Sciweavers

531 search results - page 64 / 107
» Using Photometric Invariants for 3D Object Recognition
Sort
View
ICCV
2003
IEEE
16 years 1 months ago
Using Specularities for Recognition
Recognition systems have generally treated specular highlights as noise. We show how to use these highlights as a positive source of information that improves recognition of shiny...
Margarita Osadchy, David W. Jacobs, Ravi Ramamoort...
AVI
2000
15 years 1 months ago
Diagrams Based on Structural Object Perception
Most diagrams, particularly those used in software engineering, are line drawings consisting of nodes drawn as rectangles or circles, and edges drawn as lines linking them. In the...
Pourang Irani, Colin Ware
ICPR
2004
IEEE
16 years 29 days ago
Neural Network Based Modeling and Color Rendering for Mixed Reality
This paper describes a new approach to color image rendering for mixed reality applications. The approach has two steps. The first uses neural network based photometric stereo to ...
Haruki Kawanaka, Kenji Funahashi, Robert J. Woodha...
3DOR
2008
15 years 2 months ago
Characterizing Shape Using Conformal Factors
We present a new 3D shape descriptor based on conformal geometry. Our descriptor is invariant under non-rigid quasi-isometric transformations, such as pose changes of articulated ...
Mirela Ben-Chen, Craig Gotsman
ACIVS
2006
Springer
15 years 3 months ago
Context-Based Scene Recognition Using Bayesian Networks with Scale-Invariant Feature Transform
Scene understanding is an important problem in intelligent robotics. Since visual information is uncertain due to several reasons, we need a novel method that has robustness to the...
Seung-Bin Im, Sung-Bae Cho