Minimum Description Length Shape and Appearance Models |
Hans Henrik Thodberg
|
| Abstract | The Minimum Description Length (MDL) approach to shape modelling is reviewed. It solves the point correspondence problem of selecting points
on shapes defined as curves so that the points correspond across a data set. An efficient numerical implementation is presented and made available as open source Matlab code. The problems with the early MDL approaches are discussed. Finally the MDL approach is extended to an MDL Appearance Model, which is proposed as a means to perform unsupervised image segmentation. |
| Keywords | Shape Modelling, Minimum Description Length, Appearance Models, Point Correspondence Problem, Unsupervised Vision, Image Segmentation |
| Type | Conference paper [With referee] |
| Conference | Proceedings of Information Processing in Medical Imaging (IPMI 2003) , |
| Editors | C. Taylor and J. A. Noble |
| Year | 2003 |
| Publisher | Springer |
| Series | Lecture Notes In Computer Science (LNCS) 2732 |
| Electronic version(s) | [pdf] |
| BibTeX data | [bibtex] |
| IMM Group(s) | Image Analysis & Computer Graphics |