We propose a registration algorithm based on successively refined quantization and an alignment metric derived from a minimal spanning tree entropy estimate. The metric favors edg...
We propose in this paper an interactive segmentation algorithm based on curve evolution techniques. The task of automated segmentation has proven to be highly complex and applicat...
Most tracking algorithms detect moving objects by comparing incoming images against a reference frame. Crucially, this reference image must adapt continuously to the current light...
Jonathan D. Rymel, John-Paul Renno, Darrel Greenhi...
Skin detection or segmentation is employed in many tasks related to the detection and tracking of humans and human-body parts. However, skin detection is not robust enough for dea...
Pixels in hyperspectral images usually contain spectra from several classifiable objects, so that the recorded pixel is a mixture of the classes. Current methods estimate the prop...
Face localization is the process of finding the exact position of a face in a given image. This can be useful in several applications such as face tracking or person authenticatio...
We present a new model for the extraction of networks from images in the presence of occlusions. Such occlusions cause gaps in the extracted network that need to be closed. Using ...
In this paper, an information theoretic framework for image segmentation is presented. This approach is based on the information channel that goes from the image intensity histogr...
DCT-based CODECs such as MPEG-4 Visual and H.263 "skip" many macroblocks during encoding of typical video sequences (i.e. no coded data is transmitted for these macroblo...