Scale-space filtering: A new approach to multi-scale description

  title={Scale-space filtering: A new approach to multi-scale description},
  author={A. Witkin},
  • A. Witkin
  • Published in ICASSP 1984
  • Mathematics, Computer Science
  • The extrema in a signal and its first few derivatives provide a useful general purpose qualitative description for many kinds of signals. A fundamental problem in computing such descriptions is scale: a derivative must be taken over some neighborhood, but there is seldom a principled basis for choosing its size. Scale-space filtering is a method that describes signals qualitatively, managing the ambiguity of scale in an organized and natural way. The signal is first expanded by convolution with… CONTINUE READING
    1,126 Citations

    Figures and Topics from this paper

    Scale space filtering by Fejer kernel
    • J. Y. Shi, H. T. Tsui
    • Mathematics
    • Proceedings of ICSIPNN '94. International Conference on Speech, Image Processing and Neural Networks
    • 1994
    • 3
    Uniqueness of the Gaussian Kernel for Scale-Space Filtering
    • 846
    Scaling Theorems for Zero Crossings of Bandlimited Signals
    • 25
    Zero-crossing contour construction for scale-space filtering
    • H. Dehghan
    • Mathematics
    • Conference Record of the Thirty-First Asilomar Conference on Signals, Systems and Computers (Cat. No.97CB36136)
    • 1997
    • 3
    • PDF
    A multi-channel-based approach for extracting significant scales on gray-level images
    • 3
    An Extended Class of Scale-Invariant and Recursive Scale Space Filters
    • 116
    Multiscale Methods for Image Processing: The Wavelet and the Scale-Space Approaches
    • L. Dorini, N. J. Leite
    • Computer Science
    • 2009 Tutorials of the XXII Brazilian Symposium on Computer Graphics and Image Processing
    • 2009
    • 1
    A nonlinear scale-space filter by physical computation
    • Y.-f. Wong
    • Mathematics
    • Neural Networks for Signal Processing III - Proceedings of the 1993 IEEE-SP Workshop
    • 1993
    • 8
    Morphological scale-space with application to three-dimensional object recognition
    • 28
    • Highly Influenced
    Adaptive smoothing: a general tool for early vision
    • P. Saint-Marc, J. Chen, G. Medioni
    • Mathematics, Computer Science
    • Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition
    • 1989
    • 19


    Uniqueness of the Gaussian Kernel for Scale-Space Filtering
    • 846
    A computational theory of human stereo vision
    • D. Marr, T. Poggio
    • Mathematics
    • Proceedings of the Royal Society of London. Series B. Biological Sciences
    • 1979
    • 989
    Edge and Curve Detection for Visual Scene Analysis
    • 747
    Detecting Natural ``Plateaus'' in One-Dimensional Patterns
    • 9
    Structural Pattern Recognition
    • M. Baird
    • IEEE Transactions on Pattern Analysis and Machine Intelligence
    • 1981
    • 235
    • PDF
    Representation of Random Waveforms by Relational Trees
    • 82
    Digital Picture Processing
    • 3,759
    Representing Shapes For Visual Recognition Ph
    • Representing Shapes For Visual Recognition Ph
    • 1983
    Brown Computer Vision
    • Brown Computer Vision
    • 1982