We present a method for detecting deformable shapes in images. The main difficulty with deformable template models is the very large (or infinite) number of possible nonrigid transformations of the templates. This makes the problem of finding an optimal match of a deformable template to an image incredibly hard. Using a new representation for deformable shapes we show how to efficiently find a global optimal solution to the nonrigid matching problem. Our matching algorithm can minimize a large class of energy functions, making it applicable to a wide range of problems. We present experimental results of detecting shapes in medical and natural images. Because we do not rely on local search techniques, our method is very robust, yielding good matches even in images with high clutter.
Representation and detection of deformable shapes
01.01.2003
373192 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Representation and Detection of Deformable Shapes
British Library Conference Proceedings | 2003
|A robust object category detection system using deformable shapes
British Library Online Contents | 2009
|Determining the similarity of deformable shapes
IEEE | 1995
|Determining the Similarity of Deformable Shapes
British Library Conference Proceedings | 1995
|Sequential mean field variational analysis of structured deformable shapes
British Library Online Contents | 2006
|