2019 IEEE Congress on Evolutionary Computation (CEC) | 2019
A Binary NSGA-III for Unsupervised Band Selection in Hyper-spectral Satellite Images
Abstract
High spectral correlation among bands lead to unsupervised band selection problem in hyper-spectral images. Moreover, the presence of large number of spectral bands increase the classification complexity task. This matter is efficiently handled by non-dominated sorting method in third version of NSGA algorithm (NSGA-III). However, a concern about the NSGA-III algorithm is that it uses crossover operator for real-value initialized population. To overcome with this problem, present study introduces logical crossover and mutation operator to strengthen the performance of NSGA-III to select optimal set of bands. This enhanced algorithm is named as ‘Binary NSGA-III’ which is further implemented in order to separate distinguish spectral classes. Further, the optimized set of bands is used as feature set to provide automated classification system using K-means technique. The experimental results demonstrate the promising discriminant potential when compared against conventional methods.