An Integrated Bayesian Approach to Shape Representation and Perceptual Organization

  • Jacob Feldman
  • Manish Singh
  • Erica Briscoe
  • Vicky Froyen
  • Seha Kim
  • John Wilder
Chapter

Abstract

We present a unified Bayesian approach to shape representation and related problems in perceptual organization, including part decomposition, shape similarity, figure/ground estimation, and 3D shape. The approach is based on the idea of estimating the skeletal structure most likely to have generated the observed shape via a process of stochastic “growth.” We survey the approach briefly and show how it can be extended in a principled way to solve a wide array of related problems.

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  • Jacob Feldman
    • 1
  • Manish Singh
    • 2
  • Erica Briscoe
    • 3
  • Vicky Froyen
    • 3
  • Seha Kim
    • 3
  • John Wilder
    • 3
  1. 1.Department of Psychology, Center for Cognitive ScienceRutgers UniversityNew BrunswickUSA
  2. 2.Department of PsychologyRutgers UniversityNew BrunswickUSA
  3. 3.Aerospace, Transportation and Advanced Systems LaboratoryGeorgia Tech Research InstituteAtlantaUSA

Personalised recommendations