• DocumentCode
    1467992
  • Title

    Shape-From-Focus by Tensor Voting

  • Author

    Hariharan, R. ; Rajagopalan, A.N.

  • Author_Institution
    Dept. of Electr. Eng., Indian Inst. of Technol. Madras, Chennai, India
  • Volume
    21
  • Issue
    7
  • fYear
    2012
  • fDate
    7/1/2012 12:00:00 AM
  • Firstpage
    3323
  • Lastpage
    3328
  • Abstract
    In this correspondence, we address the task of recovering shape-from-focus (SFF) as a perceptual organization problem in 3-D. Using tensor voting, depth hypotheses from different focus operators are validated based on their likelihood to be part of a coherent 3-D surface, thereby exploiting scene geometry and focus information to generate reliable depth estimates. The proposed method is fast and yields significantly better results compared with existing SFF methods.
  • Keywords
    computer vision; image reconstruction; tensors; SFF methods; coherent 3D surface; computer vision; depth hypotheses; perceptual organization problem; scene geometry; shape-from-focus recovery; tensor voting; Estimation; Laplace equations; Organizations; Reliability; Shape; Surface treatment; Tensile stress; Focus operators; real-aperture camera; shape-from-focus (SFF); tensor voting (TV);
  • fLanguage
    English
  • Journal_Title
    Image Processing, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    1057-7149
  • Type

    jour

  • DOI
    10.1109/TIP.2012.2190612
  • Filename
    6168261