|
|
|
Segmentation method for personalized American car plate
based on clustering analysis |
| LI Xu1, XU Shu-chang2, YOU Yu-cai3, ZHANG San-yuan3 |
1. Experiment Center, Zhejiang Police College, Hangzhou 310053, China;
2. College of Information Science and Engineering, Hangzhou Normal University, Hangzhou 310036, China;
3. College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China |
|
|
|
Abstract A new segmentation algorithm was proposed to handle complex and variant American car license plate, which is very personalized and un-uniform in character number, font, spacing and background. Firstly, the tilt angle and vertical project local gradient were obtained based on the dynamic character distribution information. Then the character width was dynamically calculated and accurate character regions were obtained after applying cluster method to remove non-character regions. Finally, the characters were correctly separated by repeat segmentation based on local gradient. A database with more than 10 000 American plate images was used to verify the accuracy of the proposed algorithm. The experimental results show that compared to existing algorithms, the proposed algorithm can achieve well improved segmentation accuracy up to 5%.
|
|
Published: 01 December 2012
|
|
|
基于聚类分析的个性化美国车牌分割算法
针对美国车牌个性化严重,车牌上字符个数、字体、间距和背景等信息都不一致的情况,提出一种可处理复杂多变车牌的车牌分割算法.基于动态的字符分布信息计算车牌倾斜角度和垂直投影局部梯度,利用聚类方法去除非字符区域,并动态确定字符宽度,获得准确字符区域.基于局部梯度的循环分割得到准确的字符分割结果.为了验证该算法,基于1万多张美国车牌的数据集进行实验,结果表明：与已有算法相比,该算法对于具有字符个数不定、字符间距不一致、背景复杂等特征的个性化美国车牌的分割效果有较大提高,分割正确率提高了约5%.
|
|
|
[1] WANG Y T, TIAN R X, MA L, et al. License plate character segmentation from video Images: a survey ［C］ ∥ Proceedings of Chinese Control and Decision Conference. Mianyang, China: IEEE, 2011: 2530.\
[2\] YOON Y W, BAN K D, YOON H, et al. Blob extraction based character segmentation method for automatic license plate recognition system ［C］ ∥ Proceedings of IEEE International Conference on Systems, Man, and Cybernetics. Gyeongju, Korea: IEEE, 2011: 2192-2196.
[3] WANG S Z, LEE H J. Detection and recognition of license plate character with different appearences ［C］ ∥ Proceedings of the Intelligent Transportation Systems. Shanghai, China: SIEEE, 2003: 979-984.
[4] KIM K B, JANG S W, KIM C K. Recognition of car license plate by using dynamical thresholding method and enhanced neural networks ［C］ ∥ Proceedings of 10th International Conference on Computer Analysis of Images and Patterns. Groningen, the Netherlands: LNCS, 2003: 309-319.
[5] XIA H D, LIAO D C. The study of license plate character segmentation algorithm based on vetical projection ［C］ ∥ Proceedings of International Conference on Consumer Electronics, Communications and Networks. Xianning, China: IEEE, 2011: 4583-4586.
[6] DENG H Y, SONG X L. License plate characters segmentation using projection and template matching ［C］ ∥ Proceedings of International Conference on Information Technology and Computer Science. Kiev, Ukraine : IEEE, 2009: 534-537.
[7] LI H, ZHANG H H. Improved projection algorithm for license plate characters segmentation ［C］ ∥ Proceedings of International Conference on Intelligent Computation Technology and Automation. Changsha, China: IEEE, 2009: 534-537.
[8] LI B, ZENG Z Y, ZHOU J Z. An adaptive algorithm for license plate orientation and character segmentation ［C］ ∥ Proceedings of International Conference on Computational Intelligence and Industrial Application. Wuhan, China: IEEE, 2008: 533-537.
[9] ROY A, GHOSHAL D P. Number Plate Recognition for use in different countries using an improved segmentation ［C］ ∥ Proceedings of International Conference on Emerging Trends and Applications in Computer Science.Shillong, India: IEEE, 2011: 1-5.
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
