Functional dissipation classification of retinal images

摘要

Retinal images can be classified by selecting a classifier and a figure of merit for quantifying classification quality; selecting a transform to generate features from input data; using a recursive process of functional dissipation to generate dissipative features from the features generated according to the transform; computing the figure of merit for all of the dissipative features generated; searching for at least one of the dissipative features that maximize the figure of merit on a training set; and classifying a test set with the classifier by using the “at least one of the dissipative features.”