Abstract
Vehicle license plate (LP) detection is a relatively complex problem until we assume the use of a static camera, variations in illumination, known templates of the LP, guaranteed color patterns and other simple assumptions. Practical applications demand robust and generalized LP detection techniques to accommodate complex scenarios. This work suggests a new approach to solving this problem by treating the vehicle LP as an object. The primary focus of this study is to address following tasks associated with the challenge of LP detection: (1) LP detection in every frame of a video sequence, (2) detection of partial LPs and (3) detection of LPs with moving cameras and moving vehicles. The state-of-the-art object detection techniques, including convolutional neural networks with region proposal (RCNN), its successors (Fast-RCNN and Faster-RCNN) and the exemplar-SVM, are used in this work to provide solutions to the problem. The suggested study demonstrates better results in comprehensive tests and comparisons than other conventional approaches.
Similar content being viewed by others
References
Al-Ghaili AM, Mashohor S, Ramli AR, Ismail A (2013) Vertical-edge-based car-license-plate detection method. IEEE Trans Veh Technol 62:26–38
Anagnostopoulos C, Anagnostopoulos I, Loumos V, Kayafas E (2006) A license plate-recognition algorithm for intelligent transportation system applications. IEEE Trans Intell Transp Syst 7(3):377–392
Anagnostopoulos CNE, Anagnostopoulos IE, Psoroulas ID, Loumos V, Kayafas E (2008) License plate recognition from still images and video sequences: a survey. IEEE Trans Intell Transp Syst 9(3):377–391
Ashtari AH, Nordin MJ, Fathy M (2014) An iranian license plate recognition system based on color features. IEEE Trans Intell Transp Syst 15:1690–1705
Broitman M, Klopovsky Y, Silinskis N (2013) License plate detection algorithm, vol 9067, p 90670Z
Chavali N, Agrawal H, Mahendru A, Batra D (2015) Object-proposal evaluation protocol is ’gameable’. In: CoRR, vol abs/1505.05836
Du S, Ibrahim M, Shehata M, Badawy W (2013) Automatic license plate recognition (ALPR): a state-of-the-art review. IEEE Trans Circuits Syst Video Technol 23(2):311–325
Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (2007) The pascal visual object classes challenge 2007 (voc2007) results. http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html
Girshick R (2015) Fast R-CNN. In: Proceedings of the international conference on computer vision (ICCV)
Girshick R, Donahue J, Darrell T, Malik J (2016) Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans Pattern Anal Mach Intell 38:142–158
Gu Q, Yang J, Kong L, Cui G (2015) Multi-scaled license plate detection based on the label-moveable maximal MSER clique. Opt Rev 22(4):669–678
Hosang J, Benenson R, Dollr P, Schiele B (2016) What makes for effective detection proposals? IEEE Trans Pattern Anal Mach Intell 38:814–830
Hsu GS, Chen JC, Chung YZ (2013) Application-oriented license plate recognition. IEEE Trans Veh Technol 62:552–561
Ilonen J, Kamarainen J-K, Paalanen P, Hamouz M, Kittler J, Kaviainen H (2008) Image feature localization by multiple hypothesis testing of Gabor features. IEEE Trans Image Process 17:311–325
Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: convolutional architecture for fast feature embedding. arXiv:1408.5093
Kobayashi T (2015) Three viewpoints toward exemplar svm. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 2765–2773
Lalimi MA, Ghofrani S, McLernon D (2012) A vehicle license plate detection method using region and edge based methods. Comput Electr Eng 39(3):834–845
Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86:2278–2324
Li Q (2014) A geometric framework for rectangular shape detection. IEEE Trans Image Process 23:4139–4149
Malisiewicz T (2011) Exemplar-based representations for object detection, association and beyond. PhD thesis, The Robotics Institute Carnegie Mellon University Pittsburgh, Pennsylvania, vol 15213, p 7
Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149. doi:10.1109/TPAMI.2016.2577031
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556
Smara GA, Khalefah F (2014) Localization of license plate number using dynamic image processing techniques and genetic algorithms. IEEE Trans Evol Comput 18:244–257
Tadic V, Popovic M, Odry P (2016) Fuzzified Gabor filter for license plate detection. Eng Appl Artif Intell 48:40–58
Uijlings JRR, Sande KEA, Gevers T, Smeulders AWM (2013) Selective search for object recognition. Int J Comput Vis 104(2):154–171
Wang R, Sang N, Wang R, Jiang L (2014a) Detection and tracking strategy for license plate detection in video. Opt Int J Light Electron Opt 125(10):2283–2288
Wang R, Sang N, Huang R, Wang Y (2014b) License plate detection using gradient information and cascade detectors. Opt Int J Light Electron Opt 125(1):186–190
Xing X, Choi B-J, Chae S, Lee M-H (2009) Design of a recognizing system for vehicle’s license plates with English characters. Int J Fuzzy Logic Intell Syst 9(3):166–171
Yao Z, Yi W (2014) License plate detection based on multistage information fusion. Inf Fusion 18(1):78–85
Zeiler M, Fergus R (2014) Visualizing and understanding convolutional networks. In: Computer VisionECCV 2014, vol 8689, pp 818–833
Zheng L, He X, Samali B, Yang LT (2013) An algorithm for accuracy enhancement of license plate recognition. J Comput Syst Sci 79(2):245–255
Acknowledgements
This work was supported by the Institute for Information and Communications Technology Promotion (IITP) Grant funded by the Korea government (MSIP) (No. B0101-15-0525, Development of global multi-target tracking and event prediction techniques based on real-time large-scale video analysis).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
This article does not contain any studies with animals performed by any of the authors.
Additional information
Communicated by V. Loia.
Rights and permissions
About this article
Cite this article
Rafique, M.A., Pedrycz, W. & Jeon, M. Vehicle license plate detection using region-based convolutional neural networks. Soft Comput 22, 6429–6440 (2018). https://doi.org/10.1007/s00500-017-2696-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-017-2696-2