The paper presents an approach to the detection of deformable objects in single images. To this end we propose a robust match metric so that it preserves the relative edge point neighborhood, but allows significant shape changes. Similar metrics have been used for the detection of rigid objects. To the best of our knowledge is the adaptation to deformable objects new. In addition, we present a fast algorithm for model deformation. In contrast to the widely used thin-plate spline 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, where temporal coherence is needed, we obtain a dense flow 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.     «

The paper presents an approach to the detection of deformable objects in single images. To this end we propose a robust match metric so that it preserves the relative edge point neighborhood, but allows significant shape changes. Similar metrics have been used for the detection of rigid objects. To the best of our knowledge is the adaptation to deformable objects new. In addition, we present a fast algorithm for model deformation. In contrast to the widely used thin-plate spline it is efficient...     »