In this paper, we address the problem of constrained segmentation of natural images, in which a human user places one seed point inside each object of interest in the image and th...
Our goal was to improve image guidance during minimally invasive image guided therapy by developing an intraoperative segmentation and nonrigid registration algorithm. The algorith...
Simon K. Warfield, Arya Nabavi, Torsten Butz, Kema...
Considering wireless sensor networks for border surveillance, one of the major concerns is sensing coverage. Breach probability can be used as a measure to analyze the tradeoffs a...
Many natural textures comprise structural patterns and show strong self-similarity. We use affine symmetry to segment an image into self-similar regions; that is a patch of textu...
Multiple Instance Learning (MIL) provides a framework for training a discriminative classifier from data with ambiguous labels. This framework is well suited for the task of learni...
Carolina Galleguillos, Boris Babenko, Andrew Rabin...