We propose a novel approach to improve the distinctiveness of local image features without significantly affecting their robustness with respect to image deformations. Local image...
We present a new method for training deformable models. Assume that we have training images where part locations have been labeled. Typically, one fits a model by maximizing the l...
This paper presents a new method for detecting scale invariant interest points. The method is based on two recent results on scale space: 1) Interest points can be adapted to scal...
For each patient receiving definitive treatment for cervix cancer, several CT/MR imaging studies need to be registered in order to specify the total physical or biological dose t...
Gary E. Christensen, P. Yin, Michael W. Vannier, K...
We propose a new way of embedding shape distributions in a topological deformable template. These distributions rely on global shape descriptors corresponding to the 3D moment inva...