Constraint Networks: Modeling and Inferring Object Locations by Constraints,

Abstract : Relationships between objects in the real world are constrained by many physical and functional considerations. This paper presents a formalism called Constraint Networks which allows such constraints to be represented and used to make inferences about object locations in images. Constraint Networks are used in a system which accepts information about geometric relationships between structures in images and then uses these constraints to guide search for these structures. The system has been used successfully to infer rib positions in a chest X-ray and to locate aeration tanks and new construction sites in aerial images. (Author)