A License Plate Character Segmentation Method Based on Character Contour and Template Matching

Abstract:

In order to solve the problems of the cracked and adhesive characters of license plate caused by the plate frame, rivet, light intensity, a novel character segmentation method based on character contour and template matching was presented. In the proposed methodology, the license plate image contrast was enhanced by the adaptive gray stretch method. The cracked and adhesive characters were accurately extracted owing to the spatial scalability of the contour. Then the found characters were matched according to the adaptive templates. The characters were segmented once more by the best template and then residual characters were complemented and fake characters were removed. A large number of character segmentation experiments under different illumination conditions were made. The results show that the method has a strong robustness and practicability.

• Periodical: Applied Mechanics and Materials (Volumes 333-335)
• Pages: 974-979
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.333-335.974
• Online since: July 2013
• Authors: Yi Zhang, Zhi Qiang Zha, Lian Fa Bai
• Keywords: Character Contour, Character Segmentation, Edge Detection, Template Matching

References

[1] Tao Chen, Chenhui Yang, Bo Qing. Characters Segmentation of License Plate Based on Combination of Projection and Intrinsic characteristics. Computer Technology and Development. Vol. 19, No. 5, pp.45-47, 2003. (In Chinese).

[2] Hongyao Deng, Shu'an Guan, Xiuli Song. Unite Projection and Template Match to Segment License Plate Characters. Computer Engineering and Design. Vol. 29, No. 6, pp.1568-1570, 2008. (In Chinese).

DOI: 10.1109/itcs.2009.116

[3] Ling Gan, Xiaojing Lin, License Plate Character Segmentation Based on Connected Component Extraction, Computer Simulation. Vol. 28, No. 4, pp.336-339, 2011. (In Chinese).

[4] Yungang Zhang, Changshui Zhang. A New Algorithm for Character Segmentation of License Plate. IEEE IV2003 Intelligengt Vehicles Symposium. Columbus: Institute of Electrical and Electronics Engineers Computer Society, pp.106-109, (2003).

DOI: 10.1109/ivs.2003.1212892

[5] Lei Xu, Xiaoning Zhang. A Brightness Classification and Improved Dichotomy Based License Plate Segmentation Algorithm. Shandong Science. Vol. 25, No. 3, pp.1-6, 2012. (In Chinese).

[6] Shubo Zhang, Jianhuang Lan. A Synthesize Approach for Locating and Segmenting Vehicle License Plates. ACTA Scientiarum Natualium Universitatis Sunyatseni. Vol. 43, No. 2, pp.126-128, 132, 2004. (In Chinese).

[7] Zhaoyu Pian, Xiangping Meng, Hong Zhang. License Plate Location Algorithm Based on Multi-phases. Computer Science. Vol. 36, No. 8, pp.296-299, 2009. (In Chinese).

[8] Pengfei Shi, Xunjie Zhao. Technology Research of Vehicle License Plate Location and Character Segmentation Under Complex Scenes. Journal of Suzhou university(Engineering science edition). Vol. 29, No. 1, pp.53-57, 2009. (In Chinese).