Learning Logic Rules for Scene Interpretation Based on Markov Logic Networks

Abstract

We propose a novel logic-rule learning approach for the Tower of Knowledge (ToK) architecture, based on Markov logic networks, for scene interpretation. This approach is in the spirit of the recently proposed Markov logic networks of machine learning. Its purpose is to learn the soft-constraint logic rules for labelling the components of a scene. This approach also benefits from the architecture of ToK, in reasoning whether a component in a scene has the right characteristics in order to fulfil the functions a label implies, from the logic point of view. One significant advantage of the proposed approach, rather than the previous versions of ToK, is its automatic logic learning capability such that the manual insertion of logic rules is not necessary. Experiments of building scene interpretation illustrate the promise of this approach.