Vessel Segmentation and Analysis

The aim of this project is to develop a robust and fast vessel segmentation method for fundus images. The segmentation results are evaluated using the HRF database. The method is used as a preprocessing for extraction and visualization vassel features for screening purposes.

Localization of Optic Disk (Optic Nerve Head)

The aim of this project is to develop a method to estimate the coordinates and diameter of the optic disk in fundus images. The results are used to diagnose like glaucoma.

Localization of Macula Region

The aim of this project is to estimate the coordinates of the center of the macula region in fundus images. The results are used in analysis and visualization of macular pigment density measurements for example using spectral filtered images..

Evaluation of Spectral Filtered Fundus Images

The aim of the project is to prove the usefulness of spectral filtered fundus images developed at the eye clinic in Erlangen. The filters are used to balance the saturation of each channels of an RGB image, providing better spectral resolution. The quality of the images are analyzed, and new algorithms are developed to extract features, which are not available by using common fundus images.