No abstract

No abstract

Abstract-An unsupervised method for selecting training data is suggested here. The method is tested by applying it to hyperspectral land-use classification. The data set is reduced using an unsupervised band selection method and then clustered with a non parametric cluster technique. The cluster technique provides centers of the clusters and those are the samples selected to compose the training set. Both the band selection and the clustering are unsupervised techniques. Afterwards an expert labels those samples and the rest of unlabeled data can be classified. The inclusion of the selection step, although unsupervised, allows to select automatically the most suitable pixels to build the classifier. This reduces the expert effort because less pixels need to be labeled. However, the classification results are significantly improved in comparison with results obtained by a random selection of training samples, in particular for very small training sets.

Edge detection in hyperspectral images is an intrinsically difficult problem as the gray value intensity images related to single spectral bands may show different edges. The few existing approaches are either based on a straight forward combining of these individual edge images, or on finding the outliers in a region segmentation. As an alternative, we propose a clustering of all image pixels in a feature space constructed by the spatial gradients in the spectral bands. An initial comparative study shows the differences and properties of these approaches and makes clear that the proposal has interesting properties that should be studied further.