Combining multiscale features for classification of hyperspectral images: a sequence based kernel approach
This is an incremental improvement for researchers in remote sensing and image analysis, offering a better way to handle spatial features in hyperspectral classification.
The paper tackled hyperspectral image classification by proposing a sequence-based kernel (spectrum kernel) instead of concatenating multiscale features into a vector, showing it improves accuracy over conventional kernels on public datasets.
Nowadays, hyperspectral image classification widely copes with spatial information to improve accuracy. One of the most popular way to integrate such information is to extract hierarchical features from a multiscale segmentation. In the classification context, the extracted features are commonly concatenated into a long vector (also called stacked vector), on which is applied a conventional vector-based machine learning technique (e.g. SVM with Gaussian kernel). In this paper, we rather propose to use a sequence structured kernel: the spectrum kernel. We show that the conventional stacked vector-based kernel is actually a special case of this kernel. Experiments conducted on various publicly available hyperspectral datasets illustrate the improvement of the proposed kernel w.r.t. conventional ones using the same hierarchical spatial features.