• DocumentCode
    3128312
  • Title

    System of locating and recognizing characters in complex background

  • Author

    Liyan, Tian ; Jin, Xiao ; Xiaoguang, Hu

  • Author_Institution
    Sch. of Autom. Sci. & Electr. Eng., Beihang Univ., Beijing, China
  • fYear
    2010
  • fDate
    15-17 June 2010
  • Firstpage
    202
  • Lastpage
    206
  • Abstract
    In this paper we propose a locating and recognizing character method in complex background, a system based on this method is built. First, through color reduction to reduce the color to some main colors, then decompose the image into a series of binary images according to the representative colors. After the image decomposition, connected component analysis and combination of character area are used to locate the character area. Finally, the characters are recognized on the basis of feature extraction. The experimental results show that the method can quickly locate character area and has a high positioning accuracy; therefore, the final recognition rate is high.
  • Keywords
    character recognition; feature extraction; image colour analysis; binary images; character area combination; character location; character recognition; color reduction; complex background; connected component analysis; feature extraction; image decomposition; Batteries; Character recognition; Communication switching; Communication system security; Energy consumption; GSM; Global Positioning System; Ground penetrating radar; Mobile communication; Switching circuits; character recognition; complex background; feature extraction; image decomposition;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Industrial Electronics and Applications (ICIEA), 2010 the 5th IEEE Conference on
  • Conference_Location
    Taichung
  • Print_ISBN
    978-1-4244-5045-9
  • Electronic_ISBN
    978-1-4244-5046-6
  • Type

    conf

  • DOI
    10.1109/ICIEA.2010.5516776
  • Filename
    5516776