Universität Bielefeld - Sonderforschungsbereich 360
Perceptual Grouping using Markov Random Fields and
Cue Integration of Contour and Region Information
Stefan Posch and Daniel Schlüter
Abstract
A common feature of computer vision systems is the use of levels of
increasing abstraction to represent intermediate results and thus
successiveley bridging the gap between raw image date and the final
result. To elaborate on such a hierarchical representation we propose
a contour-based grouping hierarchy based on principles of perceptual
organization. Exploiting regularities in the image, we aim at enhancing
efficiency and robustness of subsequent processing steps of an image
analysis system by reducing ambiguities in the intermediate representation
and by realizing image primitives at a higher level of abstraction. To this
end, first grouping hypotheses are generated within the hierarchy using
the concept of areas of perceptual attentiveness. Since the generation is
based on local evidence only, the hypotheses have to be judged in a global
context. We employ a Markov Random Field to model context dependencies
and energy minimization yields a consitent interpretation of image data
with groupings from the hierarchy. Since this grouping hierarchy is
contour-based, it inherits from backdraws of contour segmentation. Therefore,
the second issue we address aims at the integration of cues from region
segmentation into the contour-based grouping process and vice versa. This
integration is done on the level of contour segments, collinearities, and
curvilinearities with complete regions to support and contrain each other.
Results are presented for real images form a construction domain.
Postscript-File (~ 720 k)
Anke Weinberger, 1998-11-23, 1999-02-11