Affine invariant model-based object recognition

Author

Lamdan, Yehezkel ; Schwartz, Jacob T. ; Wolfson, Hiam J.

Author_Institution

Courant Inst. of Math. Sci., New York Univ., NY, USA

Volume

6

Issue

5

fYear

1990

fDate

10/1/1990 12:00:00 AM

Firstpage

578

Lastpage

589

Abstract

New techniques are described for model-based recognition of the objects in 3-D space. The recognition is performed from single gray-scale images taken from unknown viewpoints. The objects in the scene may be overlapping and partially occluded. An efficient matching algorithm, which assumes affine approximation to the prospective viewing transformation, is proposed. The algorithm has an offline model preprocessing (shape representation) phase which is independent of the scene information and a recognition phase based on efficient indexing. It has a straightforward parallel implementation. The algorithm was successfully tested in recognition of industrial objects appearing in composite occluded scenes

Keywords

computer vision; computerised pattern recognition; 3D space; composite occluded scenes; computer vision; gray-scale images; industrial objects; matching algorithm; model-based object recognition; offline model; pattern recognition; Approximation algorithms; Image recognition; Indexing; Layout; Object recognition; Production facilities; Robot vision systems; Service robots; Shape; Testing;

fLanguage

English

Journal_Title

Robotics and Automation, IEEE Transactions on

Publisher

ieee

ISSN

1042-296X

Type

jour

DOI

10.1109/70.62047

Filename

62047