Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/27768

Title: Dimension reduction aided hyperspectral image classification with a small-sized training dataset: experimental comparisons
Authors: Su, Jinya
Yi, Dewei
Liu, Cunjia
Guo, Lei
Chen, Wen-Hua
Keywords: Hyperspectral image
Feature extraction/selection
Image classification
Issue Date: 2017
Publisher: MDPI © The Authors
Citation: SU, J. ... et al, 2017. Dimension reduction aided hyperspectral image classification with a small-sized training dataset: experimental comparisons. Sensors, 17 (12), 2726.
Abstract: Hyperspectral images (HSI) provide rich information which may not be captured by other sensing technologies and therefore gradually find a wide range of applications. However, they also generate a large amount of irrelevant or redundant data for a specific task. This causes a number of issues including significantly increased computation time, complexity and scale of prediction models mapping the data to semantics (e.g., classification), and the need of a large amount of labelled data for training. Particularly, it is generally difficult and expensive for experts to acquire sufficient training samples in many applications. This paper addresses these issues by exploring a number of classical dimension reduction algorithms in machine learning communities for HSI classification. To reduce the size of training dataset, feature selection (e.g., mutual information, minimal redundancy maximal relevance) and feature extraction (e.g., Principal Component Analysis (PCA), Kernel PCA) are adopted to augment a baseline classification method, Support Vector Machine (SVM). The proposed algorithms are evaluated using a real HSI dataset. It is shown that PCA yields the most promising performance in reducing the number of features or spectral bands. It is observed that while significantly reducing the computational complexity, the proposed method can achieve better classification results over the classic SVM on a small training dataset, which makes it suitable for real-time applications or when only limited training data are available. Furthermore, it can also achieve performances similar to the classic SVM on large datasets but with much less computing time.
Description: This is an Open Access Article. It is published by MDPI under the Creative Commons Attribution 4.0 International Licence (CC BY). Full details of this licence are available at: http://creativecommons.org/licenses/by/4.0/
Sponsor: This work was supported by Science and Technology Facilities Council (STFC) under Newton fund with grant number ST/N006852/1.
Version: Published
DOI: 10.3390/s17122726
URI: https://dspace.lboro.ac.uk/2134/27768
Publisher Link: https://doi.org/10.3390/s17122726
Appears in Collections:Published Articles (Aeronautical and Automotive Engineering)

Files associated with this item:

File Description SizeFormat
sensors-17-02726-v2.pdfPublished version2.54 MBAdobe PDFView/Open


SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.