Improving OCR Accuracy for Kazakh Handwriting Recognition Using GAN Models
Source abstract
Abstract
This paper aims to increase the accuracy of Kazakh handwriting text recognition (KHTR) using the generative adversarial network (GAN), where a handwriting word image generator and an image quality discriminator are constructed. In order to obtain a high-quality image of handwritten text, the multiple losses are intended to encourage the generator to learn the structural properties of the texts. In this case, the quality discriminator is trained on the basis of the relativistic loss function. Based on the proposed structure, the resulting document images not only preserve texture details but also generate different writer styles, which provides better OCR performance in public databases. With a self-created dataset, images of different types of handwriting styles were obtained, which will be used when training the network. The proposed approach allows for a character error rate (CER) of 11.15% and a word error rate (WER) of 25.65%.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Handwritten Text Recognition Techniques · Image Processing and 3D Reconstruction · Vehicle License Plate Recognition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Information Technology, Department of Computer Science, Al Farabi Kazakh National University, Almaty 050010, Kazakhstan
Institute of Information and Computational Technologies, Almaty 050010, Kazakhstan
Funding
Ministry of Science and Higher Education of the Republic of Kazakhstan
References (36)
Show source-provided references
1. An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition10.1109/TPAMI.2016.2646371 ↗
2. Tran, B.H., Le-Cong, T., Nguyen, H.M., Le, D.A., Nguyen, T.H., and Le Nguyen, P. (2020). SAFL: A Self-Attention Scene Text Recognizer with Focal Loss. arXiv.10.1109/ICMLA51294.2020.00223 ↗
3. Metzenthin, E., Bartz, C., and Meinel, C. (2022). Weakly Supervised Scene Text Detection using Deep Reinforcement Learning. arXiv.
4. (2023, April 25). Available online: https://astanatimes.com/2017/10/kazakhstan-to-switch-to-latin-alphabet-by-2025.
5. Development and implementation of a morphological model of kazakh language
6. Dash, A., Ye, J., and Wang, G. (2021). A review of Generative Adversarial Networks (GANs) and its applications in a wide variety of disciplines—From Medical to Remote Sensing. arXiv.
7. Forging new worlds: High-resolution synthetic galaxies with chained generative adversarial networks10.1093/mnras/stz602 ↗
8. Laino, M.E., Cancian, P., Politi, L.S., Della Porta, M.G., Saba, L., and Savevski, V. (2022). Generative Adversarial Networks in Brain Imaging: A Narrative Review. J. Imaging, 8.10.3390/jimaging8040083 ↗
9. Review on Generative Adversarial Networks: Focusing on Computer Vision and Its Applications10.3390/electronics10101216 ↗
10. Generation of artificial chest X-ray images using generative-adversarial neural networks
11. Fogel, S., Averbuch-Elor, H., Cohen, S., Mazor, S., and Litman, R. (2020, January 13–19). ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00438 ↗
12. Shonenkov, A., Karachev, D., and Novopoltsev, M. (2021). StackMix and Blot Augmentations for Handwritten Text Recognition. Comput. Vis. Pattern Recognit.
13. Classification at incomplete training information: Usage of clustering group to improve performance
14. An easy-to-explain decision support framework for forensic analysis of dynamic signatures10.1016/j.fsidi.2021.301216 ↗
15. A two-tier ensemble approach for writer dependent online signature verification10.1007/s12652-020-02872-5 ↗
16. COMPOSV: Compound feature extraction and depthwise separable convolution-based online signature verification10.1007/s00521-022-07018-6 ↗
17. Sumeet, S. (2021). Book: Document Analysis and Recognition, ICDAR.
18. A Comparison of Convolutional Neural Networks for Kazakh Sign Language Recognition
19. Buribayev, Z., Merembayev, T., Amirgaliyev, Y., and Miyachi, T. (2021, January 28–30). The Optimized Distance Calculation Method with Stereo Camera for an Autonomous Tomato Harvesting. Proceedings of the 2021 IEEE International Conference on Smart Information Systems and Technologies (SIST), Nur-Sultan, Kazakhstan.10.1109/SIST50301.2021.9465944 ↗
20. Amirgaliyev, Y., Shamiluulu, S., Merembayev, T., and Yedilkhan, D. (2019, January 8–12). Using machine learning algorithm for diagnosis of stomach disorders. Proceedings of the Mathematical Optimization Theory and Operations Research: 18th International Conference, MOTOR 2019, Ekaterinburg, Russia.10.1007/978-3-030-33394-2_27 ↗
21. Daiyrbayeva, E., Yerimbetova, A., Nechta, I., Merzlyakova, E., Toigozhinova, A., and Turganbayev, A. (2022). A Study of the Information Embedding Method into Raster Image Based on Interpolation. J. Imaging, 8.10.3390/jimaging8100288 ↗
22. Soil Salinity Classification Using Machine Learning Algorithms and Radar Data in the Case from the South of Kazakhstan10.12911/22998993/152281 ↗
23. Jin, T., Zhuang, J., Xiao, J., Xu, N., and Qin, S. (2023). Reconstructing Floorplans from Point Clouds Using GAN. J. Imaging, 9.10.3390/jimaging9020039 ↗
24. Wright, J., Ganesh, A., Rao, S., Peng, Y., and Ma, Y. (2009). Advances in Neural Information Processing Systems, Curran Associates.
25. Tran, N.T., Bui, T.A., and Cheung, N.M. (2018). Book Chapter, ECCV.
26. Campilho, A., Karray, F., and Wang, Z. (2020). Image Analysis and Recognition, Springer. ICIAR 2020; Lecture Notes in Computer Science.10.1007/978-3-030-50347-5 ↗
27. Shlens, J. (2014). Notes on Kullback-Leibler Divergence and Likelihood Computer Science. arXiv.
28. Ho, Y., and Wookey, S. (2020). The Human Visual System and Adversarial AI//Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Image and Video Processing (eess.IV). arXiv.
29. Kazakh handwritten recognition
30. Krishnan, P., Kovvuri, R., Pang, G., Vassilev, B., and Hassner, T. (2021). TextStyleBrush: Transfer of Text Aesthetics from a Single Example. IEEE Trans. Pattern Anal. Mach. Intell.
31. Huang, X., and Belongie, S. (2017, January 22–29). Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization. Proceedings of the IEEE, International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.167 ↗
32. Karras, T., Laine, S., and Aila, T. (2019, January 16–17). A Style-Based Generator Architecture for Generative Adversarial Networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00453 ↗
33. Brock, A., Donahue, J., and Simonyan, K. (2018). Large Scale GAN Training for High Fidelity Natural Image Synthesis. arXiv.
34. Li, M., Lv, T., Chen, J., Cui, L., Lu, Y., Florencio, D., Zhang, C., Li, Z., and Wei, F. (2021). TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models. arXiv.
35. Calamari—A High-Performance Tensorflowbased Deep Learning Package for Optical Character Recognition
36. Hamada, M.A., Sultanbek, K., Alzhanov, B., and Tokbanov, B. (2019, January 6–8). Sentimental text processing tool for russian language based on machine learning algorithms. Proceedings of the ICEMIS’19: The 5th International Conference on Engineering & MIS, Astana, Kazakhstan.10.1145/3330431.3335204 ↗