On the use of small training sets for neural network-based characterization of mixed pixels in remotely sensed hyperspectral images

DOI10.1016/j.patcog.2009.04.008zbMath1175.68518OpenAlexW2061280223MaRDI QIDQ2270780

Antonio Plaza, Javier Plaza, Rosa Perez, Pablo A. Martínez

Publication date: 29 July 2009

Published in: Pattern Recognition (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.patcog.2009.04.008

zbMATH Keywords

image processingspectral mixture analysismulti-layer perceptronmixed pixelshyperspectralautomatic training sample generation algorithmsmixed training samplesnonlinear spectral unmixing

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computing methodologies for image processing (68U10)

Related Items

Dynamics of unidirectionally-coupled ring neural network with discrete and distributed delays ⋮ On endmember identification in hyperspectral images without pure pixels: a comparison of algorithms ⋮ Hopf-pitchfork bifurcation in a two-neuron system with discrete and distributed delays

Cites Work

• Unnamed Item
• Unnamed Item
• Independent component analysis, a new concept?
• Real-time constrained linear discriminant analysis to target detection and classification in hyperspectral imagery
• Implementation of real-time constrained linear discriminant analysis to remote sensing image classification