A hybrid interval type-2 semi-supervised possibilistic fuzzy c-means clustering and particle swarm optimization for satellite image analysis

Although satellite images can provide more information about the earth’s surface in a relatively short time and over a large scale, they are affected by observation conditions and the accuracy of the image acquisition equipment. The objects on the images are often not clear and uncertain, especially at their borders. The type-1 fuzzy set based fuzzy clustering technique allows each data pattern to belong to many different clusters through membership function (MF) values, which can handle data patterns with unclear and uncertain boundaries well. However, this technique is quite sensitive to noise, outliers, and limitations in handling uncertainties. To overcome these disadvantages, we propose a hybrid method encompassing interval type-2 semi-supervised possibilistic fuzzy c-means clustering (IT2SPFCM) and Particle Swarm Optimization (PSO) to form the proposed IT2SPFCM-PSO. We experimented on some satellite images to prove the effectiveness of the proposed method. Experimental results show that the IT2SPFCM-PSO algorithm gives accuracy from 98.8% to 99.39% and is higher than that of other matching algorithms including SFCM, SMKFCM, SIIT2FCM, PFCM, SPFCM-W, SPFCM-SS, and IT2SPFCM. Analysis of the results by indicators PC-I, CE-I, D-I, XB-I, t -I, and MSE also showed that the proposed method gives better results in most experiments.