Hyper spectral Image Segmentation Using the Concept of Data Stuctures

Abstract

The optimal exploitation of the information provided by hyperspectral images requires the development of advanced Image processing tools. This paper introduces a new hierarchical structure representation for such images using binary Partition trees (BPT). Based on region merging techniques using statistical measures, this region-based representation reduces the number of elementary primitives and allows a more robust. Filtering, segmentation, classification or information retrieval. To demonstrate BPT capabilities, we then propose a pruning strategy in order to perform a classification. Labeling each BPT node with SVM classi.ers outputs, a pruning decision based on an impurity measure is addressed. Experimental results on two different hyperspectral data sets have demonstrated the good performances of a BPT-based representation.

Keywords: Hyper Spectral Imaging, Binary Partition Tree, segmentation, classification, filtering.