For the past few years, the automatic license plate recognition system has gained more importance in the development of smart cities for vehicle management, investigation of stolen vehicles, and traffic monitoring and control. In this paper, we propose an efficient Automatic License Plate Recognition system (ALPR) for the Indian license plate. ALPR first localizes the license plate by using an adaptive sliding window technique with the help of a convolution neural network classifier. Then, the characters are segmented from the license plate by using the morphological operations. Segmented characters are converted into text upon using Transfer learning techniques on Mobilenet. ALPR was tested and has outperformed traditional license plate recognition system. Also, the performance of ALPR was satisfactory in variation in illumination condition, text style, uncanny and skewness of the license plate. The ALPR system can be integrated with the Speed Calculation System so that the authority can notify the traffic offender.

Automatic License Plate Recognition system(ALPR), convolution neural network classifier(CNNC), Optical character recognition(OCR), adaptive sliding window technique(ASW), MobileNet

[1] D.Kendre, H., V.Talokar, G., Girhe, M., & Pidkalwar, T. (2013). The Automatic Number Plate Recognition System (Anpr). Internation Journal of Mathematics and Computer Research, 99-102.
[2] Devi, D., & D.Kanagapushpavalli. (2011). Automatic License Plate Recognition. IEEE, 75-78.
[3] Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., . . . Adam, H. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. Computer Vision and Pattern Recognition.
[4] Lin, C.-H., Lin, Y.-S., & Liu, W.-C. (2018). An Efficient License Plate Recognition System Using Convolution Neural Networks. IEEE Conferenceon Applied System Innovation 2018 (pp. 224-227). IEEE.
[5] Qadri, M. T., & Muhammad, A. (2009). Automatic Number Plate Recognition System for Vehicle Identification using Optical Character Recognition. 2009 International Conference on Education Technology and Computer (pp. 335-338). IEEE.
[6] Shaikh, S., Lahiri, B., Bhatt, G., & Raja, N. (2013). A novel approach for Automatic Number Plate Recognition. 2013 International Conference on Intelligent System and Signal Processing(ISSP) (pp. 375-380). IEEE.
[7] Youusef, K. M., Al-Tabanjah, M., Hudaib, E., & Ikrai, M. (2015). SIFT Based Automatic Number Plate Recognition. 6th International Conference on Information and Communication Systems(ICICS) (pp. 124-129). IEEE.
[8] A. Raj, D. Dubey, A. Mishra, N. Chopda, N.M. Borkar, V.S. Lande, B.A. Neole, "Semi-Geometrical approach to estimate the speed of the vehicle through a surveillance video stream", International Journal of Computer Sciences and Engineering, Vol.7, Issue.3, pp.791-798, 2019.
[9] Brownlee, J. (2017, July 3). Gentle Introduction to the Adam Optimization Algorithm for Deep Learning. Retrieved from machinelearningmastery: https://machinelearningmastery.com/adam-optimization-algorithm-for-deep-learning/
[10] Chollet, F. (2016, June 5). Building powerful image classification models using very little data. Retrieved from The Keras Blog: https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html
[11] Sliding Windows for Object Detection with Python and OpenCV. (2019). Retrieved from pyimagesearch: https://www.pyimagesearch.com/2015/03/23/sliding-windows-for-object-detection-with-python-and-opencv/
[12] python-mnist. (2019). Retrieved from github: https://github.com/sorki/python-mnist.
[13] The SciPy community. (2019, January 31). NumPy v1.16 Manual. Retrieved from SciPy: https://docs.scipy.org/doc/numpy/
[14] Keras: The Python Deep Learning library. (n.d.). Retrieved from Keras documentation: https://keras.io/
[15] User`s Guide. (2019, March 18). Retrieved from matplotlib: https://matplotlib.org/users/index.html
[16] TensorFlow Guide. (2019). Retrieved from TensorFlow: https://www.tensorflow.org/guide
[17] opencv dev team. (2019, March 24). OpenCV Tutorials. Retrieved from OpenCV: https://docs.opencv.org/2.4/doc/tutorials/tutorials.html
[18] deep-learning-models. (2019). Retrieved from github: https://github.com/fchollet/deep-learning-models/releases
[19] BLOCK CHARACTERS FOR OCR,Dataset. (19, 4 3). Retrieved from Kaggle: https://www.kaggle.com/rajaman/block-characters-for-ocr
[20] Vehicle Number Plate,Dataset. (18, 12 20). Retrieved from Kaggle: https://www.kaggle.com/rajaman/vehicle-licence-plate
[21] The CHAR74K Dataset:Character Recognition in Natural Images. (2012, October 15). Retrieved from ee.survey: http://www.ee.surrey.ac.uk/CVSSP/demos/chars74k/
[22] NIST Special Database 19. (2018, July 23). Retrieved from NIST: https://www.nist.gov/srd/nist-special-database-19