A New Paradigm for Recognizing 3-D Object Shapes from Range Data

  • Authors:
  • Salvador Ruiz-Correa;Linda G. Shapiro;Marina Meila

  • Affiliations:
  • -;-;-

  • Venue:
  • ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Most of the work on 3-D object recognition from rangedata has used an alignment-verification approach in whicha specific 3-D object is matched to an exact instance of thesame object in a scene. This approach has been successfullyused in industrial machine vision, but it is not capable ofdealing with the complexities of recognizing classes of similarobjects. This paper undertakes this task by proposingand testing a component-based methodology encompassingthree main ingredients: 1) a new way of learning and extractingshape-class components from surface shape information;2) a new shape representation called a symbolicsurface signature that summarizes the geometric relationshipsamong components; and 3) an abstract representationof shape classes formed by a hierarchy of classifiersthat learn object-class parts and their spatial relationshipsfrom examples.