Hyperspectral Image Spectral-Spatial Feature Extraction via Tensor Principal Component Analysis

Yuemei Ren; Liang Liao; Stephen John Maybank; Yanning Zhang; Xin Liu

doi:10.1109/LGRS.2017.2686878

Hyperspectral Image Spectral-Spatial Feature Extraction via Tensor Principal Component Analysis

Yuemei Ren, Liang Liao, Stephen John Maybank, Yanning Zhang, Xin Liu

School of Computer Science

Research output: Contribution to journal › Article › peer-review

58 Scopus citations

Abstract

We consider the tensor-based spectral-spatial feature extraction problem for hyperspectral image classification. First, a tensor framework based on circular convolution is proposed. Based on this framework, we extend the traditional principal component analysis (PCA) to its tensorial version tensor PCA (TPCA), which is applied to the spectral-spatial features of hyperspectral image data. The experiments show that the classification accuracy obtained using TPCA features is significantly higher than the accuracies obtained by its rivals.

Original language	English
Article number	7993025
Pages (from-to)	1431-1435
Number of pages	5
Journal	IEEE Geoscience and Remote Sensing Letters
Volume	14
Issue number	9
DOIs	https://doi.org/10.1109/LGRS.2017.2686878
State	Published - Sep 2017

Keywords

Feature extraction
hyperspectral image classification
principal component analysis (PCA)
tensor model

Access to Document

10.1109/LGRS.2017.2686878

Cite this

@article{b8e8a638b4f44c37b3482915084697df,

title = "Hyperspectral Image Spectral-Spatial Feature Extraction via Tensor Principal Component Analysis",

abstract = "We consider the tensor-based spectral-spatial feature extraction problem for hyperspectral image classification. First, a tensor framework based on circular convolution is proposed. Based on this framework, we extend the traditional principal component analysis (PCA) to its tensorial version tensor PCA (TPCA), which is applied to the spectral-spatial features of hyperspectral image data. The experiments show that the classification accuracy obtained using TPCA features is significantly higher than the accuracies obtained by its rivals.",

keywords = "Feature extraction, hyperspectral image classification, principal component analysis (PCA), tensor model",

author = "Yuemei Ren and Liang Liao and Maybank, {Stephen John} and Yanning Zhang and Xin Liu",

note = "Publisher Copyright: {\textcopyright} 2004-2012 IEEE.",

year = "2017",

month = sep,

doi = "10.1109/LGRS.2017.2686878",

language = "英语",

volume = "14",

pages = "1431--1435",

journal = "IEEE Geoscience and Remote Sensing Letters",

issn = "1545-598X",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "9",

}

TY - JOUR

T1 - Hyperspectral Image Spectral-Spatial Feature Extraction via Tensor Principal Component Analysis

AU - Ren, Yuemei

AU - Liao, Liang

AU - Maybank, Stephen John

AU - Zhang, Yanning

AU - Liu, Xin

PY - 2017/9

Y1 - 2017/9

N2 - We consider the tensor-based spectral-spatial feature extraction problem for hyperspectral image classification. First, a tensor framework based on circular convolution is proposed. Based on this framework, we extend the traditional principal component analysis (PCA) to its tensorial version tensor PCA (TPCA), which is applied to the spectral-spatial features of hyperspectral image data. The experiments show that the classification accuracy obtained using TPCA features is significantly higher than the accuracies obtained by its rivals.

AB - We consider the tensor-based spectral-spatial feature extraction problem for hyperspectral image classification. First, a tensor framework based on circular convolution is proposed. Based on this framework, we extend the traditional principal component analysis (PCA) to its tensorial version tensor PCA (TPCA), which is applied to the spectral-spatial features of hyperspectral image data. The experiments show that the classification accuracy obtained using TPCA features is significantly higher than the accuracies obtained by its rivals.

KW - Feature extraction

KW - hyperspectral image classification

KW - principal component analysis (PCA)

KW - tensor model

UR - http://www.scopus.com/inward/record.url?scp=85028944074&partnerID=8YFLogxK

U2 - 10.1109/LGRS.2017.2686878

DO - 10.1109/LGRS.2017.2686878

M3 - 文章

AN - SCOPUS:85028944074

SN - 1545-598X

VL - 14

SP - 1431

EP - 1435

JO - IEEE Geoscience and Remote Sensing Letters

JF - IEEE Geoscience and Remote Sensing Letters

IS - 9

M1 - 7993025

ER -

Hyperspectral Image Spectral-Spatial Feature Extraction via Tensor Principal Component Analysis

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this