Sciweavers

1877 search results - page 184 / 376
» A new method for bottleneck detection
Sort
View
CVPR
2011
IEEE
14 years 6 months ago
FlowBoost - Appearance Learning from Sparsely Annotated Video
We propose a new learning method which exploits temporal consistency to successfully learn a complex appearance model from a sparsely labeled training video. Our approach consists...
Karim Ali, Francois Fleuret, David Hasler
ISMAR
2009
IEEE
15 years 5 months ago
Augmenting text document by on-line learning of local arrangement of keypoints
We propose a technique for text document tracking over a large range of viewpoints. Since the popular SIFT or SURF descriptors typically fail on such documents, our method conside...
Hideaki Uchiyama, Hideo Saito
111
Voted
MICCAI
2003
Springer
15 years 12 months ago
Hierarchical Segmentation of Thin Structures in Volumetric Medical Images
We introduce a new method for segmentation of 3D medical data based on geometric variational principles. A minimal variance criterion is coupled with a geometric edge alignment mea...
Michal Holtzman-Gazit, Dorith Goldsher, Ron Kimmel
ICDS
2009
IEEE
15 years 5 months ago
Local Contrast Segmentation to Binarize Images
—In this paper, a new binarization algorithm for degraded document images is proposed. The method is based on positive and negative pixel energies using the Laplacian of an image...
Marco Block, Raúl Rojas
57
Voted
GI
2007
Springer
15 years 5 months ago
Enhanced Disparity Computation for ADAS Applications
: Many of ADAS applications such as pedestrian and vehicle detection are using stereo vision. By computing the well-known disparity the range of objects ahead of the car can be det...
Basel Fardi, Ammar Abbas, Gerd Wanielik