Classification and Segmentation Models for Hyperspectral Imaging - An Overview

An advancement in Hyperspectral Imaging (HI) technology is creating important attraction among the researchers to develop better classification techniques. This technology is well known for its high spatial and spectral information due to which the discrimination of materials is much more accurate and efficient. The useful information is extracted in Hyperspectral Imaging technology after applying it in agriculture, biomedical, and disaster management studies. A review comparison has been carried out for air borne images using hyperspectral acquisition hardware for classification as well as segmentation purpose. Numerous approaches that have been focused for implementation namely semi-supervised technique used for hyperspectral imaging using active learning and multinomial logistic regression, Generalized Composite Kernels (GCKs) classification framework, classification of spectral-spatial based data on loopy belief propagation (LBP), multiple feature learning of HI classification, and semi-supervised GCKs with classification accuracy on AVIRIS dataset (59.97%, 92.89%, 81.45%, 75.84%, and 95.50) and segmentation accuracies using α-expansion method as (73.27%, 93.57%, 92.86%, 91.73% and 98.31), respectively.