We study unsupervised learning of occluding objects in images of visual scenes. The derived learning algorithm is based on a probabilistic generative model which parameterizes obj...
Image processing applications need shorter processing times. This requires the parallelization of low and mid levels sequential process chains on specific machines. In this paper ...
A region based algorithm for segmentation motivated by a parallel implementation is introduced. It is obtained by combining the watershed transform with further merging based on a...
The paper first traces the image-based modeling back to feature tracking and factorization that have been developed in the group led by Kanade since the eighties. Both feature tra...
We present a novel approach, clustering on local image profiles, for statistically characterizing image intensity in object boundary regions. In deformable model segmentation, a d...
Joshua Stough, Stephen M. Pizer, Edward L. Chaney,...