Sciweavers

566 search results - page 12 / 114
» OCR with No Shape Training
Sort
View
AVSS
2008
IEEE
14 years 1 months ago
Recognizing Shapes in Video Sequences Using Multi-class Boosting
We model the spatio-temporal variations of the shape of objects in a video sequence using a unique SVD-like decomposition. The decomposition is used to compute shape features, whi...
Naresh P. Cuntoor, Matt Welborn
ICIP
2007
IEEE
14 years 9 months ago
Projection onto a Shape Manifold for Image Segmentation with Prior
Image segmentation with shape priors has received a lot of attention over the past years. Most existing work focuses on a linearized shape space with small deformation modes aroun...
Florent Ségonne, Patrick Etyngier, Renaud K...
VMV
2004
292views Visualization» more  VMV 2004»
13 years 8 months ago
Automatic Generation of Shape Models Using Nonrigid Registration with a Single Segmented Template Mesh
Statistical shape modeling using point distribution models (PDMs) has been studied extensively for segmentation and other image analysis tasks. Methods investigated in the literat...
Geremy Heitz, Torsten Rohlfing, Calvin R. Maurer J...
CVPR
2001
IEEE
14 years 9 months ago
Learning Models for Object Recognition
We consider learning models for object recognition from examples. Our method is motivated by systems that use the Hausdorff distance as a shape comparison measure. Typically an ob...
Pedro F. Felzenszwalb
AAAI
2000
13 years 8 months ago
Interactive Training for Synthetic Characters
Compelling synthetic characters must behave in ways that reflect their past experience and thus allow for individual personalization. We therefore need a method that allows charac...
Song-Yee Yoon, Robert C. Burke, Bruce Blumberg, Ge...