Unsupervised component reduction of hyperspectral images and clustering without performance loss: Application to marine algae identification

B. Chen (1) , K. Chehdi (1) , E. de Oliveira (2) , Claude Cariou (1) , B. Charbonnier (2)

1 IETR - Institut d'Électronique et des Technologies du numéRique
2 EDF R&D STEP - Simulation et Traitement de l'information pour l'Exploitation des systèmes de Production

Keywords: Classification (of information); Identification (control systems); Independent component analysis; Iterative methods; Pixels; Reduction; Remote sensing; Signal processing; Spectroscopy; Feature reduction; Marine algae; Algae; Hyper-spectral imageries; stable; unsupervised; Image processing

Domains: Computer Science [cs]; Networking and Internet Architecture [cs.NI]; Engineering Sciences [physics]; Electronics

B. Chen, K. Chehdi, E. de Oliveira, Claude Cariou, B. Charbonnier. Unsupervised component reduction of hyperspectral images and clustering without performance loss: Application to marine algae identification. Image and Signal Processing for Remote Sensing XXII, Sep 2016, Edinburgh, United Kingdom. pp.100040Q, ⟨10.1117/12.2241190⟩. ⟨hal-01484540⟩