Journal of Jilin University Science Edition

Previous Articles     Next Articles

Recognition of Vehicle License Plate Locating Based onColor Feature and Improved Canny Operator

SUN Jinling, PANG Juan, ZHANG Zelong   

  1. School of Economics and Management, Lanzhou University of Technology, Lanzhou 730050, China
  • Received:2014-11-19 Online:2015-07-26 Published:2015-07-27
  • Contact: PANG Juan E-mail:pangjuan1979@gmail.com

Abstract:

For the problems of low accuracy, and slow locating speed in the existing license plate locating algorithms, a method of license plate locating based on color feature and improved Canny operator was proposed. Firstly, the color feature of the image is used for license plate preliminary locating; the color feature extracted is not included in the luminance information, overcoming the effects of illumination changes effectively. Secondly, based on the indepth research of the Canny edge detection algorithm, a new calculation method of firstorder partial derivative is proposed for the gradient magnitude and gradient direction, at the same time, an adaptive method for high and low dualthreshold determination is also given. Many license plate images were used to evaluate the performance of the algorithm proposed, and the correctness and effectiveness were confirmed, which provides a basis for the pre\|processing of license plate locating in the realtime license plate recognition systems used in the field of intelligent transportation.

Key words: vehicle license plate locating, color feature, Canny operator, edge detection

CLC Number: 

  • TP391.41