Multimodal Reasoning in Molecular Imagery

Multimodal Reasoning

Volume

Papers from the 1998 AAAI Spring Symposium

Contents

Pattern recognition, model building, and image segmentation and interpretation are integral processes in the recovery of the three-dimensional structure of a protein model from experimentally derived data. The tools and techniques developed for computational imagery provide a multimodal framework for representing and reasoning with visual/spatial characteristics in this domain. This paper overviews the three distinct representations for computational imagery and describe their application to the problem of molecular scene analysis.