Fast extracting of change area from remote sensing image by Fuzzy theory and case base reasoning

This study presents the technology to combine the remote sensing image of SPOT and FORMOSAT-2 satellite image by Fuzzy theory and case base reasoning. This method adopt three experience identify factors of NDVI, shape, and color to establish the membership function. The Fuzzy theory was applied to estimate the process of thinking as the human brain; while the Case Base Reasoning method was used to increase the capability of self-loop learning and support its consistency with the real nature. The results show that the successful rate of identification was between 90 percent. The Case Base Reasoning results show that the two data similarity was between 46 percent. The Fuzzy and Case Base Reasoning difference factor was (satellite sensors, inclination, date, shadowing, etc.). The rate can be increase if there is enough experienced data. It reveal that fuzzy theory with case base reasoning indeed can rapid screen the change area from remote sensing image in before and after the disaster event.