Compressed Models for Pedestrian Detection,” arxiv:1612.00478, 2016. https://doi.org/10.48550/arXiv.1612.00478
  40. [40] Y. Teh, V. Bapst, W. M. Czarnecki, J. Quan, J. Kirkpatrick, R. Hadsell, N. Heess, and R. Pascanu, “Distral: Robust Multitask Reinforcement Learning,” Proc. of the 31st Int. Conf. on Neural Information Processing Systems, pp. 4499-4509, 2017.

Creative Commons License  This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Mar. 18, 2025