CHARACTERIZATION OF ECOTONES USING MEMBERSHIP DEGREES COMPUTED WITH AFUZZY CLASSIFIER

Ecotones zones lie between homogeneous ecological systems. They are ch aracterised on images by heterogeneous pixels in a specific neighbourh ood. Fuzzy classifiers output membership degrees that better represent the heterogeneity within a pixel and can be further processed within the context of a local neighbourhood. This Letter formalises these not ations. Two coral reef systems examples are presented. They illustrate the use of possibility measurement to characterise ecotones, and the use of information on well-known ecotones to increase the accuracy of image classification.