Neural Comp. Sign up for ETOCS
HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
QUICK SEARCH:   [advanced]


     

This Article
Right arrow Full Text (PDF)
Right arrow Alert me when this article is cited
Right arrow Alert me if a correction is posted
Services
Right arrow Similar articles in this journal
Right arrow Alert me to new issues of the journal
Right arrow Download to citation manager
Right arrow reprints & permissions
Citing Articles
Right arrow Citing Articles via HighWire
Right arrow Citing Articles via Google Scholar
Google Scholar
Right arrow Articles by Williams, L. R.
Right arrow Articles by Jacobs, D. W.
Right arrow Search for Related Content
PubMed
Right arrow Articles by Williams, L. R.
Right arrow Articles by Jacobs, D. W.

Neural Computation, Vol 9, 859-881, Copyright © 1997 by The MIT Press

LETTERS

Local Parallel Computation of Stochastic Completion Fields

Lance R. Williams and David W. Jacobs

We describe a local parallel method for computing the stochastic completion field introduced in the previous article (Williams and Jacobs, 1997). The stochastic completion field represents the likelihood that a completion joining two contour fragments passes through any given position and orientation in the image plane. It is based on the assumption that the prior probability distribution of completion shape can be modeled as a random walk in a lattice of discrete positions and orientations. The local parallel method can be interpreted as a stable finite difference scheme for solving the underlying Fokker-Planck equation identified by Mumford (1994). The resulting algorithm is significantly faster than the previously employed method, which relied on convolution with large-kernel filters computed by Monte Carlo simulation. The complexity of the new method is O(n3m), while that of the previous algorithm was O(n4m2) (for an n x n image with m discrete orientations). Perhaps most significant, the use of a local method allows us to model the probability distribution of completion shape using stochastic processes that are neither homogeneous nor isotropic. For example, it is possible to modulate particle decay rate by a directional function of local image brightnesses (i.e., anisotropic decay). The effect is that illusory contours can be made to respect the local image brightness structure. Finally, we note that the new method is more plausible as a neural model since (1) unlike the previous method, it can be computed in a sparse, locally connected network, and (2) the network dynamics are consistent with psychophysical measurements of the time course of illusory contour formation.


This article has been cited by other articles:


Home page
 Cereb CortexHome page
Y. Lerner, T. Hendler, and R. Malach
Object-completion Effects in the Human Lateral Occipital Complex
Cereb Cortex, February 1, 2002; 12(2): 163 - 177.
[Abstract] [Full Text] [PDF]

Home page
 Neural Comput.Home page
L. R. Williams and K. K. Thornber
Orientation, Scale, and Discontinuity as Emergent Properties of Illusory Contour Shape
Neural Comput., August 1, 2001; 13(8): 1683 - 1711.
[Abstract] [Full Text] [PDF]

Home page
 Neural Comput.Home page
P.-Y. Burgi, A. L. Yuille, and N. M. Grzywacz
Probabilistic Motion Estimation Based on Temporal Coherence
Neural Comput., August 1, 2000; 12(8): 1839 - 1867.
[Abstract] [Full Text]

Home page
 Proc. Natl. Acad. Sci. USAHome page
A. Sarti, R. Malladi, and J. A. Sethian
Subjective surfaces: A method for completing missing boundaries
PNAS, June 6, 2000; 97(12): 6258 - 6263.
[Abstract] [Full Text] [PDF]


HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
J COGNITIVE NEUROSCIENCE NEURAL COMPUTATION MIT PRESS JOURNALS
Copyright © 1997 by The MIT Press.