Study of VIN Based on BP Neural Network Recognition

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 205)


A new fuzzy recognition method of machine-printed VIN number based on neural network is presented. This method includes ten links: VIN number detection and separation of right on top of VIN, binarization, denoising, incline correction, extraction of VIN numerals, window scaling, location standardization, thinning, extraction of numeral feature and fuzzy recognition based on BP neural network. Through testing, the recognition rate of this method can be over 95 %. The recognition time of characters for character is less than 1 s, which means that the method is of more effective recognition ability and can better satisfy the real system requirements.


Fuzzy recognition VIN BP neural network 


  1. 1.
    Wei W, Qi-Sen Z, Xin-Han H (2000) Research of number-plate recognition using distributed processing. J Changsha Commun Univ 02:77–81Google Scholar
  2. 2.
    Rafael CG, Richard EW (2002) Digital image processing (2th). Prentice Hall, New Jersey, vol 06, pp 353–358Google Scholar
  3. 3.
    Ming-Chang W, Lixin X, Yiheng Y, Zhihui L (2006) Directional weighted two dimensional multistep median filtering in image processing. J Jilin Univ 06(01):18–22Google Scholar
  4. 4.
    Xuechun Z, Feihu Q (1998) Automatic recognition of vehicle license based on color segmentation. J Shanghai Jiaotong Univ 18(10):4–8Google Scholar
  5. 5.
    Jian Ping W, Feng Q (2004) On the Adaptive binarization filtering algorithm for gray character images and its application. J Hefei Univ Technol 05:509–513Google Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  1. 1.ShiYan Technical InstituteShiYanChina

Personalised recommendations