基于Zernike不变矩与SVM交通标志的识别

Abstract
Figure/Table
References (0)
Related Citation (15)

Abstract To prevent traffic signs from appearing in different degrees of geometric distortion in complex environments, the invariant moment, which includes translation, rotation, and scaling invariance characteristics, is used in image recognition. First, images are pre-processed. Second, the Zernike and Hu invariant moments of the images are extracted to establish the corresponding feature datasets. Third, the data set is inputted into a support vector machine (SVM) for target classification. Real-time-collected images and the recognition image database in German traffic sign recognition benchmark are used in the experiment. Compared with extracting the Hu invariant moment, extracting the Zernike invariant moments and using SVM recognition both demonstrate a higher real-time recognition rate for traffic signs in a complex environment.

Key words： ITS traffic sign recognition Zernike moment invariants support vector machine (SVM) characteristics of the dataset

Received: 18 September 2015

Fund:Supported by the National Natural Science Foundation of China (No.51208198; No.51168014); the Jiangxi Province Postdoctoral Scientific Research Project Funding (No. 2015KY07)

Corresponding Authors: WANG Yan,E-mail address:wyz1035206690@163.com E-mail: wyz1035206690@163.com

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	WANG Yan
	MU Chun-yang
	MA Xing

Cite this article:

WANG Yan,MU Chun-yang,MA Xing. Using Zernike Moments and SVM for Traffic Sign Recognition[J]. Journal of Highway and Transportation Research and Development, 2016, 10(3): 85-89.

URL:

http://manu27.magtech.com.cn/Jwk_gljtkj_en/EN/ OR http://manu27.magtech.com.cn/Jwk_gljtkj_en/EN/Y2016/V10/I3/85

[1] WEGMAN F. Implementing, Monitoring, Evaluation and Updating a Road Safety Programme[C]//Contribution to the Best in Europe 2003 Conference of the European Transport Safety Council:Targeted Road Safety Programmers in the EU. Brussels:SWOV Institute for Road Safety Research, 2003.
[2] KHAN J F, BHUIYAN S M A, ADHAMI R R. Image Segmentation and Shape Analysis for Road-sign Detection[J]. IEEE Transactions on Intelligent Transportation Systems, 2011, 12(1):83-96.
[3] FENG Chun-gui, ZHU Shi-ping, WANG Hai-jun, et al. On Identification of Speed-limit Signs Based on Modified Template Match[J]. Journal of southwest university:Natural Science Edition, 2013, 35(4):167-172. (in Chinese)
[4] PENG Yue-jun. A Traffic Sign Recognition Algorithm Based on SURF[J]. Information Technology, 2013(17):12-15. (in Chinese)
[5] HU Jin-cheng, LI Shi-ying, LI Ren-fa. Traffic Sign Recognition Based on Stable Surfs[J]. Application Research of Computer, 2012, 29(8):3179-3181. (in Chinese)
[6] SHI M, WU H F, FLEYEH H. Support Vector Machines for Traffic Signs Recognition[C]//Proceedings of IEEE International Joint Conference on Neural Networks. Hong Kong:IEEE, 2008:516-524.
[7] JING Zhi-guo, LI Xiang, CHEN Xiao-lin. Hu's Invariant Moments using in Road Traffic Signs Recognition System[J]. Journal of Jinggang shan University:Natural Science Edition, 2013, 34(1):75-78. (in Chinese)
[8] TIAN Qiu-xia, LIU Cheng-xia, DU Xiao. Research on Method of Traffic Signs Recognition Based on Zernike Invariant Moment and BP Network[J]. Journal of Zhejiang Institute of Science and technology, 2012, 29(2):235-239. (in Chinese)
[9] LIAO S X, PAWLAK M. On the Accuracy of Zernike Moments for Image Analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(12):1358-1364.
[10] HU M K. Visual Pattern Recognition by Moment Invariants[J]. IRE Transactions on Information Theory, 1962, 8(2):179-187.
[11] VAPNIK V. An Overview of Statistical Learning Theory[J]. IEEE Transactions on Neural Network, 1999, 10(5):988-999.
[12] CHANG C C, LIN C J. Libsvm:Alibrary for Support Vector Machines[J]. ACM Transaction on Intelligent Systems and Technology (TIST), 2011, 2(3):389-396.