Sciweavers

25 search results - page 2 / 5
» Natural task decomposition with intrinsic potential fields
Sort
View
CVPR
2009
IEEE
16 years 4 months ago
Increased Discrimination in Level Set Methods with Embedded Conditional Random Fields
We propose a novel approach for improving level set seg- mentation methods by embedding the potential functions from a discriminatively trained conditional random field (CRF) in...
Dana Cobzas (University of Alberta), Mark Schmidt ...
NIPS
2008
14 years 11 months ago
Multiscale Random Fields with Application to Contour Grouping
We introduce a new interpretation of multiscale random fields (MSRFs) that admits efficient optimization in the framework of regular (single level) random fields (RFs). It is base...
Longin Jan Latecki, ChengEn Lu, Marc Sobel, Xiang ...
CVPR
2005
IEEE
15 years 11 months ago
Fields of Experts: A Framework for Learning Image Priors
We develop a framework for learning generic, expressive image priors that capture the statistics of natural scenes and can be used for a variety of machine vision tasks. The appro...
Stefan Roth, Michael J. Black
95
Voted
ERCIMDL
2000
Springer
147views Education» more  ERCIMDL 2000»
15 years 1 months ago
Map Segmentation by Colour Cube Genetic K-Mean Clustering
Segmentation of a colour image composed of different kinds of texture regions can be a hard problem, namely to compute for an exact texture fields and a decision of the optimum num...
Vitorino Ramos, Fernando Muge
CGI
2004
IEEE
15 years 1 months ago
Curvature Tensor Based Triangle Mesh Segmentation with Boundary Rectification
This paper presents a new and efficient algorithm for decomposition of 3D arbitrary triangle mesh into surface patches. Our method is based on the curvature tensor field analysis ...
Guillaume Lavoué, Florent Dupont, Atilla Ba...