- Volume 11 Issue 3
Automatic vehicle license plate recognition technology is widely used in gate control and parking control of vehicles, and police enforcement of illegal vehicles. However inherent geometric information of the license plate can be transformed in the vehicle images due to the slant and the sunlight or lighting environment. In this paper, a distortion invariant vehicle license plate extraction and recognition algorithm is proposed. First, a binary image reserving clean character strokes can be achieved by using a DoG filter. A plate area can be extracted by using the location of consecutive digit numbers that reserves distortion invariant characteristic. License plate is recognized by using neural networks after geometric distortion correction and image enhancement. The simulation results of the proposed algorithm show that the accuracy is 98.4% and the average speed is 0.05 seconds in the recognition of 6,200 vehicle images that are obtained by using commercial LPR system.
Plate Detection;Plate Recogntion;LPR;Image Enhancement;Distortion Invariant
- M. Y. Kim and Y. D. Kim, "An Approach to Korean License Plate Recognitinon Based on Vertival Edge Matching," Systems Man and Cybernetics, IEEE International Conference Vol.4. pp.8-11, 2000.
- M. Ko, "Effective License Plate Character Recognition Based on Geometric Invariant Features," Ph. D. dissertation, Kyungpook National University, 2004.
- K. Deb, H. Chae and K. Jo, "Vehicle License Plate Detection Method Based on Sliding Concentric Windows and Histogram," J. of Computers, Vol.4, No.8, pp.771-777, 2009. https://doi.org/10.4304/jcp.4.8.771-777
- B. Enyedi, L. Konyha, and K. Fazekas, "Real Time Number Plate Localization Algorithms," J. of Electrical Engineering, Vol.57, No.2, pp.69-77, 2006.
- F. Shafait, D. Keysers, and T. M. Breuel. "Efficient Implementation of Local Adaptive Thresholding Techniques using Integral Images," SPIE DRR'08, San Jose, CA, USA. 2008(1).
- Vehicle Plate Detection in Car Black Box Video vol.2017, pp.1687-5699, 2017, https://doi.org/10.1155/2017/7587841