• DocumentCode
    2180268
  • Title

    An Enhancement to Closed-Form Method for Natural Image Matting

  • Author

    Zhu, Jun ; Zhang, Dengsheng ; Lu, Guojun

  • Author_Institution
    Gippsland Sch. of Inf. Technol., Monash Univ., Churchill, VIC, Australia
  • fYear
    2010
  • fDate
    1-3 Dec. 2010
  • Firstpage
    629
  • Lastpage
    634
  • Abstract
    Natural image matting is a task to estimate fractional opacity of foreground layer from an image. Many matting methods have been proposed, and most of them are trimap-based. Among these methods, closed-form matting offers both trimap-based and scribble-based matting. However, the closed-form method causes significant errors at background-hole regions due to over-smoothing. In this paper, we identify the source of the problem and propose our solution to enhance the closed-form method. Experiments show that our enhanced method can improve the accuracy for trimap-based images and obtain similar result to the closed-form method for scribble-based matting.
  • Keywords
    image enhancement; image matching; opacity; closed form matting Method; fractional opacity estimation; image enhancement; image foreground layer; natural image matting; scribble based matting; trimap based matting; Analytical models; Bismuth; Color; Cost function; Image color analysis; Mathematical model; Pixel; Image matting; closed-form; gradient constraint; over-smoothing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Digital Image Computing: Techniques and Applications (DICTA), 2010 International Conference on
  • Conference_Location
    Sydney, NSW
  • Print_ISBN
    978-1-4244-8816-2
  • Electronic_ISBN
    978-0-7695-4271-3
  • Type

    conf

  • DOI
    10.1109/DICTA.2010.110
  • Filename
    5692632