LINGUISTIC DESCRIPTION OF PATTERNS FROM MINED IMAGES

摘要

The objective of this paper is to propose an approach to describe patterns in remote-sensed images utilising fuzzy logic. The general form of a linguistically quantified proposition is "QY's are F" where Q is a fuzzy linguistic quantifier, Y is a class of objects and F is a summary that applies to that class. The truth of such a proposition can be determined for each object characterised by a tuple in the database. Fuzzy descriptions of linguistic summaries help to evaluate the degree to which a summary describes an object or pattern in the image. A genetic algorithm technique is used to obtain optimal solutions that describe all the objects or patterns in the database. Image mining is used to extract unusual patterns from multi-dated satellite images of a geographic area.