Classification algorithm of hyperspectral images based on kernel entropy analysis

Ying Wang; Lei Guo; Nan Liang

Classification algorithm of hyperspectral images based on kernel entropy analysis

Ying Wang
, Lei Guo
, Nan Liang

School of Automation

Northwestern Polytechnical University Xian

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

2 Scopus citations

Abstract

To take advantage of the characteristics of KECA for hyperspectral remote sensing image classification, an approach of sample set selection and C-means classification is proposed. The sample selection is based on convex geometry concepts and C-means classification uses spectral angles as distance metrics in feature space. Experiment results of HYDICE hyperspectral data confirm that the proposed approach can improve classification accuracy effectively.

Original language	English
Pages (from-to)	1597-1601
Number of pages	5
Journal	Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition)
Volume	42
Issue number	6
State	Published - Nov 2012

Keywords

Hyperspectral image
Image classification
Information processing
Kernel entropy component analysis
Renyi entropy

Cite this

@article{15b16ccdaf1a405ba93e06c5bc45555a,

title = "Classification algorithm of hyperspectral images based on kernel entropy analysis",

abstract = "To take advantage of the characteristics of KECA for hyperspectral remote sensing image classification, an approach of sample set selection and C-means classification is proposed. The sample selection is based on convex geometry concepts and C-means classification uses spectral angles as distance metrics in feature space. Experiment results of HYDICE hyperspectral data confirm that the proposed approach can improve classification accuracy effectively.",

keywords = "Hyperspectral image, Image classification, Information processing, Kernel entropy component analysis, Renyi entropy",

author = "Ying Wang and Lei Guo and Nan Liang",

year = "2012",

month = nov,

language = "英语",

volume = "42",

pages = "1597--1601",

journal = "Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition)",

issn = "1671-5497",

publisher = "Editorial Board of Jilin University",

number = "6",

}

TY - JOUR

T1 - Classification algorithm of hyperspectral images based on kernel entropy analysis

AU - Wang, Ying

AU - Guo, Lei

AU - Liang, Nan

PY - 2012/11

Y1 - 2012/11

N2 - To take advantage of the characteristics of KECA for hyperspectral remote sensing image classification, an approach of sample set selection and C-means classification is proposed. The sample selection is based on convex geometry concepts and C-means classification uses spectral angles as distance metrics in feature space. Experiment results of HYDICE hyperspectral data confirm that the proposed approach can improve classification accuracy effectively.

AB - To take advantage of the characteristics of KECA for hyperspectral remote sensing image classification, an approach of sample set selection and C-means classification is proposed. The sample selection is based on convex geometry concepts and C-means classification uses spectral angles as distance metrics in feature space. Experiment results of HYDICE hyperspectral data confirm that the proposed approach can improve classification accuracy effectively.

KW - Hyperspectral image

KW - Image classification

KW - Information processing

KW - Kernel entropy component analysis

KW - Renyi entropy

UR - https://www.scopus.com/pages/publications/84870746786

M3 - 文章

AN - SCOPUS:84870746786

SN - 1671-5497

VL - 42

SP - 1597

EP - 1601

JO - Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition)

JF - Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition)

IS - 6

ER -

Classification algorithm of hyperspectral images based on kernel entropy analysis

Abstract

Keywords

Other files and links

Fingerprint

Cite this