IMI/Publicaţii/CSJM/Ediţii/CSJM v.22, n.2 (65), 2014/

Detection of Blood Vessels in Retinal Fundus Images

Authors: Faraz Oloumi, Ashis K. Dhara, Rangaraj M. Rangayyan, Sudipta Mukhopadhyay
Keywords: Gabor filter, line operator, matched filter, multiscale analysis, retinal fundus image, vessel detection, vesselness measure.


Detection of blood vessels in retinal fundus images is an important initial step in the development of systems for computer-aided diagnosis of pathologies of the eye. In this study, we perform multifeature analysis for the detection of blood vessels in retinal fundus images. The vessel detection techniques implemented include multiscale vesselness measures, Gabor filters, line operators, and matched filters. The selection of an appropriate threshold is crucial for accurate detection of retinal blood vessels. We evaluate an adaptive threshold selection method along with several others for this purpose. We also propose a postprocessing technique for removal of false-positive pixels around the optic nerve head. Values of the area under the receiver operating characteristic curve of up to 0.961 were obtained using the 20 test images of the DRIVE database.

Faraz Oloumi and Rangaraj M. Rangayyan
Department of Electrical and Computer Engineering,
Schulich School of Engineering, University of Calgary,
Calgary, Alberta, Canada T2N 1N4.
Phone: +1 (403) 220 − 6745

Ashis K. Dhara and Sudipta Mukhopadhyay
Department of Electronics and Electrical Communication Engineering,
Indian Institute of Technology,
Kharagpur 721302, India
Phone: +91 3222 283568


Adobe PDF document0.67 Mb