Abstract
The area of automatic license plate localization and recognition has been a difficult problem for many years. Many approaches involve extraction information from the image through a variety of statistical filtering and sampling techniques, resulting in a reduced dimension feature vector that is the input for a learning algorithm. In this paper, the maximally stable extremal region(MSER) features with shape including to license plate texts are extracted by a well-defined closed boundary measure. This measure analyzes characteristics of license plate texts, such as having a different appearance from their background pixels and a closed boundary in a region. The support vector machines(SVM) is then used to classify the measured local extremal regions in an image. And then the SVMs-filters are used to detect and recognize the vehicle license plate texts belonging to a set of extremal regions. Experimental results confirm the practical efficiency of the system.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Anagnostopoulos, C.-N.E., et al.: License plate recognition form still images and video sequences: a survey. IEEE Trans. on ITS 9(3), 377–391 (2008)
Lim, H.W., Tay, Y.H.: Detection of license plate characters in natural scene with MESR and SIFT unigram classifier. In: Proc. of IEEE Conf. on Sustainable Utilization and Development in Engineering and Technology, pp. 95–98 (2010)
Matas, J., Zimmermann, K.: Unconstrained license plate and text localization and recognition. IEEE Trans. on ITS, 225–230 (2005)
Wang, W., Jiang, Q., Zhou, X., Wan, W.: Car license plate detection based on MSER. In: Proc. of IEEE Conf. on Consumer Elect., Comm. and Networks, pp. 16–18 (2011)
Massimiliano, P., Alessandro, V.: Support Vector Machines for 3D Object Recognition. IEEE Trans. on PAMI 20(6), 637–646 (1998)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)
Lan, X., Zitnick, C.L., Szeliski, R.: Local bi-gram model for object recognition. Technical report MSR-TR-2007-54 Microsoft research (2007)
Ligang, M., Youngjuan, Y.: Automatic license plate detection based on connected component analysis and template matching. In: Proc. of IEEE Conf. on ICIP, vol. 2, pp. 1090–1093 (2011)
Duan, T.D., Duc, D.A., Du, T.L.H.: Combining Hough transform and contour algorithms for detecting vehicles’ license-plates. In: Proc. of IEEE Conf. on Intelligent Multimedia, Video and Speech Processing, pp. 20–24 (2004)
Xu, Z., Zhu, H.: An efficient method of locating vehicles license plate. In: Proc. of IEEE Conf. on Natural Computation, vol. 2, pp. 189–183 (2007)
Matas, J., Chum, O., Urba, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extermal regions. In: Proc. of British Machine Vision Conference, pp. 284–396 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kim, JB. (2012). MSER and SVM-Based Vehicle License Plate Detection and Recognition System. In: Lee, G., Howard, D., Ślęzak, D., Hong, Y.S. (eds) Convergence and Hybrid Information Technology. ICHIT 2012. Communications in Computer and Information Science, vol 310. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32692-9_66
Download citation
DOI: https://doi.org/10.1007/978-3-642-32692-9_66
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32691-2
Online ISBN: 978-3-642-32692-9
eBook Packages: Computer ScienceComputer Science (R0)