<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Hyperspectral data has rich spectrum information, strong correlation between bands and high data redundancy. Feature band extraction of hyperspectral data is a prerequisite and an important basis for the subsequent study of classification and target recognition. Deep belief network is a kind of deep learning model, the paper proposed a deep belief network to realize the characteristics band extraction of hyperspectral data, and use the advantages of unsupervised and supervised learning of deep belief network, and to extract feature bands of spectral data from low level to high-level gradually. The extracted feature band has a stronger discriminant performance, so that it can better to classify hyperspectral data. Finally, the AVIRIS data is used to extract the feature band, and the SVM classifier is used to classify the data, which verifies the effectiveness of the method.</p>
</abstract>

Hyperspectral data has rich spectrum information, strong correlation between bands and high data redundancy. Feature band extraction of hyperspectral data is a prerequisite and an important basis for the subsequent study of classification and target recognition. Deep belief network is a kind of deep learning model, the paper proposed a deep belief network to realize the characteristics band extraction of hyperspectral data, and use the advantages of unsupervised and supervised learning of deep belief network, and to extract feature bands of spectral data from low level to high-level gradually. The extracted feature band has a stronger discriminant performance, so that it can better to classify hyperspectral data. Finally, the AVIRIS data is used to extract the feature band, and the SVM classifier is used to classify the data, which verifies the effectiveness of the method.

Hyperspectral Data Feature Extraction Using Deep Belief Network

International Journal on Smart Sensing and Intelligent Systems

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

{"article-title":"Hyperspectral Data Feature Extraction Using Deep Belief Network"}

Hyperspectral data has rich spectrum information, strong correlation between bands and high data redundancy. Feature band extraction of hyperspectral data is a...

Hyperspectral Data Feature Extraction Using Deep Belief Network

Publicado en línea: 01 dic 2016

Páginas: 1991 - 2009

Recibido: 15 jul 2016

Aceptado: 26 oct 2016

DOI: https://doi.org/10.21307/ijssis-2017-949

Palabras clave
Hyperspectral, Feature extraction, Deep learning, Deep belief network, Restricted boltzman machines

© 2016 Jiang Xinhua et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Hyperspectral Data Feature Extraction Using Deep Belief Network

Publicado en línea: 01 dic 2016

Páginas: 1991 - 2009

Recibido: 15 jul 2016

Aceptado: 26 oct 2016

DOI: https://doi.org/10.21307/ijssis-2017-949

Palabras claveHyperspectral, Feature extraction, Deep learning, Deep belief network, Restricted boltzman machines

© 2016 Jiang Xinhua et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Palabras clave
Hyperspectral, Feature extraction, Deep learning, Deep belief network, Restricted boltzman machines