Sciweavers

4298 search results - page 571 / 860
» From Images to Shape Models for Object Detection
Sort
View
FGR
2006
IEEE
157views Biometrics» more  FGR 2006»
16 years 23 days ago
Evaluating Error Functions for Robust Active Appearance Models
Active appearance models (AAMs) are generative parametric models commonly used to track faces in video sequences. A limitation of AAMs is they are not robust to occlusion. A recen...
Barry-John Theobald, Iain Matthews, Simon Baker
ECCV
2002
Springer
16 years 8 months ago
Using Dirichlet Free Form Deformation to Fit Deformable Models to Noisy 3-D Data
Free-form deformations (FFD) constitute an important geometric shape modification method that has been extensively investigated for computer animation and geometric modelling. In t...
Slobodan Ilic, Pascal Fua
167
Voted
SMI
2005
IEEE
16 years 9 days ago
Two-Dimensional Visibility Charts for Continuous Curves
This paper considers computation of visibility for twodimensional shapes whose boundaries are C1 continuous curves. We assume we are given a one-parameter family of candidate view...
Gershon Elber, Robert Sayegh, Gill Barequet, Ralph...
ICIP
2010
IEEE
15 years 4 months ago
Fast and robust active contours for image segmentation
Active models are widely used in applications like image segmentation and tracking. Region-based active models are known for robustness to weak edges and high computational comple...
Wei Yu, Franz Franchetti, Yao-Jen Chang, Tsuhan Ch...
CVPR
2011
IEEE
15 years 4 months ago
Learning Better Image Representations Using 'Flobject Analysis'
Unsupervised learning can be used to extract image representations that are useful for various and diverse vision tasks. After noticing that most biological vision systems for int...
Inmar Givoni, Patrick Li, Brendan Frey