• Nasa Zata Dina
  • Rachman Sinatriya Marjianto
Keywords: Detection, License Plate, Recognition, Segmentation


The number of vehicles on the road has increased drastically in recent years. The license plate is an identity card fora vehicle. It can map to the owner and further information about vehicle. License plate information is useful to helptraffic management systems. For example, traffic management systems can check for vehicles moving at speeds notpermitted by law and can also be installed in parking areas to secure the entrance or exit way for vehicles. Licenseplate recognition algorithms have been proposed by many researchers. License plate recognition requires licenseplate detection, segmentation, and characters recognition. The algorithm detects the position of a license plate andextracts the characters. Various license plate recognition algorithms have been implemented, and each algorithm hasits strengths and weaknesses. In this thesis, I implement Haar-cascade algorithm for detecting license plates andTemplate matching algorithm for recognizing license plate characters. I evaluate each of these algorithms on thesame two datasets, one from Greece and one from Thailand. For detecting license plates, Haar cascade algorithmobtained 84% and 86.5%. After the best result of license plate detection is obtained, for the segmentation part aLaplacian based method has the highest accuracy. Last, the license plate recognition experiment shows that templatematching obtained good accuracy on both datasets.


[1] Anagnostopoulos, C.-N., Ioannis, E. A., Loumos, V., & Kayafas, E.(2006). A license plate recognition algorithm for intelligenttransportation system applications. Institute of Electrical and ElectronicsEngineers, 7.
[2] Brunelli, R. (2009). Template matching techniques in computervision: Theory and practice. Wiley.
[3] Gohil, N. B. (2010). Car license plate detection. CaLifornia StateUniversity.
[4] Jain, N., Meshram, S., & Dubey, S. (2012). Image steganographyusing lsb and edge detection technique. International Journal of SoftComputing and Engineering (IJSCE), 2.
[5] Lekhana, G. C., & Srikantaswamy, R. (2012). Real time license platerecognition system. International Journal of Advanced Technology andEngineering Research, 2.
[6] Lisheng, J., Huacai, X., Jing, B., Yuqin, S., Haijing, H., & Qingning,N. (2012). License plate recognition algorithm for passenger cars inchinese residential areas. Sensors, 12.
[7] Nobuyuki, O. (1979). A threshold selection method from gray levelhistograms. Institute of Electrical and Electronics Engineers, SMC-9.
[8] Viola, P., & Jones, M. J. (2004). Robust real-time face detection.International Journal of Computer Vision, 57.
[9] Zheng, D., Zhao, Y., & Wang, J. (2005). An efficient method oflicense plate location. Elsevier Pattern Recognition Letters, 26.