Harmonic deformation model for edge based template matching

Andreas Hofhauser, Carsten Steger, Nassir Navab

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

The paper presents an approach to the detection of deformable objects in single images. To this end we propose a robust match metric that preserves the relative edge point neighborhood, but allows significant shape changes. Similar metrics have been used for the detection of rigid objects (Olson and Huttenlocher, 1997; Steger, 2002). To the best of our knowledge this adaptation to deformable objects is new. In addition, we present a fast algorithm for model deformation. In contrast to the widely used thin-plate spline (Bookstein, 1989; Donato and Belongie, 2002), it is efficient even for several thousand points. For arbitrary deformations, a forward-backward interpolation scheme is utilized. It is based on harmonic inpainting, i.e. it regularizes the displacement in order to obtain smooth deformations. Similar to optical flow, we obtain a dense deformation field, though the template contains only a sparse set of model points. Using a coarse-to-fine representation for the distortion of the template further increases efficiency. We show in a number of experiments that the presented approach in not only fast, but also very robust in detecting deformable objects.

Original languageEnglish
Title of host publicationVISAPP 2008 - 3rd International Conference on Computer Vision Theory and Applications, Proceedings
Pages75-82
Number of pages8
StatePublished - 2008
Event3rd International Conference on Computer Vision Theory and Applications, VISAPP 2008 - Funchal, Madeira, Portugal
Duration: 22 Jan 200825 Jan 2008

Publication series

NameVISAPP 2008 - 3rd International Conference on Computer Vision Theory and Applications, Proceedings
Volume2

Conference

Conference3rd International Conference on Computer Vision Theory and Applications, VISAPP 2008
Country/TerritoryPortugal
CityFunchal, Madeira
Period22/01/0825/01/08

Keywords

  • Deformable template matching
  • Object recognition
  • Pattern recognition in image understanding

Fingerprint

Dive into the research topics of 'Harmonic deformation model for edge based template matching'. Together they form a unique fingerprint.

Cite this