License Plate Recognition Under Nonuniform Illumination
License plate recognition (LPR) is an important technique in automobile management and traffic control. Experiments show that the recognition rate dropped significantly when the illumination on the license plate is nonuniform. In this chapter, we proposed a simple block-based method to resolve the problem. Experiments show that the proposed method is not only fast but also outperforms well-known Otsu as well as state-of-the-art NiBlack and MAT, with recognition rate of 86% for the 100 nonuniformly illuminated license plate test images.
KeywordsLicense plate recognition Registration Block based Edge detection Nonuniform illumination Character segmentation Character recognition
- 3.Niblack W (1986) An introduction to digital image processing. Prentice-Hall, Englewood Cliffs, pp 115–116Google Scholar
- 4.Rahman CA, Badawy W, Radmanesh A (2003) A real time vehicle’s license plate recognition system. In: Proceedings of the IEEE conference on advanced video and signal based surveillance, Miami, 21–23,July 2003, pp 163–166Google Scholar
- 5.Juntanasub R, Sureerattanan N (2005) Car license plate recognition through hausdorff distance technique. In: Proceedings of IEEE 17th international conference on tools with artificial intelligence, Hong Kong, 14–16 Nov 2005, pp 647–651Google Scholar
- 6.Broumandnia A, Fathy M (2005) Application of pattern recognition for farsi license plate recognition. In: Proceedings of the international conference on graphics, vision and image processing, Cairo, 19–21 Dec 2005, vol 5, pp 25–31Google Scholar
- 7.Brugge MH Ter, Stevens JH, Nijhuis JAG, Spaanenburg L (1998) License plate recognition using DTCNNs. In: Proceedings of 5th IEEE international workshop on cellular neural networks and their applications, London, 14–17 Apr 1998, pp 212–217Google Scholar