Automatic Number Plate Recognition System Based on Deep Learning

Authors: T. Damak, O. Kriaa, A. Baccar, M. A. Ben Ayed, N. Masmoudi

Abstract:

In the last few years, Automatic Number Plate Recognition (ANPR) systems have become widely used in the safety, the security, and the commercial aspects. Forethought, several methods and techniques are computing to achieve the better levels in terms of accuracy and real time execution. This paper proposed a computer vision algorithm of Number Plate Localization (NPL) and Characters Segmentation (CS). In addition, it proposed an improved method in Optical Character Recognition (OCR) based on Deep Learning (DL) techniques. In order to identify the number of detected plate after NPL and CS steps, the Convolutional Neural Network (CNN) algorithm is proposed. A DL model is developed using four convolution layers, two layers of Maxpooling, and six layers of fully connected. The model was trained by number image database on the Jetson TX2 NVIDIA target. The accuracy result has achieved 95.84%.

Keywords: Automatic number plate recognition, character segmentation, convolutional neural network, CNN, deep learning, number plate localization.

Digital Object Identifier (DOI): doi.org/1

References:

[1] O. Hommos, A. Al-Qahtani, Ali Farhat, A. Al-Zawqari, F. Bensaali , A. Amira, X. Zhai, “HD Qatari ANPR System” in International Conference on Industrial Informatics and Computer Systems (CIICS), Sharjah, United Arab Emirates, 13-15 March 2016.
[2] VC M. Vishnu, M. Rajalakshmi, R. Nedunchezhian “Intelligent traffic video surveillance and accident detection system with dynamic traffic signal control” in Cluster Computing, Springer Journal of Networks, Software Tools and Applications. Volume 21, Issue 1, pp 135–147, 2018.
[3] A M. Al-bakry, S O. Al-mamory, H HMushatet “Comparative Study on Automatic Vehicle Identification Techniques.” in Annual Conference on New Trends in Information & Communications Technology Applications-(NTICT'2017), Irak, 7-9 Mars,2017.
[4] F. N. Tawfeeq and Y. M. Tabra, “Gate Control System for New Iraqi License Plate” in Iraqi Comm. Comput. Informatics, vol. 1, no.1, pp. 2-4, 2014.
[5] B. A. Patel and A. Singhadia “Automatic Number PlateRecognition System Using Improved Segmentation Method” in International Journal of Engineering Trends and Technology (IJETT) –Volume16, Number8, pp. 386-389, 2014.
[6] A. Puranic, K.T. Deepak, V.Umadevi “Vehicle Number Plate Recognition System: A Literature Review and Implementation using Template Matching” in International Journal of Computer Applications, Volume 134 – No.1, pp 12, 2016.
[7] M M. Kurdi, I A. Elzein “Lebanese Automated Number Plate Reading Based onNeural Network Recognition. ” in 13th International Computer Engineering Conference (ICENCO), 2017.
[8] A S. Agbemenu , J.Yankey, E O. Addo “An Automatic Number Plate Recognition System using OpenCV and Tesseract OCR Engine” in International Journal of Computer Applications (0975 - 8887) Volume 180 - No.43, 2018.
[9] J.Wang, B.Bacic, W Q.Yan “An effective method for plate number recognition” in Springer Journal of Multimedia Tools and Applications. Volume 77, Issue 2, pp 1679–1692, 2018.
[10] C. Tomasi R. Manduch “Bilateral Filtering for Gray and Color Images” in Proceedings of the 6th IEEE International Conference on Computer Vision, Bomba, India, 1998.
[11] Lubna, M. F. Khan, N. Mufti “Comparison of Various Edge Detection Filters for ANPR” in Sixth International Conference on Innovative Computing Technology, 24-26 Aug, Dublin Ireland, 2016.
[12] Y.Zhang, L.Wu “Optimal multi-level Thresholding based on Maximum Tsallis Entropy via an Artificial Bee Colony Approach” in Entropy Open Access journal. Vol 13 (4): pp.841–859, 2011.
[13] B. U.Shankar, K. Ghosh, D P. Mandal, Shubhra, S Ray, D Zhang, S K. Pal “Pattern Recognition and Machine Intelligence” in the 7th International Conference on Pattern Recognition and Machine Intelligence, PReMI 2017, Kolkata, India, December 2017. p 531.