Hyperspectral image segmentation: The butterfly approach

• Published in: 2009 First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing pp. 1 - 4
• Main Authors: Gorretta, N., Roger, J.M., Rabatel, G., Bellon-Maurel, V., Fiorio, C., Lelong, C.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.08.2009
• Subjects: chemometrics; Data analysis; Hyperspectral imaging; Hyperspectral sensors; Image analysis; Image resolution; Image segmentation; Independent component analysis; Principal component analysis; Support vector machine classification; Support vector machines
• ISBN: 9781424446865; 1424446864
• ISSN: 2158-6268
• DOI: 10.1109/WHISPERS.2009.5289062

Few methods are proposed in the literature for coupling the spectral and the spatial dimension available on hyperspectral images. This paper proposes a generic segmentation scheme named butterfly based on an iterative process and a cross analysis of spectral and spatial information. Indeed, spatial and spatial structures are extracted in spatial and spectral space respectively both taking into account the other one. To apply this layout on hyperspectral images, we focus particularly on spatial and spectral structures i.e. topologic concepts and latent variable for the spatial and the spectral space respectively. Moreover, a cooperation scheme with these structures is proposed. Finally, results obtained on real hyperspectral images using this specific implementation of the butterfly approach are presented and discussed.