The dominant views of solid objects

Abstract

Introduces the concept of the dominant views (DVs) of a solid object as those views that, in a sense to be defined, contain maximal visual information about the solid. The set of dominant views of a solid object is a minimal subset of the object's characteristic views (CVs) that represents all of the object's surfaces in the most general manner. The authors present a method for computing the dominant views of a solid object from its characteristic-view set and illustrate the method on some sample objects. By providing a basis for multi-level indexing of an object-model database, the DV concept should prove useful in object recognition and pose determination. A scheme for multi-level indexing is considered essential for solving the problem of inexact matching in multiview model-based recognition.<>