Combination of sparse and semi-supervised learning for classification of hyperspectral images

In the classification of hyperspectral images with supervised methods, the generation of ground-truth information for a hyperspectral image is a challenging process in terms of time and cost. Besides, amount of the labeled data affects the classifier performance. In this study, as a solution of this problem a hyperspectral image classifier is proposed with semi-supervised learning, support vector machines and sparse representation classifier. In the first phase to improve the classification performance, limited number of training data increased by semi-supervised learning. Classification process is performed with support vector machines, sparse representation classifier and combination of these two classifiers. According to the acquired classification results, close classification performance is obtained by combined system with small number of training data to the supervised classification.