Perception as Bayesian inference
Perception as Bayesian inference
Filtering, Segmentation, and Depth
Filtering, Segmentation, and Depth
Occlusion Models for Natural Images: A Statistical Study of a Scale-Invariant Dead Leaves Model
International Journal of Computer Vision - Special issue on statistical and computational theories of vision: Part II
First-order modeling and stability analysis of illusory contours
Journal of Visual Communication and Image Representation
| Hi-index | 0.00 |
A significant cue for visual perception is the occlusion pattern in 2-D retinal images, which helps humans or robots navigate successfully in the 3-D environments. There have been many works in the literature on the modeling and analysis of the occlusion phenomenon, most of which are from the analytical or statistical points of view. The current paper presents a new theory of occlusion based on the simple topological definitions of preimages and a binary operation on them called "occlu." We study numerous topological as well as algebraic structures of the resultant noncommutative preimage monoids (a monoid is a semigroup with identity). Some implications of the new theory in terms of real vision research are also addressed.