An integrated Bayesian approach to shape representation and perceptual organization

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. 1 Shape and perceptual organization The visual representation of shape is a complex problem, requiring the reduction of an essentially infinite-dimensional object (the geometry of the shape) to a few perceptually meaningful dimensions. Human infants can recognize shape from line drawings without any prior experience [17], suggesting that the ability to abstract form from the bounding contour is innate. Much research in the study of shape has involved a quest for a set of shape descriptors that will allow just the right aspects of shape to be extracted—a representation that retains enough information to support recognition, shape similarity, and other key functions. Each of these techniques— geons [3], codons [37], medial axes [4], curvature extrema [18], Fourier descriptors [8], and so forth—has merits. Some have compelling mathematical motivations, while others (unfortunately not usually the same ones) have demonstrable agreement with human data. Still, broadly speaking, a complete computational characterization of human shape representation remains elusive. Jacob Feldman, Manish Singh, Vicky Froyen, Seha Kim & John D. Wilder Rutgers University, New Brunswick, USA; e-mail: {jacob.feldman,manish.singh,vickyf,sehakim,jdwilder}@rutgers.edu Erica Briscoe, Georgia Tech Research Institute; e-mail: [email protected]