Research >> Feature extraction


Feature extraction


Our feature extraction algorithms "trace" out the vascular structure
of the retina. The earliest algorithm, developed by Professor Roysam's
group, traces using a two-sided edge model. This has been extended to
accurate measurement of vessel width. A more recent algorithm is built
on a more sophisticated model of the appearance of a vesselness.


Faculty: Chuck Stewart

Current Students: Michal Sofka

Former Students: Ken Fritzche


Project website and executable:


M. Sofka and C.V. Stewart, "Retinal Vessel Extraction Using Multiscale
Matched Filters, Confidence and Edge Measures",
IEEE Transactions on Medical Imaging, vol. 25, no. 12, pp. 1531-1546, Dec. 2006. [ pdf ] [ bib ]


K. Fritzsche, A. Can, H. Shen, C. Tsai, J. Turner, H. Tanenbuam, C. Stewart,
and B. Roysam. Automated model based segmentation, tracing and analysis
of retinal vasculature from digital fundus images. In J. S. Suri and S. Laxminarayan,
editors, State-of-The-Art Angiography, Applications and Plaque Imaging Using
MR, CT, Ultrasound and X-rays, pages 225–298. Academic Press, 2003. [ bib ]


K. Fritzsche. Computer Vision Algorithms for Retinal Vessel Detection and Width
Change Detection. PhD thesis,
Rensselaer Polytechnic Institute, Troy, New York,
Dec 2004.


A. Can, H. Shen, J. N. Turner, H. L. Tanenbaum, and B. Roysam. Rapid automated
tracing and feature extraction from live high-resolution retinal fundus images using
direct exploratory algorithms. IEEE Transactions on Information Technology in
, 3(2):125–138, 1999. [ pdf ] [ bib ]


Home | People | Research | Publications | Contact | News/Events | Download | Links