Sciweavers

1935 search results - page 171 / 387
» E-Learning Applied To Computer Vision
Sort
View
108
Voted
ICCV
2007
IEEE
16 years 4 months ago
Penrose Pixels Super-Resolution in the Detector Layout Domain
We present a novel approach to reconstruction based superresolution that explicitly models the detector's pixel layout. Pixels in our model can vary in shape and size, and th...
Moshe Ben-Ezra, Zhouchen Lin, Bennett Wilburn
111
Voted
ICPR
2004
IEEE
16 years 3 months ago
Incorporating Temporal Context with Content for Classifying Image Collections
Semantic scene classification is an open problem in image understanding, especially when information purely from image content (i.e., pixels) is employed. However, in applications...
Jiebo Luo, Matthew R. Boutell
113
Voted
ACCV
2009
Springer
15 years 9 months ago
Better Correspondence by Registration
Accurate image correspondence is crucial for estimating multiple-view geometry. In this paper, we present a registration-based method for improving accuracy of the image correspond...
Shufei Fan, Rupert Brooks, Frank P. Ferrie
131
Voted
ICPR
2008
IEEE
15 years 9 months ago
A clustering algorithm combine the FCM algorithm with supervised learning normal mixture model
In this paper we propose a new clustering algorithm which combines the FCM clustering algorithm with the supervised learning normal mixture model; we call the algorithm as the FCM...
Wei Wang, Chunheng Wang, Xia Cui, Ai Wang
ECCV
2006
Springer
15 years 6 months ago
Articulated Motion Segmentation Using RANSAC with Priors
Articulated motions are partially dependent. Most of the existing segmentation methods, e.g. Costeira and Kanade[2], can not be applied to articulated motions. We propose a novel ...
Jingyu Yan, Marc Pollefeys