Learning a visual model and an image processing strategy from a series of silhouette images on MIRACLE-IV

摘要

MIRACLE-IV is capable of obtaining the internal structure of an object from a series of silhouette images with no initial explicit models about the object. The images are derived from only one object, but the form is varied. The system is composed of two subsystems: a model acquisition part (the modeler) and an image-processing strategy part (the strategist). On the assumption that the object consists of hinges, slides and solids, the modeler learns the number of these in the object and the relationship among them. The strategist binds the functional features as hinges or slides with visual features in the actual image data. The image-processing sequence for the extraction of the visual feature is not given previously but is learned automatically through trial and error.