ON THE USE OF A VISUAL CORTICAL SUB-BAND MODEL FOR INTERACTIVE HEURISTIC EDGE DETECTION

摘要

We present a novel interactive edge detection algorithm that combines A~* search with low-level adaptive image processing. The algorithm models the semantically driven interpretation that we hypothesize to occur between the mind and visual cortex in the human brain. The basic idea is that oriented Gabor sub-bands are used to model grating cells in the mammalian visual system. These sub-bands are used during the search for a path to a marker in an image. A domain expert uses image markers to select edges of interest. We demonstrate the system in several image domains. Examples are shown in the areas of photo-interpretation, medical imaging, path planning and general edge finding. The A~* search finds a suboptimal result, but executes in a time that is typically 10 to 1,000 times faster than the dynamic programming approach currently used for this type of edge detection.