Online dictionary self-taught learning for hyperspectral image classification

We study self-taught learning for hyperspectral image (HSI) classification with small labeled and unlabeled data sets. Supervised deep learning methods are currently state of the art for many machine learning problems, but these methods require large quantities of labeled data to be effective. Unfortunately, existing labeled HSI benchmarks are too small to train a deep supervised network. Alternatively, self-taught learning methods use sufficiently large quantities unlabeled data to improve the performance on a given image classification task. However, the unlabeled HSI data is also difficult to obtain. To overcome this limitation, we employ an online dictionary learning algorithm for sparse coding to self-taught learning, in which we extract features from much smaller unlabeled data sets. Furthermore, apart from the spectral information we also apply the spatial information to improve the performance of classification. Our results convinced that the proposed approach can extract discriminative features from small unlabeled and labeled data sets for classification. In addition, the results obtained by our approach are better than the results obtained by principal component analysis (PCA).