Authors:
Andreas Hofhauser
1
;
Carsten Steger
2
and
Nassir Navab
1
Affiliations:
1
Technische Universität München, Germany
;
2
MVTec Software GmbH, Germany
Keyword(s):
Deformable Template Matching, Pattern Recognition in Image Understanding, Object recognition.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Data Manipulation
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Methodologies and Methods
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Soft Computing
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 o
f 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.
(More)