Dimension Reduction and Classification of Hyperspectral Images based on Neural Network Sensitivity Analysis and Multi-instance Learning

Hui Liu1, 2, Chenming Li1 and Lizhong Xu1

  1. College of Computer and Information Engineering, Hohai University, Nanjing
    211100, China
    9120030059@jxust.edu.cn
  2. School of Science, Jiangxi University of Science and Technology, Ganzhou
    341000, China
    lcm@hhu.edu.cn
  3. College of Computer and Information Engineering, Hohai University, Nanjing
    211100, China, lzhxu@hhu.edu.cn

Abstract

Hyperspectral remote image sensing is a rapidly developing integrated technology used widely in numerous areas. The rich spectral information from hyperspectral images aids in recognition and classification of many types of objects, but the high dimensionality of these images leads to information redundancy. In this paper, we used sensitivity analysis for dimension reduction. However, another challenge is that hyperspectral images identify objects as either a "different body with the same spectrum" or "same body with a different spectrum." Therefore, it is difficult to maintain the correct correspondence between ground objects and samples, which hinders classification of the images. This issue can be addressed using multi-instance learning for classification. In our proposed method, we combined neural network sensitivity analysis with a multi-instance learning algorithm based on a support vector machine to achieve dimension reduction and accurate classification for hyperspectral images. Experimental results demonstrated that our method provided strong overall classification effectiveness when compared with prior methods.

Key words

Sensitivity Analysis, Artificial Neural Network, Ruck Sensitivity Analysis, Dimension Reduction, Classification, Hyperspectral Images, Multi-instance Learning, SVM

Digital Object Identifier (DOI)

https://doi.org/10.2298/CSIS180428003L

Publication information

Volume 16, Issue 2 (June 2019)
Year of Publication: 2019
ISSN: 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Liu, H., Li, C., Xu, L.: Dimension Reduction and Classification of Hyperspectral Images based on Neural Network Sensitivity Analysis and Multi-instance Learning. Computer Science and Information Systems, Vol. 16, No. 2, 443-468. (2019), https://doi.org/10.2298/CSIS180428003L