Hyperspectral Image Classification Using Fast and Adaptive Bidimensional Empirical Mode Decomposition With Minimum Noise Fraction

The scattered pixel problem in hyperspectral images caused by atmospheric noises and incomplete classification can lead to unsatisfactory classification; this problem remains to be solved. This letter reports the application of minimum noise fractions (MNFs) combined with fast and adaptive bidimensi...

Full description

Saved in:
Bibliographic Details
Published in:IEEE geoscience and remote sensing letters 2016-12, Vol.13 (12), p.1950-1954
Main Authors: Yang, Ming-Der, Huang, Kai-Shiang, Yang, Yeh Fen, Lu, Liang-You, Feng, Zheng-Yi, Tsai, Hui Ping
Format: Article
Language:English
Subjects:
Accuracy
Atmospheric chemistry
Classification
Decomposition
Degradation
Empirical mode decomposition
Empirical mode decomposition (EMD)
fast and adaptive bidimensional EMD (FABEMD)
Fractions
hyperspectral image classification
Hyperspectral imaging
Image classification
Image filters
Image quality
Image reconstruction
Imaging spectrometers
Infrared imagery
Infrared imaging
Infrared spectrometers
Low pass filters
minimum noise fraction (MNF)
Pinus
Signal to noise ratio
Spectra
Spectroscopic techniques
support vector machine (SVM)
Support vector machines
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The scattered pixel problem in hyperspectral images caused by atmospheric noises and incomplete classification can lead to unsatisfactory classification; this problem remains to be solved. This letter reports the application of minimum noise fractions (MNFs) combined with fast and adaptive bidimensional empirical mode decomposition (FABEMD) as a two-step process to improve the classification accuracy of airborne visible-infrared imaging spectrometer hyperspectral image of the Indian Pine data set. With dimensional reduction by using MNF, FABEMD, considered as a low-pass filter, decomposes a hyperspectral image into several bidimensional intrinsic mode functions (BIMFs) and a residue image. The first four BIMFs are removed and the remainder BIMFs are integrated to reconstruct informative images that are subsequently classified through a support vector machine classifier (SVM). The classification results show that the proposed approach can effectively eliminate noise effects and can obtain higher accuracy than does traditional MNF SVM.
ISSN:1545-598X
1558-0571
DOI:10.1109/LGRS.2016.2618930