On Considering Uncertainty and Alternatives in Low-Level Vision
This addresses uncertainty issues in low-level vision for tasks like object recognition, but it appears incremental as it builds on existing Bayesian methods without claiming major breakthroughs.
The paper tackles uncertainty in image segmentation by using a Bayesian formalism to build a probability distribution over alternative segmentations, providing operations for constructing this representation.
In this paper we address the uncertainty issues involved in the low-level vision task of image segmentation. Researchers in computer vision have worked extensively on this problem, in which the goal is to partition (or segment) an image into regions that are homogeneous or uniform in some sense. This segmentation is often utilized by some higher level process, such as an object recognition system. We show that by considering uncertainty in a Bayesian formalism, we can use statistical image models to build an approximate representation of a probability distribution over a space of alternative segmentations. We give detailed descriptions of the various levels of uncertainty associated with this problem, discuss the interaction of prior and posterior distributions, and provide the operations for constructing this representation.