TY - GEN
T1 - Harmonic deformation model for edge based template matching
AU - Hofhauser, Andreas
AU - Steger, Carsten
AU - Navab, Nassir
PY - 2008
Y1 - 2008
N2 - 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.
AB - 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.
KW - Deformable template matching
KW - Object recognition
KW - Pattern recognition in image understanding
UR - http://www.scopus.com/inward/record.url?scp=57549097696&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:57549097696
SN - 9789898111210
T3 - VISAPP 2008 - 3rd International Conference on Computer Vision Theory and Applications, Proceedings
SP - 75
EP - 82
BT - VISAPP 2008 - 3rd International Conference on Computer Vision Theory and Applications, Proceedings
T2 - 3rd International Conference on Computer Vision Theory and Applications, VISAPP 2008
Y2 - 22 January 2008 through 25 January 2008
ER -