Korean Journal of Artificial Intelligence (한국인공지능학회지)

Korea Artificial Intelligence Association (한국인공지능학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Improving License Plate Recognition Performance Using Super-Resolution Techniques

  • Kyeongseok JANG (Department of Plasma Bio Display, Kwangwoon University) ;
  • Kwangchul SON (Department of Smart Electrical and Electronic Engineering, Kwangwoon University)
  • Received : 2024.07.29
  • Accepted : 2024.09.05
  • Published : 2024.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose an innovative super-resolution technique to address the issue of reduced accuracy in license plate recognition caused by low-resolution images. Conventional vehicle license plate recognition systems have relied on images obtained from fixed surveillance cameras for traffic detection to perform vehicle detection, tracking, and license plate recognition. However, during this process, image quality degradation occurred due to the physical distance between the camera and the vehicle, vehicle movement, and external environmental factors such as weather and lighting conditions. In particular, the acquisition of low-resolution images due to camera performance limitations has been a major cause of significantly reduced accuracy in license plate recognition. To solve this problem, we propose a Single Image Super-Resolution (SISR) model with a parallel structure that combines Multi-Scale and Attention Mechanism. This model is capable of effectively extracting features at various scales and focusing on important areas. Specifically, it generates feature maps of various sizes through a multi-branch structure and emphasizes the key features of license plates using an Attention Mechanism. Experimental results show that the proposed model demonstrates significantly improved recognition accuracy compared to existing vehicle license plate super-resolution methods using Bicubic Interpolation.

Keywords

Acknowledgement

This work was conducted during the sabbatical leave with support from Kwangwoon University in 2023.

References

  1. Arica, N., & Yarman-Vural, F. T. (2002). Optical character recognition for cursive handwriting. IEEE transactions on pattern analysis and machine intelligence, 24(6), 801-813.
  2. Bugeja, M., Dingli, A., Attard, M., & Seychell, D. (2020). Comparison of vehicle detection techniques applied to IP camera video feeds for use in intelligent transport systems. Transportation Research Procedia, 45, 971-978.
  3. Cai, W., & Wei, Z. (2020). Remote sensing image classification based on a cross-attention mechanism and graph convolution. IEEE Geoscience and Remote Sensing Letters, 19, 1-5.
  4. Chen, Y., Peng, G., Zhu, Z., & Li, S. (2020). A novel deep learning method based on attention mechanism for bearing remaining useful life prediction. Applied Soft Computing, 86, 105919.
  5. Cui, X., Wang, Q., Dai, J., Xue, Y., & Duan, Y. (2021). Intelligent crack detection based on attention mechanism in convolution neural network. Advances in Structural Engineering, 24(9), 1859-1868.
  6. Dong, C., Loy, C. C., He, K., & Tang, X. (2014). Learning a deep convolutional network for image super-resolution. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part IV 13 (pp. 184-199). Springer International Publishing.
  7. Drobac, S., & Linden, K. (2020). Optical character recognition with neural networks and post-correction with finite state methods. International Journal on Document Analysis and Recognition (IJDAR), 23(4), 279-295.
  8. Dui, H., Zhang, S., Liu, M., Dong, X., & Bai, G. (2024). IoT-enabled real-time traffic monitoring and control management for intelligent transportation systems. IEEE Internet of Things Journal.
  9. El Bahi, H., & Zatni, A. (2019). Text recognition in document images obtained by a smartphone based on deep convolutional and recurrent neural network. Multimedia tools and applications, 78(18), 26453-26481.
  10. Guerrero-Ibanez, J., Contreras-Castillo, J., & Zeadally, S. (2021). Deep learning support for intelligent transportation systems. Transactions on Emerging Telecommunications Technologies, 32(3), e4169.
  11. Hassan, T., El-Mowafy, A., & Wang, K. (2021). A review of system integration and current integrity monitoring methods for positioning in intelligent transport systems. IET Intelligent Transport Systems, 15(1), 43-60.
  12. Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., ... & Shi, W. (2017). Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4681-4690).
  13. Lieskovska, E., Jakubec, M., Jarina, R., & Chmulik, M. (2021). A review on speech emotion recognition using deep learning and attention mechanism. Electronics, 10(10), 1163.
  14. Liu, Y., Shao, Z., & Hoffmann, N. (2021). Global attention mechanism: Retain information to enhance channel-spatial interactions. arXiv preprint arXiv:2112.05561.
  15. Memon, J., Sami, M., Khan, R. A., & Uddin, M. (2020). Handwritten optical character recognition (OCR): A comprehensive systematic literature review (SLR). IEEE access, 8, 142642-142668.
  16. Ngeni, F. C., Mwakalonge, J. L., Comert, G., Siuhi, S., & Vaidyan, V. (2022). Monitoring of Illegal Removal of Road Barricades Using Intelligent Transportation Systems in Connected and Non-Connected Environments.
  17. Qiu, L., Zhang, D., Tian, Y., & Al-Nabhan, N. (2021). Deep learning-based algorithm for vehicle detection in intelligent transportation systems. The Journal of Supercomputing, 77(10), 11083-11098.
  18. Qiu, M., Christopher, L., Chien, S. Y. P., & Chen, Y. (2024). Intelligent Highway Adaptive Lane Learning System in Multiple ROIs of Surveillance Camera Video. IEEE Transactions on Intelligent Transportation Systems.
  19. Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D. J., & Norouzi, M. (2022). Image super-resolution via iterative refinement. IEEE transactions on pattern analysis and machine intelligence, 45(4), 4713-4726.
  20. Salvetti, F., Mazzia, V., Khaliq, A., & Chiaberge, M. (2020). Multi-image super resolution of remotely sensed images using residual attention deep neural networks. Remote Sensing, 12(14), 2207.
  21. Woo, S., Park, J., Lee, J. Y., & Kweon, I. S. (2018). Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV) (pp. 3-19).
  22. Yang, J., Wright, J., Huang, T. S., & Ma, Y. (2010). Image super-resolution via sparse representation. IEEE transactions on image processing, 19(11), 2861-2873.