Open AccessMultilayered autoencoders in problems of hyperspectral image analysis and processing
Author(s) -
Margarita Kuzmina
Publication year - 2021
Publication title -
preprint/preprinty ipm im. m.v. keldyša
Language(s) - English
Resource type - Journals
eISSN - 2071-2901
pISSN - 2071-2898
DOI - 10.20948/prepr-2021-28
Subject(s) - autoencoder , hyperspectral imaging , artificial intelligence , image (mathematics) , pattern recognition (psychology) , computer science , set (abstract data type) , image processing , data set , full spectral imaging , computer vision , remote sensing , artificial neural network , geography , programming language
A model of five-layered autoencoder (stacked autoencoder, SAE) is suggested for deep image features extraction and deriving compressed hyperspectral data set specifying the image. Spectral cost function, dependent on spectral curve forms of hyperspectral image, has been used for the autoencoder tuning. At the first step the autoencoder capabilities will be tested based on using pure spectral information contained in image data. The images from well known and widely used hyperspectral databases (Indian Pines, Pavia University и KSC) are planned to be used for the model testing.