Recognition of 3D-Objects: an Algorithm for the Inexact Matching of High-Level Polyhedral Representations
Hans Peter Amann, Heinz Hügli, L. Breguet · 2000
This paper describes a powerful inexact matching algorithm that has been applied with success to high-level 3D-object representations in a 3D object recognition system. In a promising way, the algorithm combines several approaches proposed in the last couple of years: an extension to the backtrack strategies for inexact matching of attributed relational subgraphs, error-correction isomorphism, determination of local attribute similarity and global transformation fitting, features which are efficiently used for search-tree pruning. The algorithm was tested successfully in a series of experiments involving scenes with single and multiple objects. Index terms: 3D-object recognition, scene analysis, inexact subgraph matching, machine vision 1.