Associative Learning of Standard Regularizing Operators in Early Vision
Standard regularization methods can be used to solve satisfactorily several problems in early vision, including edge detection, surface reconstruction, the computation of motion and the recovery of color. In this paper, we suggest (a) that quadratic variational principles corresponding to standard r...
Main Authors: | , |
---|---|
Format: | Working Paper |
Language: | en_US |
Published: |
MIT Artificial Intelligence Laboratory
2008
|
Online Access: | http://hdl.handle.net/1721.1/41218 |