Skip to main content
SpringerLink
Log in

An Approach of Devanagari License Plate Detection and Recognition Using Deep Learning

  • Conference paper
  • First Online:
Advances in Computing and Data Sciences (ICACDS 2021)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1441))

Included in the following conference series:

Abstract

This paper proposes an automatic license plate recognition system for the Devanagari license plate (LP) in a static environment. The LP region is detected and localized using YOLOv3. The RGB mask of localized LP region is converted into HSV color space; and saturation mask of HSV color is processed using the CLAHE algorithm to segment unwanted regions from LP. The noise-free LP mask is acquired using different image preprocessing techniques. Skew correction is performed in the subsequent stage, followed by segmentation of LP characters using horizontal and vertical projection profiles. The characters are learned and predicted using a Convolution Neural Network (CNN). The CNN model is trained on the 19663 self-created Nepali LP character dataset. The proposed system has 99.2% accuracy on individual character recognition of LP characters and 95.5% accuracy on recognizing whole LP characters. The system is tested on both frontal and rear LPs of private two-wheelers and four-wheelers of Bagmati Zone.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 79.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 99.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Du, S., Ibrahim, M., Shehata, M., Badawy, W.: Automatic License Plate Recognition (ALPR): a state-of-the-art review. IEEE Trans. Circuits Syst. Video Technol. 23(2), 311–325 (2013)

    Article  Google Scholar 

  2. Pant, A.K., Gyawali, P.K., Acharya, S.: Automatic nepali number plate recognition with support vector machines. In: Proceedings of the 9th International Conference on Software, Knowledge, Information Management and Applications (SKIMA), pp. 92–99 (2015)

    Google Scholar 

  3. Muhammad, J., Altun, H.: Improved license plate detection using HOG-based features and genetic algorithm. In: 2016 24th Signal Processing and Communication Application Conference (SIU), pp. 1269–1272 (2016). https://doi.org/10.1109/SIU.2016.7495978

  4. Ahmad Yousef, K., Al-Tabanjah, M., Hudaib, E., Ikrai, M.: SIFT based automatic number plate recognition. In: International Conference on Information and Communication Systems. ICICS 2015, pp. 124–129 (2015). https://doi.org/10.1109/IACS.2015.7103214

  5. Bai, H., Liu, C.: A hybrid license plate extraction method based on edge statistics and morphology. In: Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004, vol. 2, pp. 831–834 (2004). https://doi.org/10.1109/ICPR.2004.1334387.

  6. Rabee, A., Barhumi, I.: License plate detection and recognition in complex scenes using mathematical morphology and support vector machines. In: IWSSIP 2014 Proceedings, pp. 59–62 (2014)

    Google Scholar 

  7. Martín-Rodríguez, F., García, M., Alba-Castro, J.L.: NEW METHODS FOR AUTOMATIC READING OF VLP’s (2002)

    Google Scholar 

  8. Azad, R., Davami, F., Azad, B.: A novel and robust method for automatic license plate recognition system based on pattern recognition. Adv. Comput. Sci. an Int. J. 2(3), 64–70 (2013)

    Google Scholar 

  9. Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Reading text in the wild with convolutional neural networks. Int. J. Comput. Vision 116(1), 1–20 (2015). https://doi.org/10.1007/s11263-015-0823-z

    Article  MathSciNet  Google Scholar 

  10. Wang, T., Wu, D.J., Coates, A., Ng, A.Y.: End-to-end text recognition with convolutional neural networks. In: Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), pp. 3304–3308 (2012)

    Google Scholar 

  11. Radzi, S.A., Khalil-Hani, M.: Character Recognition of License Plate Number Using Convolutional Neural Network. In: Zaman, H.B., et al. (eds.) Visual Informatics: Sustaining Research and Innovations, pp. 45–55. Springer Berlin Heidelberg, Berlin, Heidelberg (2011). https://doi.org/10.1007/978-3-642-25191-7_6

