Artikel
Automatic analysis of retina images regarding Papille and Vessel
Suche in Medline nach
Autoren
-
D. Paulus
- Computervisualistik, Universität Koblenz-Landau, Koblenz
-
S. Chastel
- Computervisualistik, Universität Koblenz-Landau, Koblenz
| Veröffentlicht: | 22. September 2004 |
|---|
Gliederung
Text
Detection of the papilla region and vessel detection on images of the retina are problems that can be solved by pattern recognition techniques. Fundus images can be used as well as topographic image as provided, e.g. by the HRT device. We present methods for papilla detection based on surface approximations of the papilla region; alternatively, a combination of line detection, image morphology, and Hough transform can be used in reflectivity images.
Vessels can be found with matched filters (wavelets, derivatives of the Gaussian, etc.). The parameter of these models can be chosen fixed which leads to an accurate detection of vessels of a certain width. An automatic adaptation of the parameters allows for the detection of vessels with varying diameters.
An alternative to these parametric approaches can be found when image morphology is applied. In our contribution we describe and compare these approaches.
