Sciweavers

566 search results - page 63 / 114
» OCR with No Shape Training
Sort
View
ICASSP
2008
IEEE
15 years 4 months ago
View invariant gesture recognition using 3D motion primitives
This paper presents a method for automatic recognition of human gestures. The method works with 3D image data from a range camera to achieve invariance to viewpoint. The recogniti...
Michael B. Holte, Thomas B. Moeslund
ISBI
2007
IEEE
15 years 4 months ago
Locally Adaptive Autoregressive Active Models for Segmentation of 3d Anatomical Structures
Many techniques of knowledge-based segmentation consist of building statistical models that describe the deformations of the structure of interest, and then fit these models to t...
Charles Florin, Nikos Paragios, Gareth Funka-Lea, ...
ACCV
2007
Springer
15 years 4 months ago
Object Detection Combining Recognition and Segmentation
Abstract. We develop an object detection method combining top-down recognition with bottom-up image segmentation. There are two main steps in this method: a hypothesis generation s...
Liming Wang, Jianbo Shi, Gang Song, I-fan Shen
IPMI
2003
Springer
15 years 3 months ago
Neighbor-Constrained Segmentation with 3D Deformable Models
A novel method for the segmentation of multiple objects from 3D medical images using inter-object constraints is presented. Our method is motivated by the observation that neighbor...
Jing Yang, Lawrence H. Staib, James S. Duncan
NSF
1994
Springer
15 years 1 months ago
Physics in a Fantasy World vs. Robust Statistical Estimation
Deformable models in the \physically-based" paradigm are almost always formulated in an ad-hoc fashion, not related to physical reality { they apply the equations on physics i...
Terrance E. Boult, Samuel D. Fenster, Thomas O'Don...