A connectionist classifier architecture applied to imagesegmentation

摘要

A connectionist classifier architecture that is used in an imagesegmentation scheme based upon a decision analysis paradigm isdescribed. An appropriate architecture for a connectionist classifier isdiscussed, and its relationship to other image segmentationarchitectures following the same paradigm is shown. The performance of acomplete system, including pixel descriptor extraction and connectionistclassifier, is demonstrated using scenes from industrial inspection andcombustion chamber research tasks