An evidence-driven probabilistic inference framework for semantic image understanding

Abstract. This work presents an image analysis framework driven by emerging evidence and constrained by the semantics expressed in an ontology. Human perception, apart from visual stimulus and pattern recognition, relies also on general knowledge and application context for understanding visual content in conceptual terms. Our work is an attempt to imitate this behavior by devising an evidence driven prob-abilistic inference framework using ontologies and bayesian networks. Experiments conducted for two different image analysis tasks showed improvement in performance, compared to the case where computer vision techniques act isolated from any type of knowledge or context.