Output details

An ensemble classification based approach applied to retinal blood vessel segmentation

<24> Building on the experience in classification techniques, this paper describes work that applies Ensemble classification over to ophthalmic image analysis for the first time. The implemented system achieved state-of-the-art performance when applied to publicly available datasets. It also proved robust and reliable when applied to challenging new datasets where vessel profile variability is problematic for other types of algorithms. My contribution to the paper is as the primary supervisor (Director of Studies) of the PhD student (Fraz) who implemented the algorithm.