Hyperspectral image segmentation, deblurring, and spectral analysis for material identification

Fang Li; Michael K. Ng; Robert Plemmons; Sudhakar Prasad; Qiang Zhang

doi:10.1117/12.850121

Hyperspectral image segmentation, deblurring, and spectral analysis for material identification

Fang Li, Michael K. Ng, Robert Plemmons^*, Sudhakar Prasad, Qiang Zhang

^*Corresponding author for this work

Department of Mathematics

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

16 Citations (Scopus)

Abstract

An important aspect of spectral image analysis is identification of materials present in the object or scene being imaged. Enabling technologies include image enhancement, segmentation and spectral trace recovery. Since multi-spectral or hyperspectral imagery is generally low resolution, it is possible for pixels in the image to contain several materials. Also, noise and blur can present significant data analysis problems. In this paper, we first describe a variational fuzzy segmentation model coupled with a denoising/deblurring model for material identification. A statistical moving average method for segmentation is also described. These new approaches are then tested and compared on hyperspectral images associated with space object material identification.

Original language	English
Title of host publication	Visual Information Processing XIX
DOIs	https://doi.org/10.1117/12.850121
Publication status	Published - 2010
Event	Visual Information Processing XIX - Orlando, FL, United States Duration: 6 Apr 2010 → 7 Apr 2010

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	7701
ISSN (Print)	0277-786X

Conference

Conference	Visual Information Processing XIX
Country/Territory	United States
City	Orlando, FL
Period	6/04/10 → 7/04/10

Scopus Subject Areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

User-Defined Keywords

Classification
Deblurring
Denoising
Dimensionality reduction
Hyperspectral data
Segmentation
Spectral mixture analysis

Access to Document

10.1117/12.850121

Cite this

@inproceedings{c6da2c80d92f4286ba4ebd40c44e89bc,

title = "Hyperspectral image segmentation, deblurring, and spectral analysis for material identification",

abstract = "An important aspect of spectral image analysis is identification of materials present in the object or scene being imaged. Enabling technologies include image enhancement, segmentation and spectral trace recovery. Since multi-spectral or hyperspectral imagery is generally low resolution, it is possible for pixels in the image to contain several materials. Also, noise and blur can present significant data analysis problems. In this paper, we first describe a variational fuzzy segmentation model coupled with a denoising/deblurring model for material identification. A statistical moving average method for segmentation is also described. These new approaches are then tested and compared on hyperspectral images associated with space object material identification.",

keywords = "Classification, Deblurring, Denoising, Dimensionality reduction, Hyperspectral data, Segmentation, Spectral mixture analysis",

author = "Fang Li and Ng, {Michael K.} and Robert Plemmons and Sudhakar Prasad and Qiang Zhang",

year = "2010",

doi = "10.1117/12.850121",

language = "English",

isbn = "9780819481658",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

booktitle = "Visual Information Processing XIX",

}

Li, F, Ng, MK, Plemmons, R, Prasad, S & Zhang, Q 2010, Hyperspectral image segmentation, deblurring, and spectral analysis for material identification. in Visual Information Processing XIX., 770103, Proceedings of SPIE - The International Society for Optical Engineering, vol. 7701, Visual Information Processing XIX, Orlando, FL, United States, 6/04/10. https://doi.org/10.1117/12.850121

Hyperspectral image segmentation, deblurring, and spectral analysis for material identification. / Li, Fang; Ng, Michael K.; Plemmons, Robert et al.
Visual Information Processing XIX. 2010. 770103 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 7701).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Hyperspectral image segmentation, deblurring, and spectral analysis for material identification

AU - Li, Fang

AU - Ng, Michael K.

AU - Plemmons, Robert

AU - Prasad, Sudhakar

AU - Zhang, Qiang

PY - 2010

Y1 - 2010

N2 - An important aspect of spectral image analysis is identification of materials present in the object or scene being imaged. Enabling technologies include image enhancement, segmentation and spectral trace recovery. Since multi-spectral or hyperspectral imagery is generally low resolution, it is possible for pixels in the image to contain several materials. Also, noise and blur can present significant data analysis problems. In this paper, we first describe a variational fuzzy segmentation model coupled with a denoising/deblurring model for material identification. A statistical moving average method for segmentation is also described. These new approaches are then tested and compared on hyperspectral images associated with space object material identification.

AB - An important aspect of spectral image analysis is identification of materials present in the object or scene being imaged. Enabling technologies include image enhancement, segmentation and spectral trace recovery. Since multi-spectral or hyperspectral imagery is generally low resolution, it is possible for pixels in the image to contain several materials. Also, noise and blur can present significant data analysis problems. In this paper, we first describe a variational fuzzy segmentation model coupled with a denoising/deblurring model for material identification. A statistical moving average method for segmentation is also described. These new approaches are then tested and compared on hyperspectral images associated with space object material identification.

KW - Classification

KW - Deblurring

KW - Denoising

KW - Dimensionality reduction

KW - Hyperspectral data

KW - Segmentation

KW - Spectral mixture analysis

UR - http://www.scopus.com/inward/record.url?scp=78049389202&partnerID=8YFLogxK

U2 - 10.1117/12.850121

DO - 10.1117/12.850121

M3 - Conference proceeding

AN - SCOPUS:78049389202

SN - 9780819481658

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Visual Information Processing XIX

T2 - Visual Information Processing XIX

Y2 - 6 April 2010 through 7 April 2010

ER -

Hyperspectral image segmentation, deblurring, and spectral analysis for material identification

Abstract

Publication series

Conference

Scopus Subject Areas

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this