• DocumentCode
    3358899
  • Title

    Computer-aided restoration of characters on Jiagu rubbings

  • Author

    Gu, Shaotong ; Fan, Xuexue

  • Author_Institution
    Inst. of Linguistic, Xuzhou Normal Univ., Xuzhou, China
  • fYear
    2009
  • fDate
    9-12 Aug. 2009
  • Firstpage
    4981
  • Lastpage
    4985
  • Abstract
    A character restoration of Jiagu rubbings scheme based on adaptive threshold and fractal geometry is proposed in this paper. The paper analyzes the characteristics of noise regions and the edges of the characters on Jiagu rubbings. Firstly, we calculate the adaptive threshold by means of Bayes risk function and clear the noise regions on Jiagu rubbings. Then we calculate the fractal dimension of the character edge of Jiagu rubbings by means of statistics. Diffenent compression transformations are performed to the different stroke segments of characters on Jiagu rubbings so as to smooth the character edge of Jiagu rubbings image. Finally, we combine the stroke segments and obtain the satisfactory characters which are similar to the original Jiaguwen characters. The experimental results show that such scheme could successfully smooth the character edge of Jiagu rubbings.
  • Keywords
    Bayes methods; character recognition; edge detection; fractals; Bayes risk function; Jiagu rubbings image; Jiagu rubbings scheme; Jiaguwen characters; adaptive threshold; character edge smoothing; character restoration; computer-aided restoration; fractal geometry; Animals; Biomedical imaging; Bones; Brightness; Fractals; Gaussian noise; Geometry; Image coding; Image restoration; Image segmentation; Jiagu rubbings; adaptive threshold; compression transformation; fractal geometry; stroke segment;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Mechatronics and Automation, 2009. ICMA 2009. International Conference on
  • Conference_Location
    Changchun
  • Print_ISBN
    978-1-4244-2692-8
  • Electronic_ISBN
    978-1-4244-2693-5
  • Type

    conf

  • DOI
    10.1109/ICMA.2009.5245994
  • Filename
    5245994