Sciweavers

563 search results - page 43 / 113
» Feature Space Trajectory Methods for Active Computer Vision
Sort
View
CVPR
2006
IEEE
14 years 11 months ago
Activity Analysis in Microtubule Videos by Mixture of Hidden Markov Models
We present an automated method for the tracking and dynamics modeling of microtubules -a major component of the cytoskeleton- which provides researchers with a previously unattain...
Alphan Altinok, Motaz A. El Saban, Austin J. Peck,...
ICPR
2010
IEEE
13 years 11 months ago
Geodesic Active Fields on the Sphere
In this paper, we propose a novel method to register images defined on spherical meshes. Instances of such spherical images include inflated cortical feature maps in brain medical ...
Dominique Zosso, Jean-Philippe Thiran
SCALESPACE
2007
Springer
14 years 3 months ago
Combining Different Types of Scale Space Interest Points Using Canonical Sets
Scale space interest points capture important photometric and deep structure information of an image. The information content of such points can be made explicit using image recons...
Frans Kanters, Trip Denton, Ali Shokoufandeh, Luc ...
CVPR
2007
IEEE
14 years 11 months ago
Connecting the Out-of-Sample and Pre-Image Problems in Kernel Methods
Kernel methods have been widely studied in the field of pattern recognition. These methods implicitly map, "the kernel trick," the data into a space which is more approp...
Pablo Arias, Gregory Randall, Guillermo Sapiro
CVPR
2010
IEEE
14 years 1 months ago
Local Features Are Not Lonely - Laplacian Sparse Coding for Image Classification
Sparse coding which encodes the original signal in a sparse signal space, has shown its state-of-the-art performance in the visual codebook generation and feature quantization pro...
Shenghua Gao, Wai-Hung Tsang, Liang-Tien Chia, Pei...