Deep feature representation for hyperspectral image classification
Authors:
- 1 July 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21536996,p. 4951-4954
Abstract
Hyperspectral data classification problems have been extensively studied in the past decade. However, well designed features and a robust classifier are still open issues that impact on the performance of an automatic land-cover classification system. In this paper, we propose a deep feature representation method that generates very good features and a classifier for pixel-wise hyperspectral data classification. The proposed method has two main steps: principle components of the hyperspectral image cube is first filtered by three dimensional Gabor wavelets; second, stacked autoencoders are trained on the outputs of the previous step through unsupervised pre-training, finally deep neural network is trained on those stacked autoencoders. Experimental results obtained on real hyperspectral image confirmed the effectiveness of the proposed approach in favors of the high classification accuracy and computation efficiency.Keywords
This publication has 8 references indexed in Scilit:
- A Two-Stage Feature Selection Framework for Hyperspectral Image Classification Using Few Labeled SamplesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2013
- Deep Learning of Representations: Looking Forward2013
- Hyperspectral Image Classification Based on Structured Sparse Logistic Regression and Three-Dimensional Wavelet Texture FeaturesIEEE Transactions on Geoscience and Remote Sensing, 2012
- Three-Dimensional Gabor Wavelets for Pixel-Based Hyperspectral Imagery ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2011
- Kernel-based methods for hyperspectral image classificationIEEE Transactions on Geoscience and Remote Sensing, 2005
- Dimensionality reduction and classification of hyperspectral image data using sequences of extended morphological transformationsIEEE Transactions on Geoscience and Remote Sensing, 2005
- Classification of hyperspectral remote sensing images with support vector machinesIEEE Transactions on Geoscience and Remote Sensing, 2004
- Gabor feature based classification using the enhanced fisher linear discriminant model for face recognitionIEEE Transactions on Image Processing, 2002