Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Curvature Based Signatures for Object Description and Recognition
 

Summary: Curvature Based Signatures
for Object Description and Recognition
Elli Angelopoulou, James P. Williams, Lawrence B. Wolff
Computer Vision Laboratory, Department of Computer Science,
The Johns Hopkins University, Baltimore, MD 21218, USA
e-mail: {angelop, jimbo, wolff}@cs.jhu.edu
Abstract. An invariant related to Gaussian curvature at an object point is
developed based upon the covariance matrix of photometric values related to
surface normals within a local neighborhood about the point. We employ three
illumination conditions, two of which are completely unknown. We never
need to explicitly know the surface normal at a point. The determinant of the
covariance matrix of these three-tuples in the local neighborhood of an object
point is shown to be invariant with respect to rotation and translation. A way
of combining these determinants to form a signature distribution is formulated
that is rotation, translation, and, scale invariant. This signature is shown to be
invariant over large ranges of poses of the same objects, while being signifi-
cantly different between distinctly shaped objects. A new object recognition
methodology is proposed by compiling signatures for only a few poses of a
given object.
1 Introduction

  

Source: Angelopoulou, Elli - Department of Computer Science, Friedrich Alexander University Erlangen Nürnberg

 

Collections: Computer Technologies and Information Sciences