Spectral-Spatial Feature Extraction for Hyperspectral Image Classification: A Dimension Reduction and Deep Learning Approach

• Published in: IEEE transactions on geoscience and remote sensing Vol. 54; no. 8; pp. 4544 - 4554
• Main Authors: Zhao, Wenzhi, Du, Shihong
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.08.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithm design and analysis; Balanced local discriminant embedding (BLDE); Classification; convolutional neural network (CNN); deep learning (DL); dimension reduction (DR); Feature extraction; Hyperspectral imaging; Image classification; Learning; Machine learning; Neural networks; Reduction; Spectra; Training; Balanced local discriminant embedding (BLDE); dimension reduction (DR); convolutional neural network (CNN); feature extraction; deep learning (DL)
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2016.2543748

In this paper, we propose a spectral-spatial feature based classification (SSFC) framework that jointly uses dimension reduction and deep learning techniques for spectral and spatial feature extraction, respectively. In this framework, a balanced local discriminant embedding algorithm is proposed for spectral feature extraction from high-dimensional hyperspectral data sets. In the meantime, convolutional neural network is utilized to automatically find spatial-related features at high levels. Then, the fusion feature is extracted by stacking spectral and spatial features together. Finally, the multiple-feature-based classifier is trained for image classification. Experimental results on well-known hyperspectral data sets show that the proposed SSFC method outperforms other commonly used methods for hyperspectral image classification.