A Progression Direction for Vehicle License Plate Detectors Based on Performance Evaluations Using Various Real-road Images
AUTHORS
Sang-Won Lee,Dept. of Information and Communication Eng., Inha University, Incheon, Korea
Bumsuk Choi,Korea Electronics and Telecommunications Research Institute, Deajon, Korea
Yoo-Sung Kim*,Dept. of Information and Communication Eng., Inha University, Incheon, Korea
ABSTRACT
Recently, since deep learning technologies have been widely used in developing vehicle license plate detection and recognition schemes, the data set of a large number of vehicle images is highly required. However, vehicle license plate detectors developed with the deficient training data set which does not contain the various conditions of real-roads may have insufficient functionalities for actual usages. Therefore, a training data set reflecting enough various real-road conditions is essential. To construct such a data set, the imitation ways for the various possible situations on real-roads from the actual images taken by CCTVs are defined and the imitated images are augmented to the set. Then, using this data set, performance evaluation was studied with a contemporary vehicle license plate detector proposed by Silva and Jung which is known as good at the detections of vehicle license plates in the unconstrained real environments. And, according to the performance evaluation results, we propose a future progressive direction for the secure functionalities of new vehicle license plate detectors that should be used in real situations in near future.
KEYWORDS
Real-road environments, Emulating various real-road conditions, Contemporary vehicle license plate detectors, Future progression directions
REFERENCES
[1] Hendry and Rung-ChingChena, “Automatic license plate recognition via sliding-window darknet-YOLO deep learning”, Image and Vision Computing, vol.87, pp.47-56, (2019)
[2] Laroca, R., Severo, E., Zanlorensi, L.A., Oliveira, L.S., Gon¸calves, G.R., Schwartz, W.R., Menotti, D., and “A robust real-time automatic license plate recognition based on the YOLO detector”, International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, (2018), http://www.openalpr.com/cloud-api.html, OpenALPR Cloud API
[3] Gonalves, G.R., da Silva, S.P.G., Menotti, D., Schwartz, and W.R., “Benchmark for license plate character segmentation”, Journal of Electronic Imaging, vol.25, no.5, (2016)
[4] Hsu, G.S., Chen, J.C., Chung, Y.Z., “Application-oriented license plate recognition”, IEEE Transactions on Vehicular Technology, vol.62, no.2, pp.552-561, (2013)
[5] Silva S.M. and Jung C.R., “License plate detection and recognition in unconstrained scenarios”, In: Ferrari V., Hebert M., Sminchisescu C., Weiss Y. (eds) Computer Vision – ECCV 2018, Lecture Notes in Computer Science, Springer, Cham, (2018)
[6] Bradski, G., “The OpenCV library”, Dr. Dobb’s Journal of Software Tools, (2000)
[7] Redmon, Joseph, and Ali Farhadi, “YOLO9000: better, faster, stronger”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.6517-6525, (2017)