PUB - Publikationen an der Universität Bielefeld

A common feature of computer vision systems is the use of levels of increasing abstraction to represent intermediate results and thus successively bridging the gap between raw image data 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 consistent interpretation of image data with groupings from the hierarchy. Since this grouping hierarchy is contour-based, it inherits from drawbacks 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 constrain each other. Results are presented for real images from a construction domain.