222 search results - page 20 / 45 » Self-Validated Labeling of Markov Random Fields for Image Se... |
CVPR
2008
IEEE
14 years 10 months ago
2008
IEEE
Spectral clustering and eigenvector-based methods have become increasingly popular in segmentation and recognition. Although the choice of the pairwise similarity metric (or affin...
MICCAI
2007
Springer
14 years 8 months ago
2007
Springer
In this paper, we propose a unified framework for computing atlases from manually labeled data at various degrees of "sharpness" and the joint registration-segmentation o...
DAGM
2008
Springer
13 years 9 months ago
2008
Springer
The design of inference algorithms for discrete-valued Markov Random Fields constitutes an ongoing research topic in computer vision. Large state-spaces, none-submodular energy-fun...
IJCV
2008
13 years 7 months ago
2008
Image segmentation algorithms partition the set of pixels of an image into a specific number of different, spatially homogeneous groups. We propose a nonparametric Bayesian model f...
ICCV
2009
IEEE
13 years 5 months ago
2009
IEEE
Most methods for object class segmentation are formulated as a labelling problem over a single choice of quantisation of an image space - pixels, segments or group of segments. It...