Knowledge representation and model-based image understanding: Benefits of hybrid AI

The 4EU+ European University Alliance is organizing a series of online seminars on the topic "Artificial Intelligence Techniques, Applications and Social Issues". All seminars will be held from January to March 2021 on Thursdays from 16:00 to 17:30 CET, online on Zoom. Seminars will be recorded and made publicly available in a repository of the University of Milan. More information on the website.

The fourth seminar on 18 February will deal with the topic "Knowledge representation and model-based image understanding: Benefits of hybrid AI" and will be presented by Isabelle Bloch (LIP6).

Abstract
Image understanding benefits from the modeling of knowledge about both the scene observed and the objects it contains as well as their relationships. We show in this context the contribution of hybrid artificial intelligence, combining different types of formalisms and methods. Knowledge representation may rely on symbolic and qualitative approaches, as well as semi-qualitative ones to account for their imprecision or vagueness. Structural information can be modeled in several formalisms, such as graphs, ontologies, logical knowledge bases, or neural networks, on which reasoning will be based. The problem of image understanding is then expressed as a problem of spatial reasoning. These approaches will be illustrated with examples in medical imaging, illustrating the usefulness of combining several approaches.

Short biography
Isabelle Bloch graduated from the Ecole des Mines de Paris, Paris, France, in 1986, and received the master's degree from the University Paris 12, Paris, in 1987, the Ph.D. degree from the Ecole Nationale Supérieure des Télécommunications (Télécom Paris), Paris, in 1990, and the Habilitation degree from University Paris 5, Paris, in 1995. She has been a Professor at Télécom Paris until 2020 and is now a Professor at Sorbonne Université. Her current research interests include 3D image understanding, mathematical morphology, information fusion, fuzzy set theory, structural, graph-based, and knowledge-based object recognition, spatial reasoning, symbolic and hybrid artificial intelligence, and medical imaging.