0000000000541809
AUTHOR
Steven Le Moan
showing 8 related works from this author
Spatially variant dimensionality reduction for the visualization of multi/hyperspectral images
2011
International audience; 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…
Réduction de dimensionalité et saillance pour la visualisation d'images spectrales
2012
Nowadays, digital imaging is mostly based on the paradigm that a combinations of a small number of so-called primary colors is sufficient to represent any visible color. For instance, most cameras usepixels with three dimensions: Red, Green and Blue (RGB). Such low dimensional technology suffers from several limitations such as a sensitivity to metamerism and a bounded range of wavelengths. Spectral imaging technologies offer the possibility to overcome these downsides by dealing more finely withe the electromagnetic spectrum. Mutli-, hyper- or ultra-spectral images contain a large number of channels, depicting specific ranges of wavelength, thus allowing to better recover either the radian…
Sélection de bandes pour la visualisation d'images spectrales : une approche basée sur l'étude de saillance
2011
National audience; De nos jours, la plupart des technologies d'affichage numériques sont basées sur le paradigme qu'une combinaison de trois couleurs primaires spécifiques est suffisante pour la reproduction d'une couleur quelconque pour l'oeil humain. Par ailleurs, les dispositifs d'affichage multispectraux ne sont pas encore monnaie courante sur le marché du multimédia. Ainsi, lorsqu'il s'agit de visualiser une image spectrale en couleur, sur un écran traditionnel, seuls trois bandes peuvent être utilisées simultanément, ce qui implique une réduction de dimensionnalité. Cette étape doit permettre la préservation d'un maximum de contenu informatif tout en préservant contrastes et couleurs …
Saliency-Based Band Selection For Spectral Image Visu- alization
2011
International audience; In this paper, we introduce a new band selection ap- proach for the color visualization of spectral images. Un- like traditional methods, we propose to make a selection out of a comparison of the saliency maps of the individual spectral channels. This allows to assess how different they are in terms of prominent features. A comparison metric based on Shannon's information theory at the second and third order is presented and results are subjectively and ob- jectively compared to other dimensionality reduction tech- niques on three datasets, demonstrating the efficiency of the proposed approach.
Salient Pixels and Dimensionality Reduction for Display of Multi/Hyperspectral Images
2012
International audience; Dimensionality Reduction (DR) of spectral images is a common approach to different purposes such as visualization, noise removal or compression. Most methods such as PCA or band selection use either the entire population of pixels or a uniformly sampled subset in order to compute a projection matrix. By doing so, spatial information is not accurately handled and all the objects contained in the scene are given the same emphasis. Nonetheless, it is possible to focus the DR on the separation of specific Objects of Interest (OoI), simply by neglecting all the others. In PCA for instance, instead of using the variance of the scene in each spectral channel, we show that i…
An Efficient Method for the Visualization of Spectral Images Based on a Perception-Oriented Spectrum Segmentation
2010
We propose a new method for the visualization of spectral images. It involves a perception-based spectrum segmentation using an adaptable thresholding of the stretched CIE standard observer colormatching functions. This allows for an underlying removal of irrelevant channels, and, consequently, an alleviation of the computational burden of further processings. Principal Components Analysis is then used in each of the three segments to extract the Red, Green and Blue primaries for final visualization. A comparison framework using two different datasets shows the efficiency of the proposed method.
Saliency in spectral images
2011
International audience; Even though the study of saliency for color images has been thoroughly investigated in the past, very little attention has been given to datasets that cannot be displayed on traditional computer screens such as spectral images. Nevertheless, more than a means to predict human gaze, the study of saliency primarily allows for measuring infor- mative content. Thus, we propose a novel approach for the computation of saliency maps for spectral images. Based on the Itti model, it in- volves the extraction of both spatial and spectral features, suitable for high dimensionality images. As an application, we present a comparison framework to evaluate how dimensionality reduct…
A class-separability-based method for multi/hyperspectral image color visualization
2010
In this paper, a new color visualization technique for multi- and hyperspectral images is proposed. This method is based on a maximization of the perceptual distance between the scene endmembers as well as natural constancy of the resulting images. The stretched CMF principle is used to transform reflectance into values in the CIE L*a*b* colorspace combined with an a priori known segmentation map for separability enhancement between classes. Boundaries are set in the a*b* subspace to balance the natural palette of colors in order to ease interpretation by a human expert. Convincing results on two different images are shown.