Abstract

Image understanding denotes not only the ability to extract specific, non-numerical information from images, but it implies also reasoning about the extracted information. We propose a qualitative representation for image understanding results which is suitable for reasoning with Bayesian networks. Our representation is not purely qualitative but enhanced with probabilistic information to represent uncertainties and errors in the understanding of noisy sensory data. The probabilistic information is then supplied to a Bayesian networks in order to find the most plausible interpretation. We apply this approach for the integration of image and speech understanding to find objects in a visually observed scene which are verbally described by a human. Results demonstrate the performance of our approach. 1 Introduction The representation of image understanding results is an important issue. With image understanding, we mean the extraction of symbolic or qualitative, non-numerical informatio...

Citations