Universal Analytical Forms for Modeling Image Probabilities

  • Authors:
  • Anuj Srivastava;Xiuwen Liu;Ulf Grenander

  • Affiliations:
  • -;-;-

  • Venue:
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Year:
  • 2002

Quantified Score

Hi-index 0.17

Visualization

Abstract

Seeking probability models for images, we employ a spectral approach where the images are decomposed using bandpass filters and probability models are imposed on the filter outputs (also called spectral components). We employ a (two-parameter) family of probability densities, introduced in [11] and called Bessel K forms, for modeling the marginal densities of the spectral components, and demonstrate their fit to the observed histograms for video, infrared, and range images. Motivated by object-based models for image analysis, a relationship between the Bessel parameters and the imaged objects is established. Using \big. L^2\hbox{-}{\rm{metric}}\bigr. on the set of Bessel K forms, we propose a pseudometric on the image space for quantifying image similarities/differences. Some applications, including clutter classification and pruning of hypotheses for target recognition, are presented.