Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Deformable 2D Shape Matching Based on Shape Contexts and Dynamic Programming
 

Summary: Deformable 2D Shape Matching Based on Shape
Contexts and Dynamic Programming
Iasonas Oikonomidis and Antonis A. Argyros
Institute of Computer Science, Forth
and
Computer Science Department, University of Crete
{oikonom,argyros}@ics.forth.gr
http://www.ics.forth.gr/cvrl/
Abstract. This paper presents a method for matching closed, 2D shapes
(2D object silhouettes) that are represented as an ordered collection of
shape contexts [1]. Matching is performed using a recent method that
computes the optimal alignment of two cyclic strings in sub-cubic run-
time. Thus, the proposed method is suitable for efficient, near real-time
matching of closed shapes. The method is qualitatively and quantita-
tively evaluated using several datasets. An application of the method for
joint detection in human figures is also presented.
1 Introduction
Shape matching is an important problem of computer vision and pattern recog-
nition which can be defined as the establishment of a similarity measure between
shapes and its use for shape comparison. A byproduct of this task might also

  

Source: Argyros, Antonis - Foundation of Research and Technology, Hellas & Department of Computer Science, University of Crete

 

Collections: Computer Technologies and Information Sciences