Convergence Rates of Algorithms for Visual Search : Detecting Visual Contours

  • Smith-Kettlewell Inst. San Francisco, Smith-Kettlewell Inst
  • Published 1999


This paper formulates the problem of visual search as Bayesian inference and defines a Bayesian ensemble of problem instances. In particular, we address the problem of the detection of visual contours in noise/clutter by optimizing a global criterion which combines local intensity and geometry information. We analyze the convergence rates of A* search… (More)

2 Figures and Tables


  • Presentations referencing similar topics