Directly invertible nonlinear divisive normalization pyramid for image representation

R Valerio, E P Simoncelli and R Navarro.

Published in Visual Content Processing and Representation- Proc 8th Int'l Workshop, VLBV, pp. 331--340, Sep 2003.

DOI: 10.1007/978-3-540-39798-4_42

Download:

  • Reprint (pdf)
    • We present a multiscale nonlinear image representation that permits an efficient coding of natural images. The input image is first decomposed into a set of subbands at multiple scales and orientations using near-orthogonal symmetric quadrature mirror filters. This is followed by a nonlinear divisive normalization stage, in which each linear coefficient is divided by a value computed from a small set of neighboring coefficients in space, orientation and scale. This neighborhood is chosen to allow this nonlinear operation to be efficiently inverted. The parameters of the normalization operation are optimized in order to maximize the independence of the normalized responses for natural images. We demonstrate the near-independence of these nonlinear responses, and suggest a number of applications for which this representation should be well suited.
  • Listing of all publications