Search
Skip to Search Results- 3Reinforcement Learning
- 2Computer Vision and Multimedia Communications
- 13D imaging
- 13D thinning alogorithms
- 1Automatic brain tumor segmentation
- 1Decision making. Mathematical models.
-
2008
Technical report TR08-11. 3D thinning algorithms are generally faster than any other connectivity-preservation skeletonization methods. However, most 3D thinning algorithms cannot guarantee to generate unit-width skeleton. This document describes an algorithm to generate unit-width skeleton ...
-
2007
Wang, Tao, Schuurmans, Dale, Bowling, Michael, Lizotte, Daniel
Technical report TR07-05. We investigate novel, dual algorithms for dynamic programming and reinforcement learning, based on maintaining explicit representations of stationary distributions instead of value functions. In particular, we investigate the convergence properties of standard dynamic...
-
Spring 2010
Skeletonization and segmentation are two important techniques for object representation and analysis. Skeletonization algorithm extracts the “centre-lines” of an object and uses them to efficiently represent the object. It has many applications in various areas, such as computer-aided design,...
-
2008
Technical report TR08-10. A parametric active contour model based on dynamic boundary vector flow is presented in this paper. The contribution of this model is two-fold. First, it has the largest capture range. Second, it is able to extract concave shape. We apply this method to infant brain...
-
2006
Wang, Tao, Schuurmans, Dale, Bowling, Michael
Technical report TR06-26. We investigate the dual approach to dynamic programming and reinforcement learning, based on maintaining an explicit representation of stationary distributions as opposed to value functions. A significant advantage of the dual approach is that it allows one to exploit...
-
2007
Wang, Tao, Bowling, Michael, Lizotte, Daniel, Schuurmans, Dale
Technical report TR07-10. We propose to use a new dual approach to dynamic programming. The idea is to maintain an explicit representation of stationary distributions as opposed to value functions. A significant advantage of the dual approach is that it allows one to exploit well developed...
-
2008
Lizotte, Daniel, Wang, Tao, Bowling, Michael, Schuurmans, Dale
Technical report TR08-16. We propose a dual approach to dynamic programming and reinforcement learning based on maintaining an explicit representation of visit distributions as opposed to value functions. An advantage of working in the dual is that it allows one to exploit techniques for...
-
2005
Technical report TR05-32. An algorithm for automatic estimation of 3D transformations between two objects is presented in this paper. Skeletons of the 3D objects are created with a fully parallel thinning algorithm and feature point pairs (land markers) are extracted from skeletons automatically,...
-
Automatic Brain Tumor Segmentation with Normalized Gaussian Bayesian Classifier and Fluid Vector Flow
Download2009
Technical report TR09-11. An automatic brain tumor segmentation method is presented in this paper. This method has 3 stages. In the first stage, a so-called Normalized Gaussian Mixture Model (NGMM) is proposed and used to model the brain tissues. In the second stage, a Gaussian Bayesian...