Author/Editor		Noyel, Guillaume; Angulo, Jesus; Jeulin, Dominique
Title		Morphological segmentation of hyperspectral images
Type		članek
Source		Image Anal Stereol
Vol. and No.		Letnik 26, št. 3
Publication year		2007
Volume		str. 101-9
Language		eng
Abstract		The present paper develops a general methodology for the morphological segmentation of hyperspectral images, i.e., with an important number of channels. This approach, based on watershed, is composed of a spectral classification to obtain the markers and a vectorial gradient which gives the spatial information. Several alternative gradients are adapted to the different hyperspectral functions. Data reduction is performed either by Factor Analysis or by model fitting. Image segmentation is done on different spaces: factor space, parameters space, etc. On all these spaces the spatial/spectral segmentation approach is applied, leading to relevant results on the image.
Descriptors		COLOR MULTIVARIATE ANALYSIS FACTOR ANALYSIS, STATISTICAL IMAGE PROCESSING, COMPUTER-ASSISTED