Eva Dittrich: Automatic Model Generation for Sparse MRF Appearance Models using MDL
| What |
|
|---|---|
| When |
Oct 17, 2008 from 04:40 pm to 04:40 pm |
| Where | Sem 183-2 |
| Contact Name | Yll Haxhimusa |
| Contact Email | yll@prip.tuwien.ac.at |
| Contact Phone | 18370 |
| Add event to calendar |
vCal
iCal
|
Title: Automatic Model Generation for Sparse MRF Appearance Models using Minimum Description Length
(Praktikumsabschlusspräsentation)
In the work the Minimum Description Length (MDL) approach was combined with Sparse MRF Appearance Models (SAMs). SAMs are a method to locate a structure that is learnt from annotated training data in a new and unseen image. However, to achieve this result it is necessary to provide the SAMs with manual annotations of the images (landmarks), which is a time consuming and error-prone requirement. The goal of this project was to become independent from these manual annotations and to obtain the annotations automatically by using an MDL based approach. The quality of the resulting annotations was tested extensively with different types of data (synthetic data, 2D X-rays and 3D CTs) and the method was modified to reach the best possible results for each of them. The resulting approach allows to construct SAMs in a fully automated fashion.
