An Embedded Automatic License Plate Recognition System using Deep Learning
Resumo
An automatic system to recognize vehicle license plates is a growing need to improve safety and traffic control, specifically in major urban centers. The License Plate Recognition task is generally a computational-intensive task, where the entire input image frame is scanned, the found plates are segmented, and character recognition is then performed. Frequently, this processing is made using general purposes GPUs. This paper proposes an embedded solution to detect and recognize Brazilian license plates using convolutional neural networks (CNN). The system was implemented in a Raspberry Pi3 with a Pi NoIR v2 camera module, which was used to obtain the images of vehicles. The proposed system detects license plates in the captured image using Tiny YOLOv3 architecture and identifies its characters using a second convolutional network trained on synthetic images and fine-tuned with real license plate images. The proposed system has demonstrated to be robust to angle, lightning and noise variations. The system was validated using real license plate images under different environmental conditions reached a detection rate of 99.37% and an overall recognition rate of 97.00% while showing an average time of 2.70 seconds to process 1024x768 images with a single license plate.
Referências
H.E . Kocer and K.K. Cevik, "Artificial neural networks based vehicle license plate recognition," Procedia Computer Science, vol.3 , pp.1033 -1037, 2011.
Z.-X. Chen, c.-Y. Liu, F.-L. Chang, and G. -Y. Wang, "Automatic license-plate location and recognition based on feature salience," IEEE transactions on vehicular technology, vol.58, no. 7, p. 3781,2009.
S. Du, M. Ibrahim, M. Shehata, and W. Badawy, "Automatic license plate recognition (alpr): A state-of-the-art review," IEEE Transactions on circuits and systems for video technology , vol.23 , no.2 , pp. 311-325, 2013.
C. Patel, D. Shah, and A. Patel, "Automatic number plate recognition system (anpr) : A survey, "International Journal of Computer Applications, vol.69 , no. 9,2013.
H. Li and C. Shen, "Reading car license plates using deep convolutional neural networks and Istms ," arXiv preprint arXiv:1601.05610, 2016.
Y. LeCun, Y. Bengio, and G . Hinton, "Deep learning ," nature, vol.521 , no. 7553, p. 436, 2015.
M. Sarfraz, M. J. Ahmed, and S. A.Ghazi ," Saudi arabian license plate recognition system ," in Geometric Modeling and Graphics, 2003. Proceedings. 2003 International Conference on . IEEE,2003,pp.36-41.
T. Bjorklund, A. Fiandrotti, M. Annarumma, G. Francini, and E . Magli, "Automatic license plate recognition with convolutional neural networks trained on synthetic data," in Multimedia Signal Processing (MMSP), 2017 IEEE 19th International Workshop on. IEEE, 2017, pp.1 -6.
A . Krizhevsky, I. Sutskever, and G . E. Hinton, "Irnagenet classification with deep convolutional neural networks," in Advances in neural information processing systems, 2012, pp. 1097-1105.
M. Earl, "Number plate recogrution with tensorftow," https://github.com/matthewearl/deep-anpr, 2016.
J . Xiao, j. Hays, K. A. Ehinger, A. Oliva, andA . Torralba, "Sun database: Large-scale scene recognition from abbey to zoo ," in Computer vision and pattern recognition (CVPR), 2010 IEEE conference on. IEEE, 2010, pp. 3485-3492.
J . Redmon and A . Farhadi, "Yolov3: An incremental improvement," arXiv preprint arXiv:1804.02767, 2018.
J . Redmon and A . Farhadi, "YOL09000 : Better, Faster, Stronger," ArXiv e-prints, Dec . 2016.
F. Stark, C. Hazirbas, R. Triebel, and D. Cremers, "Captcha recognition with active deep learning," in GCPR Workshop on New Challenges in Neural Computation, 2015.
D . P. Kingma and J.Ba, "Adam: A method for stochastic optimization," arXiv preprint arXiv:1412.6980,2014.
