The Kolmogorov–Sinai Entropy in the Setting of Fuzzy Sets for Atmospheric Corrosion Image Texture Analysis

Abstract

Image analysis gives us a new opportunity in corrosion science. Fuzzy Kolmogorov–Sinai (K–S) entropy is used to quantify the average amount of uncertainty of a dynamical system through a sequence of observations. The fuzzy K–S entropy for horizontal and vertical orientations is sensitive to distribution of corrosion product or corrosion degree, and the entropy values decrease as the corrosion becomes more and more serious. It is concluded that the fuzzy K–S entropy is illustrated as an effective feature for image analysis and corrosion classification.