Keywords
scene perception, perceptual organization, spatial-taxon, visual taxometrics, image segmentation, fuzzy logic
Abstract
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.
Start Date
15-5-2015 11:30 AM
End Date
15-5-2015 11:55 AM
Session Number
05
Session Title
Early Vision
Included in
Categorical Data Analysis Commons, Cognition and Perception Commons, Other Computer Engineering Commons
Image Segmentation Using Fuzzy-Spatial Taxon Cut
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.