Traditional methods for image scene interpretation and understanding are based mainly on such single-threaded procedural paradigms as hypothesize-and-test or syntactic parsing. As a result, these systems are unable to carry out tasks that require concurrent hypothesis testing.This book explores a method for symbolically interpreting images based upon a parallel implementation of a network-of-frames suggested, for example, by Minsky (1975), to describe intelligent processing. The system has been implemented in an object-oriented environment in the logic programming language Parlog++ and includes the propagation of uncertainty through each frame using Baldwin''s (1986) formulation. The system is tested with several scenarios of increasing complexity, culminating with legal interpretation of traffic intersection images.

Traditional methods for image scene interpretation and understanding are based mainly on such single-threaded procedural paradigms as hypothesize-and-test or syntactic parsing. As a result, these systems are unable to carry out tasks that require concurrent hypothesis testing.This book explores a method for symbolically interpreting images based upon a parallel implementation of a network-of-frames suggested, for example, by Minsky (1975), to describe intelligent processing. The system has been implemented in an object-oriented environment in the logic programming language Parlog++ and includes the propagation of uncertainty through each frame using Baldwin''s (1986) formulation. The system is tested with several scenarios of increasing complexity, culminating with legal interpretation of traffic intersection images.