Abstract
In this letter, a self-improving convolutional neural network (CNN) based method is proposed for the classification of hyperspectral data. This approach solves the so-called curse of dimensionality and the lack of available training samples by iteratively selecting the most informative bands suitable for the designed network via fractional order Darwinian particle swarm optimization. The selected bands are then fed to the classification system to produce the final classification map. Experimental results have been conducted with two well-known hyperspectral data sets: Indian Pines and Pavia University. Results indicate that the proposed approach significantly improves a CNN-based classification method in terms of classification accuracy. In addition, this letter uses the concept of dither for the first time in the remote sensing community to tackle overfitting.
Original language | English |
---|---|
Article number | 7544576 |
Pages (from-to) | 1537-1541 |
Number of pages | 5 |
Journal | IEEE Geoscience and Remote Sensing Letters |
Volume | 13 |
Issue number | 10 |
DOIs | |
State | Published - Oct 2016 |
Keywords
- Convolutional neural network (CNN)
- deep learning
- feature selection
- fractional order Darwinian particle swarm optimization (FODPSO)
- hyperspectral image classification