Quantization of hyperspectral image manifold using probabilistic distances - Gianni Franchi, Jesús Angulo
-
last edited by Geo-Sci-InfoAuthor: Gianni Franchi, Jesús Angulo
DOI URL: http://dx.doi.org/10.1007/978-3-319-25040-3_44
Video: http://www.youtube.com/watch?v=Xwav5x4AWEY
Slides: Franchi_Quantization hyperspectral image.pdf
Presentation: https://www.see.asso.fr/node/14306
Creative Commons Attribution-ShareAlike 4.0 InternationalAbstract:
A technique of spatial-spectral quantization of hyperspectral images is introduced. Thus a quantized hyperspectral image is just summarized by K spectra which represent the spatial and spectral structures of the image. The proposed technique is based on α-connected components on a region adjacency graph. The main ingredient is a dissimilarity metric. In order to choose the metric that best fit the hyperspectral data manifold, a comparison of different probabilistic dissimilarity measures is achieved.
