Unsupervised and supervised classification of hyperspectral imaging data using projection pursuit and Markov random field segmentation

Abstract

This work presents a classification technique for hyperspectral image analysis when concurrent ground truth is either unavailable or available. The method adopts a principal component analysis (PCA)-based projection pursuit (PP) procedure with an entropy index for dimensionality reduction, followed by a Markov random field (MRF) model-based segmentation. An ordinal optimization approach to PP determines a set of ‘good enough projections’ with high probability, the best among which is chosen with the help of MRF model-based segmentation. When ground-truth is absent, the segmented output obtained is labelled with the desired number of classes so that it resembles the natural scene closely. When the land-cover classes are in detailed level, some special reflectance characteristics based on the classes of the study area are determined and incorporated in the segmentation stage. Segments are evaluated with training samples so as to yield a classified image with respect to the type of ground-truth data. Two illustrations are presented: (i) an AVIRIS-92AV3C image with concurrent ground truth – for both supervised and unsupervised cases and (ii) an EO-1 Hyperion sensor image with concurrent ground-truth at detailed level classes. Provided with the illustrations are comparisons of classification accuracies and computational times of other approaches with those of the proposed methodology. Experimental results demonstrate that the proposed method provides high classification accuracy and is not computationally intensive.