• 2020 (Vol.34)

Segmentation of vehicle registration plates based on dynamic time warping

© 2018 M. A. Povolotskiy, E. G. Kuznetsova, N. V. Utkin, D. P. Nikolaev

Institute for Information Transmission Problems RAS 127051 Moscow, Bolshoi Karetny per., 19

Received 09 Aug 2017

A fast number plate segmentation algorithm for automatic license plate recognition system is proposed. It is robust to inaccurate plate quadrangle localization, as well as image brightness distortion. The algorithm uses a priori information about standard plate types geometry and additionally adjusts symbols positions by estimation and correction of localization error. A plate localization error model is built. Its optimal parameters are computed effectively through dynamic programming. Also an algorithm modification is suggested for simultanious segmentation and optimal type selection from a known set. Experimental results are presented to demonstrate the efficiency of this approach.

Key words: license plate recognition, license plate segmentation, dynamic time warping, dynamic programming

DOI: 10.7868/S0235009218010080

Cite: Povolotskiy M. A., Kuznetsova E. G., Utkin N. V., Nikolaev D. P. Segmentatsiya registratsionnykh nomerov avtomobilei s primeneniem algoritma dinamicheskoi transformatsii vremennoi osi [Segmentation of vehicle registration plates based on dynamic time warping]. Sensornye sistemy [Sensory systems]. 2018. V. 32(1). P. 50-59 (in Russian). doi: 10.7868/S0235009218010080

References:

  • Kunina I.A., Gladilin S.A., Nikolaev D.P. Slepaya kompensatsiya radial’noi distorsii na odinochnom izobrazhenii c ispol’zovaniem bystrogo preobrazovaniya Hafa [Blind compensation of radial distortion in a single image using fast Hough transform]. Komp’yuternaya optika [Computer Optics]. 2016. V. 40 (3). P. 395–403 (in Russian).
  • ABBYY Russia Best OCR software for Windows – ABBYY FineReader 14. URL: https://www.abbyy.com/finereader (accessed: 30.08.2017).
  • Du S., Ibrahim M., Shehata M., Badawy W. Automatic license plate recognition (ALPR): A state-of-the-art review. IEEE Transactions on Circuits and Systems for Video Technology. 2013. V. 23 (2). P. 311–325.
  • Gao Q., Wang X., Xie G. License plate recognition based on prior knowledge. 2007 IEEE International Conference on Automation and Logistics. 2007. P. 2964–2968.
  • Gosset W.S. The Probable Error of a Mean. Biometrika. 1908. V. 6 (1). P. 1–25. DOI: 10.2307/2331554.
  • Paliy I., Turchenko V., Koval V., Sachenko A., Markowsky G. Approach to recognition of license plate numbers using neural networks. Proceedings of 2004 IEEE International Joint Conference on Neural Networks. 2004. V. 4. P. 2965–2970.
  • Povolotskiy M.A., Kuznetsova E.G., Khanipov T.M. Russian license plate segmentation based on dynamic time warping. ECMS 2017 Proceedings. 2017. P. 285–291. DOI: 10.7148/2017-0285
  • Tian J., Wang R., Wang G., Liu J., Xia Y. A two-stage character segmentation method for Chinese license plate. Computers & Electrical Engineering. 2015. V. 46. P. 539–553.
  • Uddin M. A., Joolee J. B., Chowdhury S.A. Bangladeshi Vehicle Digital License Plate Recognition for Metropolitan Cities Using Support Vector Machine. Proc. International Conference on Advanced Information and Communication Technology. 2016.
  • Van Herk M. A fast algorithm for local minimum and maximum filters on rectangular and octagonal kernels. Pattern Recognition Letters. 1992. V. 13 (7). P. 517–521.
  • Viola P., Jones M.J. Robust real-time face detection. International journal of computer vision. 2004. V. 57 (2). P. 137–154.
  • Visillect service LLC Automatic number plate recognition – Visillect. URL: http://visillect.com/en/alpr (accessed: 30.08.2017).
  • Xia H., Liao D. The study of license plate character segmentation algorithm based on vetical projection. 2011 IEEE International Conference on Consumer Electronics, Communications and Networks (CECNet). 2011. P. 4583–4586.S