• DocumentCode
    527661
  • Title

    Vehicle license plate slant correction based on mathematical morphology and Radon transformation

  • Author

    Gong, Li-xia ; Hu, Hong-ping ; Bai, Yan-ping

  • Author_Institution
    Sch. of Sci., North Univ. of China, Taiyuan, China
  • Volume
    7
  • fYear
    2010
  • fDate
    10-12 Aug. 2010
  • Firstpage
    3457
  • Lastpage
    3461
  • Abstract
    Slant vehicle license plate had the bad effect on its character segmentation and recognition. In this paper, a new method to remedy the effect based on mathematical morphology and Radon transformation was presented. According to the Radon transformation, the corresponding correction methods are presented for three inclined ways. Firstly, the edge of the plate picture is detected by the related operation of mathematical morphology. Then, lossless rotation correction is performed to the tilt plate to the horizontal direction, and bilinear interpolation offset correction is made to the plate that is tilt to the vertical direction. Experimental results show that the method can be implemented easily and offers robustness when dealing with dirty plates and license plates in variant lighting conditions.
  • Keywords
    Radon transforms; character recognition; edge detection; image segmentation; interpolation; mathematical morphology; road traffic; traffic engineering computing; Radon transformation; bilinear interpolation offset correction; character recognition; character segmentation; edge detection; lossless rotation correction; mathematical morphology; plate picture; vehicle license plate slant correction; Covariance matrix; Image edge detection; Interpolation; Licenses; Morphology; Transforms; Vehicles; Radon transformation; Vehicle license plate recognition; license plate slant correction; mathematical morphology;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Natural Computation (ICNC), 2010 Sixth International Conference on
  • Conference_Location
    Yantai, Shandong
  • Print_ISBN
    978-1-4244-5958-2
  • Type

    conf

  • DOI
    10.1109/ICNC.2010.5583577
  • Filename
    5583577