Please use this identifier to cite or link to this item: doi:10.22028/D291-26376
Title: Retinal vessel detection via second derivative of local radon transform
Author(s): Krause, Michael
Alles, Ralph M.
Burgeth, Bernhard
Weickert, Joachim
Language: English
Year of Publication: 2008
Free key words: retinal imaging
vessel detection
vessel segmentation
local radon transform
conjunctiva vessels
DDC notations: 510 Mathematics
Publikation type: Other
Abstract: For the automatic detection of retinal blood vessels a preprocessing of the noisy original images is necessary. Retinal blood vessels are assumed to be line-like structures and can therefore be enhanced via convolution with suitable, elongated kernels. Consequently we use the local Radon kernel as a prototype of an elongated kernel for this task. The Radon kernel is rotated at different angles and adapts via a maximisation procedure to the directions of the vessels. The proposed algorithm is easy to implement and combined with edge- and coherence-enhancing anisotropic diffusion as a preprocessing step it offers higher robustness than the Laplacian of Gaussian or Haralick operator. Furthermore, our algorithm detects vessels as connected structures with very few interruptions. The performance is evaluated in experiments on the publicly available databases DRIVE and STARE as well as on selected examples of our clinical database. Since our algorithm does not depend on a priori directional and branching models, in its generality it is capable to detect other vessel structures in the human eye such as the conjunctiva vessels.
Link to this record: urn:nbn:de:bsz:291-scidok-47429
Series name: Preprint / Fachrichtung Mathematik, Universität des Saarlandes
Series volume: 212
Date of registration: 11-Apr-2012
Faculty: MI - Fakultät für Mathematik und Informatik
Department: MI - Mathematik
Collections:SciDok - Der Wissenschaftsserver der Universität des Saarlandes

Files for this record:
File Description SizeFormat 
preprint_212_08.pdf5,72 MBAdobe PDFView/Open

Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.