Image Segmentation Using Fuzzy-Spatial Taxon Cut
Lauren Barghout · Purdue e-Pubs (Purdue University System) · 2015
Images convey multiple meanings that depend on the context in which the viewer perceptually organizes the scene. This presents a problem for automated image segmentation, because it adds uncertainty to the process of selecting which objects to include or not include within a segment. I’ll discuss the implementation of a fuzzy-logic-natural-vision-processing engine that solves this problem by assuming the scene architecture prior to processing. The scene architecture, a standardized natural-scene-perception-taxonomy comprised of a hierarchy of nested spatial-taxons. Spatial-taxons are regions (pixel-sets) that are figure-like, in that they are perceived as having a contour, are either `thing-like', or a `group of things', that draw our attention. Defined in this way, the image segmentation problem can be operationalized into a series of iterative two-class fuzzy inferences. Spatial-taxon cut is determined operationally, by simultaneously minimizing of attentional resources and maximizes of utility. This system provides a top-down computer vision model of scene organization.