Reasoning Over Visual Knowledge

In imagistic domains, such as Medicine, Meteorology and Geology, the tasks are accomplished through intensive use of visual knowledge, offering many challenges to the Computer Science. In this work we focus in an essential task accomplished in many imagistic domains: the visual interpretation task. We call visual interpretation the expert reasoning process that describes a cognitive path that starts with the visual perception of domain objects, involves the recognition of visual patterns in these objects and results in the understanding of the scene. We investigate the role played by foundational ontologies in problem solving methods involving visual information. We propose a cognitive model for visual interpretation that combines domain ontologies, ontologically well founded inferential knowledge structures based on the notion of perceptual chunks and PSM’s. The proposed model was effectively applied through a Problem-solving method to solve the task of visual interpretation of depositional processes, within the Sedimentary Stratigraphy domain.