  12. Wang, Q., Gao, J., Yuan, Y.: A joint convolutional neural networks and context transfer for street scenes labeling. IEEE Trans. Intell. Transp. Syst. 19(5), 1457–1470 (2018). https://doi.org/10.1109/TITS.2017.2726546

  13. Silva, S.M., Jung, C.R.: Real-time license plate detection and recognition using deep convolutional neural networks. J. Vis. Commun. Image Represent. 71, 102773 (2020). https://doi.org/10.1016/j.jvcir.2020.102773

  14. Rabbani, G., Islam, M.A., Azim, M.A., Islam, M.K., Rahman, M.M.: bangladeshi license plate detection and recognition with morphological operation and convolution neural network. 2018 21st International Conference of Computer and Information Technology ICCIT 2018, pp. 1–5 (2019). https://doi.org/10.1109/ICCITECHN.2018.8631937

  15. Redmon, J., Farhadi, A.: YOLOv3: An Incremental Improvement [Online] (2018). http://arxiv.org/abs/1804.02767

  16. GitHub - AlexeyAB/darknet: YOLOv4 (v3/v2) - Windows and Linux version of Darknet Neural Networks for object detection. https://github.com/AlexeyAB/darknet. Accessed on 05 May 2020

  17. Zuiderveld, K.: Contrast Limited Adaptive Histogram Equalization. In: Graphics Gems IV, pp. 474–485. Academic Press Professional Inc, USA (1994)

    Google Scholar 

  18. Pizer, S., et al.: Adaptive histogram equalization and its variations. Comput. Vis. Graph. Image Process. 39(3), 355–368 (1987). https://doi.org/10.1016/S0734-189X(87)80186-X

  19. Otsu, N.: A Threshold Selection Method from Gray-Level Histogram. Automatica 11, 285–296 (1975)

    Article  Google Scholar 

  20. Ninno, E., Nicchiotti, G., Ottaviani, E.: A general and flexible deskewing method based on generalized projection. In: Bimbo, A. (ed.) ICIAP 1997. LNCS, vol. 1311, pp. 632–638. Springer, Heidelberg (1997). https://doi.org/10.1007/3-540-63508-4_177

    Chapter  Google Scholar 

  21. Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors (2012)

    Google Scholar 

  22. Character_dataset. https://www.kaggle.com/pankajdawadi/nepali-lp-dataset. Accessed on 18 Mar 2021

Download references

Acknowledgment

The authors would like to thank Khagendra Acharya for his English editing.

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Kathmandu University, Dhulikhel, Kavre, Nepal

    Pankaj Raj Dawadi, Manish Pokharel & Bal Krishna Bal

Authors
  1. Pankaj Raj Dawadi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Manish Pokharel
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Bal Krishna Bal
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Pankaj Raj Dawadi .

Editor information

Editors and Affiliations

  1. Consilio Research Lab, Tallinn, Estonia

    Mayank Singh

  2. Jaypee University of Engineering and Technology, Guna, Madhya Pradesh, India

    Vipin Tyagi

  3. Jaypee University of Information Technology, Waknaghat, Himachal Pradesh, India

    P. K. Gupta

  4. Institute of Information Theory and Automation, Prague, Czech Republic

    Jan Flusser

  5. University of Ottawa, Ottawa, ON, Canada

    Tuncer Ören

  6. MVPS's Karmaveer Adv. Baburao Ganpatrao Thakare College of Engineering, Nashik, Maharashtra, India

    V. R. Sonawane

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Dawadi, P.R., Pokharel, M., Bal, B.K. (2021). An Approach of Devanagari License Plate Detection and Recognition Using Deep Learning. In: Singh, M., Tyagi, V., Gupta, P.K., Flusser, J., Ören, T., Sonawane, V.R. (eds) Advances in Computing and Data Sciences. ICACDS 2021. Communications in Computer and Information Science, vol 1441. Springer, Cham. https://doi.org/10.1007/978-3-030-88244-0_9

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-88244-0_9

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-88243-3

  • Online ISBN: 978-3-030-88244-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation