Publication Type
Conference Paper
Publication Date
Page Numbers
842 to 845
Conference Name
28th Annual Inter. Conf. of the IEEE Engineering in Medicine and Biology Society
Conference Location
New York, New York, United States of America
Conference Sponsor
IEEE
Conference Date
-
Abstract
In this work we compare two methods for automatic optic nerve (ON) localization in retinal imagery. The first method uses a Bayesian decision theory is criminator based on four spatial features of the retina imagery. The
second method uses a principal component-based reconstruction to model the ON. We report on an improvement to the model-based technique by incorporating
linear discriminant analysis and Bayesian decision theory methods. We explore a method to combine both techniques to produce a composite technique with high accuracy and rapid throughput. Results are shown for a data set of 395 images with 2-fold validation testing.
