Authors:
Muhammad Ahmad
1
;
Adil Mehmood Khan
2
;
Manuel Mazzara
2
and
Salvatore Distefano
3
Affiliations:
1
Innopolis University, Innopolis, Russia, University of Messina, Messina and Italy
;
2
Innopolis University, Innopolis and Russia
;
3
University of Messina, Messina and Italy
Keyword(s):
Extreme Learning Machine (ELM), Deep Neural Networks (DNN), Auto Encoder (AE), Hyperspectral Image Classification.
Related
Ontology
Subjects/Areas/Topics:
Active and Robot Vision
;
Applications and Services
;
Computer Vision, Visualization and Computer Graphics
;
Features Extraction
;
Image and Video Analysis
;
Image Formation and Preprocessing
;
Imaging for Cultural Heritage (Modeling/Simulation, Virtual Restoration)
;
Motion, Tracking and Stereo Vision
;
Multimodal and Multi-Sensor Models of Image Formation
Abstract:
Hyperspectral imaging (HSI) has attracted the formidable interest of the scientific community and has been applied to an increasing number of real-life applications to automatically extract the meaningful information from the corresponding high dimensional datasets. However, traditional autoencoders (AE) and restricted Boltzmann machines are computationally expensive and do not perform well due to the Hughes phenomenon which is observed in HSI since the ratio of the labeled training pixels on the number of bands is usually quite small. To overcome such problems, this paper exploits a multi-layer extreme learning machine-based autoencoder (MLELM-AE) for HSI classification. MLELM-AE learns feature representations by adopting a singular value decomposition and is used as basic building block for learning machine-based autoencoder (MLELM-AE). MLELM-AE method not only maintains the fast speed of traditional ELM but also greatly improves the performance of HSI classification. The experimen
tal results demonstrate the effectiveness of MLELM-AE on several well-known HSI dataset.
(More)