| | |
Summary: A HYBRID FEATURE SELECTION STRATEGY FOR IMAGE DEFINING
FEATURES: TOWARDS INTERPRETATION OF OPTIC NERVE IMAGES
1
JIN YU, 1
SYED SIBTE RAZA ABIDI, 2
PAUL HABIB ARTES
1
Faculty of Computer Science, Dalhousie University, Halifax B3H 1W5, Canada
2
Deptartment of Ophthalmology and Visual Sciences, Dalhousie University, Halifax B3H 1W5, Canada
E-MAIL: sraza@cs.dal.ca
Abstract:
Modern imaging techniques such as Confocal
Scanning Laser Tomography (CSLT) capture
high-quality optic nerve images. The automated analysis
of CSLT images, by combining image processing and
data mining methods, offers the potential for developing
objective methods for supporting clinical
decision-making in glaucoma. We present our approach
that involves the analysis of CSLT images using moment
|
