Efficient inference and learning for computer vision labelling problems
Discrete energy minimization has recently emerged as an indispensable tool for computer vision problems. It enables inference of the maximum a posteriori solutions of Markov and conditional random fields which can be used to model labelling problems in vision. When formulating such problems in an en...
| Main Author: | |
|---|---|
| Published: |
Oxford Brookes University
2010
|
| Subjects: | |
| Online Access: | http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.530806 |