• DocumentCode
    2402781
  • Title

    A combined approach for degraded historical documents denoising using Curvelet and mathematical morphology

  • Author

    Gangamma, B. ; Murthy, K.S. ; Chandra, G.C.P. ; Kaushik, Shishir ; Kumar, Saurabh

  • Author_Institution
    Dept. of ISE, PES Inst. of Technol., Bangalore, India
  • fYear
    2010
  • fDate
    28-29 Dec. 2010
  • Firstpage
    1
  • Lastpage
    6
  • Abstract
    India is praised for its rich past and the culture. The rich heritage of the country has been carried over generations through the manuscripts and historic writings. A great deal of effort is being made to prevent their further degradation. A lot of research is also done in finding methods to digitize these documents so that they can be immortalized. But in order to achieve this, the noise in the documents (result of exposure to environmental factors and age) has to be eliminated. This paper deals with one such method aimed at denoising a degraded image. We describe a method to denoise an image using Curvelet and mathematical morphology. Proposed implementation offers reconstruction of the image from the degraded document and edge enhancement by eliminating background.
  • Keywords
    curvelet transforms; document image processing; history; image denoising; image enhancement; image reconstruction; culture; curvelet morphology; degraded historical documents denoising; degraded image denoising; edge enhancement; heritage; historic writings; image reconstruction; manuscripts; mathematical morphology; Image restoration; Morphology; Noise measurement; PSNR; Pixel; Transforms; Curvelet Transform; Degraded Document; Enhancement; Historical Document; Mathematical Morphology;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computational Intelligence and Computing Research (ICCIC), 2010 IEEE International Conference on
  • Conference_Location
    Coimbatore
  • Print_ISBN
    978-1-4244-5965-0
  • Electronic_ISBN
    978-1-4244-5967-4
  • Type

    conf

  • DOI
    10.1109/ICCIC.2010.5705862
  • Filename
    5705862