Next Article in Journal
Sub-Diffraction Visible Imaging Using Macroscopic Fourier Ptychography and Regularization by Denoising
Next Article in Special Issue
Segmentation and Multi-Scale Convolutional Neural Network-Based Classification of Airborne Laser Scanner Data
Previous Article in Journal
Let’s Talk about TEX—Understanding Consumer Preferences for Smart Interactive Textile Products Using a Conjoint Analysis Approach
Open AccessArticle

Hyperspectral Image Classification with Capsule Network Using Limited Training Samples

1
School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, China
2
State Key Laboratory of Earth Surface Processes and Resource Ecology, Beijing Normal University, Beijing 100875, China
3
State Environmental Protection Key Laboratory of Satellites Remote Sensing, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China
4
State Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, China
*
Author to whom correspondence should be addressed.
Sensors 2018, 18(9), 3153; https://doi.org/10.3390/s18093153
Received: 21 August 2018 / Revised: 10 September 2018 / Accepted: 17 September 2018 / Published: 18 September 2018
(This article belongs to the Special Issue Deep Learning Remote Sensing Data)
Deep learning techniques have boosted the performance of hyperspectral image (HSI) classification. In particular, convolutional neural networks (CNNs) have shown superior performance to that of the conventional machine learning algorithms. Recently, a novel type of neural networks called capsule networks (CapsNets) was presented to improve the most advanced CNNs. In this paper, we present a modified two-layer CapsNet with limited training samples for HSI classification, which is inspired by the comparability and simplicity of the shallower deep learning models. The presented CapsNet is trained using two real HSI datasets, i.e., the PaviaU (PU) and SalinasA datasets, representing complex and simple datasets, respectively, and which are used to investigate the robustness or representation of every model or classifier. In addition, a comparable paradigm of network architecture design has been proposed for the comparison of CNN and CapsNet. Experiments demonstrate that CapsNet shows better accuracy and convergence behavior for the complex data than the state-of-the-art CNN. For CapsNet using the PU dataset, the Kappa coefficient, overall accuracy, and average accuracy are 0.9456, 95.90%, and 96.27%, respectively, compared to the corresponding values yielded by CNN of 0.9345, 95.11%, and 95.63%. Moreover, we observed that CapsNet has much higher confidence for the predicted probabilities. Subsequently, this finding was analyzed and discussed with probability maps and uncertainty analysis. In terms of the existing literature, CapsNet provides promising results and explicit merits in comparison with CNN and two baseline classifiers, i.e., random forests (RFs) and support vector machines (SVMs). View Full-Text
Keywords: capsule network; hyperspectral; image classification; deep learning; possibility density capsule network; hyperspectral; image classification; deep learning; possibility density
Show Figures

Figure 1

MDPI and ACS Style

Deng, F.; Pu, S.; Chen, X.; Shi, Y.; Yuan, T.; Pu, S. Hyperspectral Image Classification with Capsule Network Using Limited Training Samples. Sensors 2018, 18, 3153.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop