Knowledge Based Image Understanding by Iterative

In this paper knowledge based image interpretation is formulated and solved as an optimization problem which takes into account the observed image data, the available task speciic knowledge, and the requirements of an application. Knowledge is represented by a semantic network consisting of concepts (nodes) and links (edges). Concepts are further deened by attributes, relations, and a judgment function. The interface between the symbolic knowledge base and the results of image (or signal) processing and initial segmentation is speciied via primitive concepts. We present a recently developed approach to optimal interpretation that is based on the automatic conversion of the concept oriented semantic network to an attribute centered representation and the use of iterative optimization procedures, like e.g. simulated annealing or genetic algorithms. We show that this is a feasible approach which providesàny{time' capability and allows parallel processing. It provides a well{deened combination of signal and symbol oriented processing by optimizing a heuristic judgment function. The general ideas have been applied to various problems of image and speech understanding. As an example we describe the recognition of streets from TV image sequences to demonstrate the eeciency of iterative optimization.