Task-specific information: An imaging system analysis tool

Amit Ashok, Pawan K. Baheti, Mark A Neifeld

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

We present a novel method for computing the information content of an image. We introduce the notion of task-specific information (TSI) in order to quantify imaging system performance for a given task. This new approach employs a recently-discovered relationship between the Shannon mutual-information and minimum estimation error. We demonstrate the utility of the TSI formulation by applying it to several familiar imaging systems including (a) geometric imagers, (b) diffraction-limiter imagers, and (c) projective/compressive imagers. Imaging system TSI performance is analyzed for two tasks: (a) detection, and (b) classification.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Volume6575
DOIs
StatePublished - 2007
EventVisual Information Processing XVI - Orlando, FL, United States
Duration: Apr 10 2007Apr 10 2007

Other

OtherVisual Information Processing XVI
CountryUnited States
CityOrlando, FL
Period4/10/074/10/07

Fingerprint

systems analysis
Image sensors
Imaging systems
Systems analysis
Limiters
Error analysis
Diffraction
formulations
diffraction

Keywords

  • Diffraction-limited imager
  • Entropy
  • Minimum-mean square error
  • Mutual information

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Ashok, A., Baheti, P. K., & Neifeld, M. A. (2007). Task-specific information: An imaging system analysis tool. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 6575). [65750G] https://doi.org/10.1117/12.720878

Task-specific information : An imaging system analysis tool. / Ashok, Amit; Baheti, Pawan K.; Neifeld, Mark A.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6575 2007. 65750G.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ashok, A, Baheti, PK & Neifeld, MA 2007, Task-specific information: An imaging system analysis tool. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 6575, 65750G, Visual Information Processing XVI, Orlando, FL, United States, 4/10/07. https://doi.org/10.1117/12.720878
Ashok A, Baheti PK, Neifeld MA. Task-specific information: An imaging system analysis tool. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6575. 2007. 65750G https://doi.org/10.1117/12.720878
Ashok, Amit ; Baheti, Pawan K. ; Neifeld, Mark A. / Task-specific information : An imaging system analysis tool. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6575 2007.
@inproceedings{0c6acb91987c4d7eb19b0fe3ecb6acf6,
title = "Task-specific information: An imaging system analysis tool",
abstract = "We present a novel method for computing the information content of an image. We introduce the notion of task-specific information (TSI) in order to quantify imaging system performance for a given task. This new approach employs a recently-discovered relationship between the Shannon mutual-information and minimum estimation error. We demonstrate the utility of the TSI formulation by applying it to several familiar imaging systems including (a) geometric imagers, (b) diffraction-limiter imagers, and (c) projective/compressive imagers. Imaging system TSI performance is analyzed for two tasks: (a) detection, and (b) classification.",
keywords = "Diffraction-limited imager, Entropy, Minimum-mean square error, Mutual information",
author = "Amit Ashok and Baheti, {Pawan K.} and Neifeld, {Mark A}",
year = "2007",
doi = "10.1117/12.720878",
language = "English (US)",
isbn = "0819466972",
volume = "6575",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Task-specific information

T2 - An imaging system analysis tool

AU - Ashok, Amit

AU - Baheti, Pawan K.

AU - Neifeld, Mark A

PY - 2007

Y1 - 2007

N2 - We present a novel method for computing the information content of an image. We introduce the notion of task-specific information (TSI) in order to quantify imaging system performance for a given task. This new approach employs a recently-discovered relationship between the Shannon mutual-information and minimum estimation error. We demonstrate the utility of the TSI formulation by applying it to several familiar imaging systems including (a) geometric imagers, (b) diffraction-limiter imagers, and (c) projective/compressive imagers. Imaging system TSI performance is analyzed for two tasks: (a) detection, and (b) classification.

AB - We present a novel method for computing the information content of an image. We introduce the notion of task-specific information (TSI) in order to quantify imaging system performance for a given task. This new approach employs a recently-discovered relationship between the Shannon mutual-information and minimum estimation error. We demonstrate the utility of the TSI formulation by applying it to several familiar imaging systems including (a) geometric imagers, (b) diffraction-limiter imagers, and (c) projective/compressive imagers. Imaging system TSI performance is analyzed for two tasks: (a) detection, and (b) classification.

KW - Diffraction-limited imager

KW - Entropy

KW - Minimum-mean square error

KW - Mutual information

UR - http://www.scopus.com/inward/record.url?scp=36048931762&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36048931762&partnerID=8YFLogxK

U2 - 10.1117/12.720878

DO - 10.1117/12.720878

M3 - Conference contribution

AN - SCOPUS:36048931762

SN - 0819466972

SN - 9780819466976

VL - 6575

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

ER -