Abstraction and Generalization of 3D structure for recognition in large intra-class variation

Humans have abstract models for object classes which helps recognize previously unseen instances, despite large intra-class variations. Also objects are grouped into classes based on their purpose. Studies in cognitive science show that humans maintain abstractions and certain specificc features from the instances they observe. In this paper, we address the challenging task of creating a system which can learn such canonical models in a uniform manner for dierent classes. Using just a few examples the system creates a canonical model (COMPAS) per class, which is used to recognize classes with large intra-class variation (chairs, benches, sofas all belong to sitting class). We propose a robust representation and automatic scheme for abstraction and generalization. We quantitatively demonstrate improved recognition and classification accuracy over state-of-art 3D shape matching/classication method and discuss advantages over rule based systems.

• Type: Conference
• Year: 2010
• Where: ACCV
• Authors: Gowri Somanath, Chandra Kambhamettu
• Keywords: 3d Object Categorization, 3d Object Recognition, 3D Shape Classification, Abstraction, ACCV 2010, Canonical Class Model, COMPAS, Function Based Categorization, Function Based Object Classification, Object Classification, Shape Analysis And Matching