Sciweavers

149 search results - page 10 / 30
» Robust Active Appearance Model Matching
Sort
View
CVPR
2008
IEEE
14 years 9 months ago
Parameterized Kernel Principal Component Analysis: Theory and applications to supervised and unsupervised image alignment
Parameterized Appearance Models (PAMs) (e.g. eigentracking, active appearance models, morphable models) use Principal Component Analysis (PCA) to model the shape and appearance of...
Fernando De la Torre, Minh Hoai Nguyen
FGR
2004
IEEE
160views Biometrics» more  FGR 2004»
13 years 11 months ago
A Comparison of Shape Constrained Facial Feature Detectors
We consider the problem of robustly and accurately locating facial features. The relative positions of different feature points are represented using a statistical shape model. We...
David Cristinacce, Timothy F. Cootes
ICASSP
2011
IEEE
12 years 11 months ago
Efficient block-division model for robust multiple object tracking
Tracking multiple objects under occlusion is one of the most challenging issues in computer vision. Occlusion results in mistaken match when finding the most similar candidate. A...
Wenhan Luo, Xiaoqin Zhang, Yang Liu, Xi Li, Weimin...
CVPR
1996
IEEE
13 years 11 months ago
3-D model-based tracking of humans in action: a multi-view approach
We present a vision system for the 3-D modelbased tracking of unconstrained human movement. Using image sequences acquired simultaneously from multiple views, we recover the 3-D b...
Dariu Gavrila, Larry S. Davis
CVPR
2006
IEEE
14 years 9 months ago
Robust AAM Fitting by Fusion of Images and Disparity Data
Active Appearance Models (AAMs) have been popularly used to represent the appearance and shape variations of human faces. Fitting an AAM to images recovers the face pose as well a...
Joerg Liebelt, Jing Xiao, Jie Yang