Inference of object attributes from local image features caused by occlusion
The natural visual environment has considerable structure, but to date the characterization of this structure has been restricted to fairly simple statistical regularities. Here I describe a novel method to calculate the joint statistics of complex image features exactly, for a generative model of images known as the Dead Leaves model. The simplified world described by this model is composed of independent, textured objects which occlude each other. This simplification enables us to isolate certain image properties that are important for object segmentation. It also allows us to calculate the joint probability distribution of image values sampled at many arbitrarily located points, in some cases without approximation. By choosing the samples appropriately, one can then convert this result into joint probabilities of edges, T-junctions, and other salient image features. These features can be related to the underlying generative model, providing us a way to relate local intensity patterns to higher-level attributes like object size, shape, depth, and border ownership. We use this method to demonstrate how such psychophysical phenomena as contour facilitation, phantom edges, and the cornsweet illusion can be interpreted as probabilistic inference.
Conference:
Computational and systems
neuroscience 2009, Salt Lake City, UT, United States, 26 Feb - 3 Mar, 2009.
Presentation Type:
Poster Presentation
Topic:
Poster Presentations
Citation:
(2009). Inference of object attributes from local image features caused by occlusion.
Front. Syst. Neurosci.
Conference Abstract:
Computational and systems
neuroscience 2009.
doi: 10.3389/conf.neuro.06.2009.03.017
Copyright:
The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers.
They are made available through the Frontiers publishing platform as a service to conference organizers and presenters.
The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated.
Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed.
For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions.
Received:
29 Jan 2009;
Published Online:
29 Jan 2009.