Abstract
Since the road signs (RS) are susceptible to noise and difficult to recognize, the paper proposed a method to remove noise of RS and recognize it, where the parameters were estimated by the EM algorithm. The algorithm consists of two steps: first, the RS were modeled and restored by the Markov random field (MRF); Second, recognizing restored RS was through calculating the invariant moments. Simulation experiment compares the median filtering method and Gaussian smooth method. The results show that the proposed algorithm is better than other two methods in restoration and easily to recognize the RS.
This work was supported in part by the NSFC (91016020, 60934009, 61175030), the ZJNSF (Y1101218, Y1080422), and the Hangzhou Dianzi University (KYS065609051).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Zhang QZ, Kamata SI (2008) Automatic road sign detection method based on color Barycenters hexagon model. In: The 19th international conference on pattern recognition, 8–11 Dec, Tampa, Florida, U S A, pp 1–4
Broggi A, Cerri P, Medici P, Porta PP, Ghisio G (2007) Real time road signs recognition. In: The 2007 IEEE intelligent vehicles symposium, Istanbul, Turkey, pp 981–986
Miura J, Kanda T, Shirai Y (2000) An active vision system for real-time traffic sign recognition. In: The 2000 IEEE intelligent transportation systems proceedings, Dearbom, U S A, pp 52–57
Li SZ (2009) Markov random field modeling in image analysis. Springer, Berlin, pp 199–208
Lu MJ, Wang RS (2000) The markov random fields in computer vision. J Electronics Inf Technol 22(6):1028–1037. (in Chinese)
Chen WK, Zhang LZ, Zhang QZ, Zeng T, Cui G (2007) Segmentation of moving object based on markov random field. Microcomput Appl 7(28):673–677. (in Chinese)
Wu Q, Zhao XB, Zhou HQ (2006) Detection of vane defects based on markov random field model. Comput Appl 9(6):187–212. (in Chinese)
Hammersley JM, Clifford P (1971) Markov field on finite graphs and lattices. Unpublished
Geman S, Geman D (1984) Stochastic relaxation Gibbs distribution and Bayesian restoration of image. IEEE Trans Pattern Anal Machine Intell 6(6):721–741
Wang KQ, Bai XB (2006) Classification of wood surface texture based on Gauss-MRF model. J Forestry Res Northeast Forestry Univ Harbin China 17(1):57–61
Liu WF, Han CZ, Shi Y (2009) Unsupervised learning for finite mixture models via modified gibbs sampling. J Xi'an Jiaotong Univ 2(43):15–19
Wang HX, Xu XF, Xu SY (2004) An invariant moment approach to recognize objects. Opt Precis Eng Z2(12):1–6. (in Chinese)
Xia YQ, Liu ZD, Yang JY (2005) Application of invariant moment approach in region matching. J Comput Aided Design Comput Graph 10(17):2152–2156. (in Chinese)
Qi SS (2008) Studies on recognition of cell images and initial application based on invariance moments. Inner Mongolia Agriculture University, Huhhot, China, pp 10–15. (in Chinese)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag London Limited
About this paper
Cite this paper
Yang, A., Liu, W., Wen, C. (2012). Denoising and Recognition for Road Signs Based on Markov Random Fields . In: Wang, X., Wang, F., Zhong, S. (eds) Electrical, Information Engineering and Mechatronics 2011. Lecture Notes in Electrical Engineering, vol 138. Springer, London. https://doi.org/10.1007/978-1-4471-2467-2_80
Download citation
DOI: https://doi.org/10.1007/978-1-4471-2467-2_80
Published:
Publisher Name: Springer, London
Print ISBN: 978-1-4471-2466-5
Online ISBN: 978-1-4471-2467-2
eBook Packages: EngineeringEngineering (R0)