Subspace Multinomial Logistic Regression Ensemble for Classification of Hyperspectral Images

Exploiting multiple complementary classifiers in an ensemble framework has shown to be effective for improving hyperspectral image classification results, specially when the training samples are limited. With a different principle and based on this assumption that hyperspectal feature vectors effectively lie in a low-dimensional subspace, the subspace-based techniques have shown great classification performance. In this work, we propose a new ensemble method for accurate classification of hyperspectral images, which exploits the concept of subspace projection. For this purpose, we extend the subspace multinomial logistic regression classifier (MLRsub) to learn from multiple random subspaces for each class. More specifically, we impose diversity in constructing MLRsub by randomly selecting bootstrap samples from the training set and subsets of the original hyperspectral feature space, which lead to generate different class subspace features. Experimental results, conducted on two real hyperspectral data sets, indicate that the proposed method provides significant classification results in comparison with other state-of-the-art approaches.