Modified Independent Component Analysis for Initializing Non-negative Matrix Factorization : An approach to Hyperspectral Image Unmixing (WHISPERS 2013)

Djaouad Benachir (1, 2) , Shahram Hosseini (2) , Yannick Deville (2) , Moussa Karoui (2) , Abdelkader Hameurlain (1)

1 IRIT-PYRAMIDE - Optimisation Dynamique de Requêtes Réparties à grande échelle
2 IRAP - Institut de recherche en astrophysique et planétologie

In this paper, we propose an unsupervised unmixing approach for hyperspectral images, consisting of a modified version of ICA, followed by NMF. In the ideal case of a hyperspectral image combining (C−1) statistically independent source images , and a C th image which is dependent on them due to the sum-to-one constraint, our modified ICA first estimates these (C −1) sources and associated mixing coefficients, and then derives the remaining source and coefficients, while also removing the BSS scale indeterminacy. In real conditions, the above (C−1) sources may be somewhat dependent. Our modified ICA method then only yields approximate data. These are then used as the initial values of an NMF method, which refines them. Our tests show that this joint modifICA-NMF approach significantly outperforms the considered classical methods.

Mots clés: ICA; NMF; Hyperspectral unmixing

Domaines: Théorie de l'information [cs.IT]; Recherche d'information [cs.IR]

Djaouad Benachir, Shahram Hosseini, Yannick Deville, Moussa Karoui, Abdelkader Hameurlain. Modified Independent Component Analysis for Initializing Non-negative Matrix Factorization : An approach to Hyperspectral Image Unmixing (WHISPERS 2013). 5th IEEE Workshop on Hyperstectral Image and Signal Processing : Evolution in Remote Sensing (WHISPERS 2013), Jun 2013, Gainesville, United States. pp.1-6, ⟨10.1109/WHISPERS.2013.8080719⟩. ⟨hal-01166256⟩