Nonlinear discriminant analysis

Hongbin Zhang; Eric Clarkson; Harrison H. Barrett

doi:10.1117/12.431117

Nonlinear discriminant analysis

Hongbin Zhang, Eric Clarkson, Harrison H. Barrett

Medical Imaging

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

Abstract

We describe a new nonlinear discriminant analysis method for feature extraction. This method applies a nonsingular transform to the data such that the transformed data have a Gaussian distribution. Then a Bayes likelihood ratio is calculated for the transformed data. The nonsingular transform makes use of wavelet transforms and histogram matching. Wavelet transforms are an effective tool in analyzing data structures. Histogram matching is applied to the wavelet coefficients and the ordinary image pixel values in order to create a transformed image that has the desired Gaussian statistics.

Original language	English (US)
Pages (from-to)	448-455
Number of pages	8
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	4322
Issue number	1
DOIs	https://doi.org/10.1117/12.431117
State	Published - Jul 3 2001

Keywords

Histogram matching
Hypothesis testing
Nonlinear discriminant analysis
Nonsingular transform
Wavelets

ASJC Scopus subject areas

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

Access to Document

10.1117/12.431117

Cite this

@article{11af0a28ffd54a43bc29c366aff7419c,

title = "Nonlinear discriminant analysis",

abstract = "We describe a new nonlinear discriminant analysis method for feature extraction. This method applies a nonsingular transform to the data such that the transformed data have a Gaussian distribution. Then a Bayes likelihood ratio is calculated for the transformed data. The nonsingular transform makes use of wavelet transforms and histogram matching. Wavelet transforms are an effective tool in analyzing data structures. Histogram matching is applied to the wavelet coefficients and the ordinary image pixel values in order to create a transformed image that has the desired Gaussian statistics.",

keywords = "Histogram matching, Hypothesis testing, Nonlinear discriminant analysis, Nonsingular transform, Wavelets",

author = "Hongbin Zhang and Eric Clarkson and Barrett, {Harrison H.}",

year = "2001",

month = jul,

day = "3",

doi = "10.1117/12.431117",

language = "English (US)",

volume = "4322",

pages = "448--455",

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

issn = "0277-786X",

publisher = "SPIE",

number = "1",

}

TY - JOUR

T1 - Nonlinear discriminant analysis

AU - Zhang, Hongbin

AU - Clarkson, Eric

AU - Barrett, Harrison H.

PY - 2001/7/3

Y1 - 2001/7/3

N2 - We describe a new nonlinear discriminant analysis method for feature extraction. This method applies a nonsingular transform to the data such that the transformed data have a Gaussian distribution. Then a Bayes likelihood ratio is calculated for the transformed data. The nonsingular transform makes use of wavelet transforms and histogram matching. Wavelet transforms are an effective tool in analyzing data structures. Histogram matching is applied to the wavelet coefficients and the ordinary image pixel values in order to create a transformed image that has the desired Gaussian statistics.

AB - We describe a new nonlinear discriminant analysis method for feature extraction. This method applies a nonsingular transform to the data such that the transformed data have a Gaussian distribution. Then a Bayes likelihood ratio is calculated for the transformed data. The nonsingular transform makes use of wavelet transforms and histogram matching. Wavelet transforms are an effective tool in analyzing data structures. Histogram matching is applied to the wavelet coefficients and the ordinary image pixel values in order to create a transformed image that has the desired Gaussian statistics.

KW - Histogram matching

KW - Hypothesis testing

KW - Nonlinear discriminant analysis

KW - Nonsingular transform

KW - Wavelets

UR - http://www.scopus.com/inward/record.url?scp=0034842824&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034842824&partnerID=8YFLogxK

U2 - 10.1117/12.431117

DO - 10.1117/12.431117

M3 - Article

AN - SCOPUS:0034842824

SN - 0277-786X

VL - 4322

SP - 448

EP - 455

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

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

IS - 1

ER -

Nonlinear discriminant analysis

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this