DOI QR코드

DOI QR Code

Semi-Supervised Learning Based Anomaly Detection for License Plate OCR in Real Time Video

  • Kim, Bada (Department of Computer Engineering, Hansung University) ;
  • Heo, Junyoung (Department of Computer Engineering, Hansung University)
  • Received : 2020.01.21
  • Accepted : 2020.01.30
  • Published : 2020.03.31

Abstract

Recently, the license plate OCR system has been commercialized in a variety of fields and preferred utilizing low-cost embedded systems using only cameras. This system has a high recognition rate of about 98% or more for the environments such as parking lots where non-vehicle is restricted; however, the environments where non-vehicle objects are not restricted, the recognition rate is about 50% to 70%. This low performance is due to the changes in the environment by non-vehicle objects in real-time situations that occur anomaly data which is similar to the license plates. In this paper, we implement the appropriate anomaly detection based on semi-supervised learning for the license plate OCR system in the real-time environment where the appearance of non-vehicle objects is not restricted. In the experiment, we compare systems which anomaly detection is not implemented in the preceding research with the proposed system in this paper. As a result, the systems which anomaly detection is not implemented had a recognition rate of 77%; however, the systems with the semi-supervised learning based on anomaly detection had 88% of recognition rate. Using the techniques of anomaly detection based on the semi-supervised learning was effective in detecting anomaly data and it was helpful to improve the recognition rate of real-time situations.

Acknowledgement

Supported by : Korea Agency for Infrastructure Technology Advancement(KAIA)

References

  1. Cho, Wooyeong, et al., "A Comparative Study on OCR using Super-Resolution for Small Fonts," International journal of advanced smart convergence, Vol. 8, No.3, pp. 95-101, Oct 2019. DOI: https://doi.org/10.7236/IJASC.2019.8.3.95 https://doi.org/10.7236/ijasc.2019.8.3.95
  2. Zhong, Z., Jin, L., and Xie, Z., "High performance offline handwritten chinese character recognition using googlenet and directional feature maps," International Conference on Document Analysis and Recognition (ICDAR), IEEE, pp.846-850, Aug 2015. DOI: https://doi.org/10.1109/ICDAR.2015.7333881
  3. Lee, S., Son, K., Kim, H., and Park, J, "Car plate recognition based on CNN using embedded system with GPU," In 2017 10th International Conference on Human System Interactions (HSI), pp. 239-241, Jul 2017. DOI: https://doi.org/10.1109/HSI.2017.8005037
  4. ETRI, Purpose and Necessity of Technology Transfer. https://itec.etri.re.kr/itec/sub02/sub02_01_1.do?t_id=7101- 2018-01492.
  5. Lopresti, D, “Optical character recognition errors and their effects on natural language processing,” International Journal on Document Analysis and Recognition (IJDAR), Vol. 12, No. 3, pp. 141-151, Sep 2009. DOI: https://doi.org/10.1007/s10032-009-0094-8 https://doi.org/10.1007/s10032-009-0094-8
  6. Sonavane, Kiran, Badal Soni, and Umakanta Majhi. "Survey on Automatic Number Plate Recognition (ANR)," International Journal of Computer Applications, Vol. 125, No.6, Sep 2015. DOI: https://doi.org/10.5120/ijca2015905920
  7. Jung-Hwan Kim and Joon-Hong Lim, “License Plate Detection and Recognition Algorithm using Deep Learning,” The Journal of Institute of Electrical and Electronic Engineers, Vol. 23, No. 2, pp. 642-651, June 2019. DOI: https://doi.org/10.7471/ikeee.2019.23.2.642
  8. Ahmed, Mohiuddin, Abdun Naser Mahmood, and Jiankun Hu. "A survey of network anomaly detection techniques," Journal of Network and Computer Applications, Vol. 60, pp. 19-31, Jan 2016. DOI: https://doi.org/10.1016/j.jnca.2015.11.016 https://doi.org/10.1016/j.jnca.2015.11.016
  9. Park, Chang-Mok. "Dam Sensor Outlier Detection using Mixed Prediction Model and Supervised Learning." International journal of advanced smart convergence, Vol. 7, No. 1, pp. 24-32, Mar 2018. DOI: https://doi.org/10.7236/IJASC.2018.7.1.4 https://doi.org/10.7236/IJASC.2018.7.1.4
  10. Gornitz, Nico, et al. "Toward supervised anomaly detection," Journal of Artificial Intelligence Research, Vol. 46, pp. 235-262, Feb 2013. DOI: https://doi.org/10.1613/jair.3623 https://doi.org/10.1613/jair.3623
  11. Haeusser, P., Mordvintsev, A., & Cremers, D, "Learning by Association-A Versatile Semi-Supervised Training Method for Neural Networks," In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 89-98, Jul 2017. DOI: https://doi.org/10.1109/CVPR.2017.74
  12. Ministry of Land, Infrastructure and Transport, Notice on the Standard of Registration Number Plate. http://www.law.go.kr/admRulLsInfoP.do?admRulSeq=2100000176243.
  13. Iandola, Forrest N., et al. "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size," arXiv preprint arXiv:1602.07360, Feb 2016. arXiv: https://arxiv.org/abs/1602.07360
  14. Jang, Eric, Shixiang Gu, and Ben Poole. "Categorical reparameterization with gumbel-softmax," arXiv preprint arXiv:1611.01144, Nov 2016. arXiv: https://arxiv.org/abs/1611.01144