Nonlinear dimensionality reduction for structural discovery in image processing

David Floyd; Robert Cloutier; Teresa Zigh

doi:10.1109/AIPR.2013.6749319

Nonlinear dimensionality reduction for structural discovery in image processing

David Floyd, Robert Cloutier, Teresa Zigh

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Nonlinear dimensionality reduction techniques are a thriving area of research in many fields, including pattern recognition, statistical learning, medical imaging, and statistics. This is largely driven by our need to collect, represent, manipulate, and understand high-dimensional data in practically all areas of science. Here we define 'high-dimensional' to be where dimension d > 10, and in many applications d 10. In this paper we discuss several nonlinear dimensionality reduction techniques and compare their characteristics, with a focus on applications to improve tractability and provide low-dimensional structural discovery for image processing.

Original language	English
Title of host publication	2013 IEEE Applied Imagery Pattern Recognition Workshop
Subtitle of host publication	Sensing for Control and Augmentation, AIPR 2013
DOIs	https://doi.org/10.1109/AIPR.2013.6749319
State	Published - 2013
Event	2013 IEEE Applied Imagery Pattern Recognition Workshop: Sensing for Control and Augmentation, AIPR 2013 - Washington, DC, United States Duration: 23 Oct 2013 → 25 Oct 2013

Publication series

Name	Proceedings - Applied Imagery Pattern Recognition Workshop
ISSN (Print)	1550-5219

Conference

Conference	2013 IEEE Applied Imagery Pattern Recognition Workshop: Sensing for Control and Augmentation, AIPR 2013
Country/Territory	United States
City	Washington, DC
Period	23/10/13 → 25/10/13

Keywords

Changed data
Diffusion maps
Generalization
Kernel eigenmaps
Temporal graph evolution
Vector

Access to Document

10.1109/AIPR.2013.6749319

Cite this

@inproceedings{d8dfbf979dd5440385215f9f9b7c2bdf,

title = "Nonlinear dimensionality reduction for structural discovery in image processing",

abstract = "Nonlinear dimensionality reduction techniques are a thriving area of research in many fields, including pattern recognition, statistical learning, medical imaging, and statistics. This is largely driven by our need to collect, represent, manipulate, and understand high-dimensional data in practically all areas of science. Here we define 'high-dimensional' to be where dimension d > 10, and in many applications d 10. In this paper we discuss several nonlinear dimensionality reduction techniques and compare their characteristics, with a focus on applications to improve tractability and provide low-dimensional structural discovery for image processing.",

keywords = "Changed data, Diffusion maps, Generalization, Kernel eigenmaps, Temporal graph evolution, Vector",

author = "David Floyd and Robert Cloutier and Teresa Zigh",

year = "2013",

doi = "10.1109/AIPR.2013.6749319",

language = "English",

isbn = "9781479925407",

series = "Proceedings - Applied Imagery Pattern Recognition Workshop",

booktitle = "2013 IEEE Applied Imagery Pattern Recognition Workshop",

note = "2013 IEEE Applied Imagery Pattern Recognition Workshop: Sensing for Control and Augmentation, AIPR 2013 ; Conference date: 23-10-2013 Through 25-10-2013",

}

Floyd, D, Cloutier, R & Zigh, T 2013, Nonlinear dimensionality reduction for structural discovery in image processing. in 2013 IEEE Applied Imagery Pattern Recognition Workshop: Sensing for Control and Augmentation, AIPR 2013., 6749319, Proceedings - Applied Imagery Pattern Recognition Workshop, 2013 IEEE Applied Imagery Pattern Recognition Workshop: Sensing for Control and Augmentation, AIPR 2013, Washington, DC, United States, 23/10/13. https://doi.org/10.1109/AIPR.2013.6749319

Nonlinear dimensionality reduction for structural discovery in image processing. / Floyd, David; Cloutier, Robert; Zigh, Teresa.
2013 IEEE Applied Imagery Pattern Recognition Workshop: Sensing for Control and Augmentation, AIPR 2013. 2013. 6749319 (Proceedings - Applied Imagery Pattern Recognition Workshop).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Nonlinear dimensionality reduction for structural discovery in image processing

AU - Floyd, David

AU - Cloutier, Robert

AU - Zigh, Teresa

PY - 2013

Y1 - 2013

N2 - Nonlinear dimensionality reduction techniques are a thriving area of research in many fields, including pattern recognition, statistical learning, medical imaging, and statistics. This is largely driven by our need to collect, represent, manipulate, and understand high-dimensional data in practically all areas of science. Here we define 'high-dimensional' to be where dimension d > 10, and in many applications d 10. In this paper we discuss several nonlinear dimensionality reduction techniques and compare their characteristics, with a focus on applications to improve tractability and provide low-dimensional structural discovery for image processing.

AB - Nonlinear dimensionality reduction techniques are a thriving area of research in many fields, including pattern recognition, statistical learning, medical imaging, and statistics. This is largely driven by our need to collect, represent, manipulate, and understand high-dimensional data in practically all areas of science. Here we define 'high-dimensional' to be where dimension d > 10, and in many applications d 10. In this paper we discuss several nonlinear dimensionality reduction techniques and compare their characteristics, with a focus on applications to improve tractability and provide low-dimensional structural discovery for image processing.

KW - Changed data

KW - Diffusion maps

KW - Generalization

KW - Kernel eigenmaps

KW - Temporal graph evolution

KW - Vector

UR - http://www.scopus.com/inward/record.url?scp=84898482365&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898482365&partnerID=8YFLogxK

U2 - 10.1109/AIPR.2013.6749319

DO - 10.1109/AIPR.2013.6749319

M3 - Conference contribution

AN - SCOPUS:84898482365

SN - 9781479925407

T3 - Proceedings - Applied Imagery Pattern Recognition Workshop

BT - 2013 IEEE Applied Imagery Pattern Recognition Workshop

T2 - 2013 IEEE Applied Imagery Pattern Recognition Workshop: Sensing for Control and Augmentation, AIPR 2013

Y2 - 23 October 2013 through 25 October 2013

ER -

Nonlinear dimensionality reduction for structural discovery in image processing

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this