Study of SigmoidSpectral Composite Kernel based noise classifier with entropy in handling non linear separation of classes

This paper gives an implemented explanation of incorporating composite kernel methods with fuzzy based image classifiers. The work demonstrates how non linearity among the different classes of remote sensing data with uncertainty are handled with Noise classifier with entropy(fuzzy classifier) using composite kernel technique for land use/land cover maps generation. This study has incorporated the composition of two prominent kernels Spectral and Sigmoid Kernel. The performance of the classifier is evaluated in supervised mode and, the assessment of accuracy has been carried out using FERM (Fuzzy Error Matrix), SCM (Sub-pixel Confusion Uncertainty Matrix). The basic objective is to optimize the resolution parameter ‘(δ’, regularizing parameter ‘v’ and weight factor λ for Composite Kernel based Noise clustering with entropy classifier (Composite-KNCWE) and analysis of the classified fraction images.