Ting-Yu Wu
ABSTRACT
The license plate recognition is widely used in daily life. Basically, the license plate recognition process is divided into two phases: detection and recognition. Most of the previous studies are simply use conventional pattern recognition techniques or deep learning. Therefore, the industrial computer vision library (Euresys Open eVision) and deep learning are integrated to fulfill license plate recognition and presented in this paper. The proposed approach is divided into three phases: the first phase is to apply deep learning to detect the license plate in the image with a complicated background. The second phase is the license plate correction. A perspective transformation is used to correct the angle of the license plate. Finally, optical character recognition (OCR) is used to recognize the license plate. According to the experimental results, the accuracy of the proposed approach can reach 96.7% with an average identification time of 63.4ms. It shows that the proposed approach is feasible in a practical environment.
- Bai, H. L., Zhu, J. M., and Liu, C. P. 2003. A fast license plate extraction method on complex background. Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems (Shanghai, China, Oct. 2003), 985--987.Google Scholar
- Duan, T. D., Du Hong, T. L., Phuoc, T. V., and Hoang, N. V. 2005. Building an Automatic Vehicle License-Plate Recognition System. Int. Conf. Comput. Sci. RIVF (Cantho, Vietnam, Feb. 2005), 59--63.Google Scholar
- Qin, Z., Shi, S., and Fu. H. 2006. Method of License Plate Location Based on Corner Feature. 2006-6th World Congress on Intelligent Control and Automation (Dalian, China, Jun. 2006), 8645--8649.Google Scholar
- Wu, W. Wang, M. J., and Huang, Z. X. 2001. An automatic method of location for number-plate using color features. In Proc. IEEE ICIP (Thessaloniki, Greece, Oct. 2001) 782--785.Google Scholar
- Hsieh, C.-T., Juan, Y.-S., and Hung, K.-M. 2005. Multiple license plate detection for complex background. 19th International Conference on Advanced Information Networking and Applications (Taipei, Taiwan, Mar. 2005), 389--392.Google Scholar
- Kim, D.-S., and Chien, S.-I. 2001. Automatic car license plate extraction using modified generalized symmetry transform and image warping. In Proc. ISIE (Pusan, South Korea, Jun. 2001). 2022--2027.Google Scholar
- Hinton, G. E., and Salakhutdinov, R. R. 2006. Reducing the dimensionality of data with neural networks. Science, 313, 5786, (Jul. 2006) 504--507.Google Scholar
- Ren, S., He, K., Girshick, R., and Sun, J. 2015. Faster R-CNN: towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems 28 (Montreal, Canada, Dec. 2015), 91--99.Google Scholar
- Redmon, J., and Farhadi, A. 2018. Yolov3: An incremental improvement. arXiv preprint. arXiv:1804.02767.Google Scholar
- Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., and Berg, A. C. 2016. SSD: Single shot multibox detector. European Conference on Computer Vision (Amsterdam, Netherlands, Oct. 2016), 21--37.Google Scholar
- Mao, Y.-H., Liao, H.-C., and Lim, Z.-Y. 2018. License Plate Recognition for Moving Motorcycles Using Industrial Computer Vision Library. International Journal of Advanced Information Technologies, 12, 2, 38--44.Google Scholar
Index Terms
- Integration of Deep Learning and Industrial Computer Vision Library for Motorcycle and Vehicle License Plate Recognition
Recommendations
ROI-based Deep Learning Method for Variable-length License Plate Character Segmentation
CSSE '20: Proceedings of the 3rd International Conference on Computer Science and Software EngineeringLicense plate character segmentation plays link function between license plate detection and recognition. It is based on the results of license plate detection and produces segmented characters for subsequent recognition module. Character is the region ...
Research on License Plate Recognition Based on Deep Learning in Complex Scenarios
ICMLSC '23: Proceedings of the 2023 7th International Conference on Machine Learning and Soft ComputingThe license plate angle is unfixed, the vehicle position is ununiform, and the picture is not sufficiently illuminated which leads to the decrease of license plate recognition accuracy. In order to improve the accuracy of license plate recognition, a ...
Representation learning in a deep network for license plate recognition
AbstractThe goal of license plate recognition (LPR) is to read the license plate characters. Due to image degradation, there are many difficulties in the way of achieving this goal. In this paper, the proposed method recognizes the license plate ...
Comments