Minimum reconstruction error in feature-specific imaging

Jun Ke; Michael D. Stenner; Mark A. Neifeld

doi:10.1117/12.603059

Minimum reconstruction error in feature-specific imaging

Jun Ke, Michael D. Stenner, Mark A. Neifeld

Research output: Contribution to journal › Conference article › peer-review

7 Scopus citations

Abstract

We describe theoretical and experimental results for a new class of optimal features for feature-specific imaging (FSI). In this paper, we theoretically solve the reconstruction problem without noise, and find a more general solution than principle component analysis (PCA). We present a generalized framework to Qnd FSI projection matrices. Using Stochastic Tunneling, we find an optimal solution in the presence of noise and under an energy conservation constraint. We also show that a non-negativity requirement does not significantly reduce system performance. Finally, we propose an experimental system for FSI using a polarization-based optical pipeline processor.

Original language	English (US)
Article number	02
Pages (from-to)	7-12
Number of pages	6
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	5817
DOIs	https://doi.org/10.1117/12.603059
State	Published - 2005
Externally published	Yes
Event	Visual Information Processing XIV - Orlando, FL, United States Duration: Mar 29 2005 → Mar 30 2005

Keywords

Feature-Specific Imaging
Image reconstruction
PCA
Stochastic Tunneling
Weiner operator

ASJC Scopus subject areas

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

Access to Document

10.1117/12.603059

Cite this

@article{c9a0d663ae1043a1b17e50c6ad747251,

title = "Minimum reconstruction error in feature-specific imaging",

abstract = "We describe theoretical and experimental results for a new class of optimal features for feature-specific imaging (FSI). In this paper, we theoretically solve the reconstruction problem without noise, and find a more general solution than principle component analysis (PCA). We present a generalized framework to Qnd FSI projection matrices. Using Stochastic Tunneling, we find an optimal solution in the presence of noise and under an energy conservation constraint. We also show that a non-negativity requirement does not significantly reduce system performance. Finally, we propose an experimental system for FSI using a polarization-based optical pipeline processor.",

keywords = "Feature-Specific Imaging, Image reconstruction, PCA, Stochastic Tunneling, Weiner operator",

author = "Jun Ke and Stenner, {Michael D.} and Neifeld, {Mark A.}",

year = "2005",

doi = "10.1117/12.603059",

language = "English (US)",

volume = "5817",

pages = "7--12",

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

issn = "0277-786X",

publisher = "SPIE",

note = "Visual Information Processing XIV ; Conference date: 29-03-2005 Through 30-03-2005",

}

TY - JOUR

T1 - Minimum reconstruction error in feature-specific imaging

AU - Ke, Jun

AU - Stenner, Michael D.

AU - Neifeld, Mark A.

PY - 2005

Y1 - 2005

N2 - We describe theoretical and experimental results for a new class of optimal features for feature-specific imaging (FSI). In this paper, we theoretically solve the reconstruction problem without noise, and find a more general solution than principle component analysis (PCA). We present a generalized framework to Qnd FSI projection matrices. Using Stochastic Tunneling, we find an optimal solution in the presence of noise and under an energy conservation constraint. We also show that a non-negativity requirement does not significantly reduce system performance. Finally, we propose an experimental system for FSI using a polarization-based optical pipeline processor.

AB - We describe theoretical and experimental results for a new class of optimal features for feature-specific imaging (FSI). In this paper, we theoretically solve the reconstruction problem without noise, and find a more general solution than principle component analysis (PCA). We present a generalized framework to Qnd FSI projection matrices. Using Stochastic Tunneling, we find an optimal solution in the presence of noise and under an energy conservation constraint. We also show that a non-negativity requirement does not significantly reduce system performance. Finally, we propose an experimental system for FSI using a polarization-based optical pipeline processor.

KW - Feature-Specific Imaging

KW - Image reconstruction

KW - PCA

KW - Stochastic Tunneling

KW - Weiner operator

UR - http://www.scopus.com/inward/record.url?scp=27644566559&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27644566559&partnerID=8YFLogxK

U2 - 10.1117/12.603059

DO - 10.1117/12.603059

M3 - Conference article

AN - SCOPUS:27644566559

SN - 0277-786X

VL - 5817

SP - 7

EP - 12

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

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

M1 - 02

T2 - Visual Information Processing XIV

Y2 - 29 March 2005 through 30 March 2005

ER -

Minimum reconstruction error in feature-specific imaging

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this