We present a quantitative method for the comparison of vascular topology and geometry measured from retinal fundus photographs. The measure compares the difference between distributions taken from a graph representation of the vasculature, which is derived by image segmentation. The measure uses the Kullback-Leibler distance between statistical measures on… (More)
in 2001. He is currently studying for his PhD in Medical Image Processing at Warwick University and is working on the application of Markov Chain Monte Carlo methods to the problems in image analysis and, in particular, for retinal imagery. His research interest include biomedical image processing and statistical image analysis.