Spatially variant dimensionality reduction for the visualization of multi/hyperspectral images

Steven Le Moan (1, 2) , Alamin Mansouri (1) , Yvon Voisin (1) , Jon Hardeberg (3)

1 Le2i - Laboratoire Electronique, Informatique et Image [UMR6306]
2 ColorLab - The Norvegian Research Color Laboratory
3 ColorLab - The Norwegian Color Research Laboratory

In this paper, we introduce a new approach for color visu- alization of multi/hyperspectral images. Unlike traditional methods, we propose to operate a local analysis instead of considering that all the pixels are part of the same population. It takes a segmentation map as an input and then achieves a dimensionality reduction adaptively inside each class of pixels. Moreover, in order to avoid unappealing discon- tinuities between regions, we propose to make use of a set of distance transform maps to weigh the mapping applied to each pixel with regard to its relative location with classes' centroids. Results on two hyperspec- tral datasets illustrate the efficiency of the proposed method.

Mots clés: spectral images; visualization; dimensionality reduction; spatially variant

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Steven Le Moan, Alamin Mansouri, Yvon Voisin, Jon Hardeberg. Spatially variant dimensionality reduction for the visualization of multi/hyperspectral images. International Conference on Image Analysis and Recognition, Jun 2011, Burnaby, Canada. pp.375-384, ⟨10.1007/978-3-642-21593-3_38⟩. ⟨hal-00637936⟩