Browsing by Author "Courty,N."

Now showing 1 - 3 of 3

Citation Count: 7
A classwise supervised ordering approach for morphology based hyperspectral image classification
(2012) Courty,N.; Aptoula,E.; Lefevre,S.
We present a new method for the spectral-spatial classification of hyperspectral images, by means of morphological features and manifold learning. In particular, mathematical morphology has proved to be an invaluable tool for the description of remote sensing images. However, its application to hyperspectral data is problematic, due to the absence of a complete lattice structure at higher dimensions. We address this issue by following up previous experimental indications on the interest of classwise orderings. The practical interest of the proposed approach is shown through comparison on the Pavia dataset with Extended Morphological Profiles, against which it achieves superior results. © 2012 ICPR Org Committee.
Citation Count: 5
An end-member based ordering relation for the morphological description of hyperspectral images
(Institute of Electrical and Electronics Engineers Inc., 2014) Aptoula,E.; Courty,N.; Lefevre,S.
Despite the popularity of mathematical morphology with remote sensing image analysis, its application to hyperspectral data remains problematic. The issue stems from the need to impose a complete lattice structure on the multi-dimensional pixel value space, that requires a vector ordering. In this article, we introduce such a supervised ordering relation, which conversely to its alternatives, has been designed to be image-specific and exploits the spectral purity of pixels. The practical interest of the resulting multivariate morphological operators is validated through classification experiments where it achieves state-of-the-art performance. © 2014 IEEE.
Citation Count: 8
Mitosis detection in breast cancer histological images with mathematical morphology;
(2013) Aptoula,E.; Courty,N.; Lefèvre,S.
One of the most important outcome predictors of malignant tumors is the mitotic count, i.e. The division speed of cells. This value is computed from the patient's tissue samples by medical experts, that count each mitosis case one by one under a microscope, and as such it is a time consuming process. In order to accelerate it, we present in this paper a system capable of mitosis detection from histological breast cancer images. To this end we have developed a fully automatic solution based on mathematical morphology. The proposed approach has achieved the 10th best performance among 14 teams at the international mitosis detection contest organized by ICPR'12. © 2013 IEEE.