Rapid image analysis using neural signals

Santosh Mathan, Deniz Erdogmus, Yonghong Huang, Misha Pavel, Patricia Ververs, James Carciofini, Michael Dorneich, Stephen Whitlow

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

25 Citations (Scopus)

Abstract

The problem of extracting information from large collections of imagery is a challenge with few good solutions. Computers typically cannot interpret imagery as effectively as humans can, and manual analysis tools are slow. The research reported here explores the feasibility of speeding up manual image analysis by tapping into split second perceptual judgments using electroencephalograph sensors. Experimental results show that a combination of neurophysiological signals and overt physical responses-detected while a user views imagery in high speed bursts of approximately 10 images per second-provide a basis for detecting targets within large image sets. Results show an approximately six-fold, statistically significant, reduction in the time required to detect targets at high accuracy levels compared to conventional broad-area image analysis.

Original languageEnglish (US)
Title of host publicationConference on Human Factors in Computing Systems - Proceedings
Pages3309-3314
Number of pages6
DOIs
StatePublished - 2008
Event28th Annual CHI Conference on Human Factors in Computing Systems - Florence, Italy
Duration: Apr 5 2008Apr 10 2008

Other

Other28th Annual CHI Conference on Human Factors in Computing Systems
CountryItaly
CityFlorence
Period4/5/084/10/08

Fingerprint

Image analysis
Sensors

Keywords

  • Brain computer interface
  • EEG
  • Rapid Serial Visual Presentation (RSVP)
  • Visual search

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

Mathan, S., Erdogmus, D., Huang, Y., Pavel, M., Ververs, P., Carciofini, J., ... Whitlow, S. (2008). Rapid image analysis using neural signals. In Conference on Human Factors in Computing Systems - Proceedings (pp. 3309-3314) https://doi.org/10.1145/1358628.1358849

Rapid image analysis using neural signals. / Mathan, Santosh; Erdogmus, Deniz; Huang, Yonghong; Pavel, Misha; Ververs, Patricia; Carciofini, James; Dorneich, Michael; Whitlow, Stephen.

Conference on Human Factors in Computing Systems - Proceedings. 2008. p. 3309-3314.

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

Mathan, S, Erdogmus, D, Huang, Y, Pavel, M, Ververs, P, Carciofini, J, Dorneich, M & Whitlow, S 2008, Rapid image analysis using neural signals. in Conference on Human Factors in Computing Systems - Proceedings. pp. 3309-3314, 28th Annual CHI Conference on Human Factors in Computing Systems, Florence, Italy, 4/5/08. https://doi.org/10.1145/1358628.1358849
Mathan S, Erdogmus D, Huang Y, Pavel M, Ververs P, Carciofini J et al. Rapid image analysis using neural signals. In Conference on Human Factors in Computing Systems - Proceedings. 2008. p. 3309-3314 https://doi.org/10.1145/1358628.1358849
Mathan, Santosh ; Erdogmus, Deniz ; Huang, Yonghong ; Pavel, Misha ; Ververs, Patricia ; Carciofini, James ; Dorneich, Michael ; Whitlow, Stephen. / Rapid image analysis using neural signals. Conference on Human Factors in Computing Systems - Proceedings. 2008. pp. 3309-3314
@inproceedings{2965d3f8084e4fa095c317a077da44be,
title = "Rapid image analysis using neural signals",
abstract = "The problem of extracting information from large collections of imagery is a challenge with few good solutions. Computers typically cannot interpret imagery as effectively as humans can, and manual analysis tools are slow. The research reported here explores the feasibility of speeding up manual image analysis by tapping into split second perceptual judgments using electroencephalograph sensors. Experimental results show that a combination of neurophysiological signals and overt physical responses-detected while a user views imagery in high speed bursts of approximately 10 images per second-provide a basis for detecting targets within large image sets. Results show an approximately six-fold, statistically significant, reduction in the time required to detect targets at high accuracy levels compared to conventional broad-area image analysis.",
keywords = "Brain computer interface, EEG, Rapid Serial Visual Presentation (RSVP), Visual search",
author = "Santosh Mathan and Deniz Erdogmus and Yonghong Huang and Misha Pavel and Patricia Ververs and James Carciofini and Michael Dorneich and Stephen Whitlow",
year = "2008",
doi = "10.1145/1358628.1358849",
language = "English (US)",
pages = "3309--3314",
booktitle = "Conference on Human Factors in Computing Systems - Proceedings",

}

TY - GEN

T1 - Rapid image analysis using neural signals

AU - Mathan, Santosh

AU - Erdogmus, Deniz

AU - Huang, Yonghong

AU - Pavel, Misha

AU - Ververs, Patricia

AU - Carciofini, James

AU - Dorneich, Michael

AU - Whitlow, Stephen

PY - 2008

Y1 - 2008

N2 - The problem of extracting information from large collections of imagery is a challenge with few good solutions. Computers typically cannot interpret imagery as effectively as humans can, and manual analysis tools are slow. The research reported here explores the feasibility of speeding up manual image analysis by tapping into split second perceptual judgments using electroencephalograph sensors. Experimental results show that a combination of neurophysiological signals and overt physical responses-detected while a user views imagery in high speed bursts of approximately 10 images per second-provide a basis for detecting targets within large image sets. Results show an approximately six-fold, statistically significant, reduction in the time required to detect targets at high accuracy levels compared to conventional broad-area image analysis.

AB - The problem of extracting information from large collections of imagery is a challenge with few good solutions. Computers typically cannot interpret imagery as effectively as humans can, and manual analysis tools are slow. The research reported here explores the feasibility of speeding up manual image analysis by tapping into split second perceptual judgments using electroencephalograph sensors. Experimental results show that a combination of neurophysiological signals and overt physical responses-detected while a user views imagery in high speed bursts of approximately 10 images per second-provide a basis for detecting targets within large image sets. Results show an approximately six-fold, statistically significant, reduction in the time required to detect targets at high accuracy levels compared to conventional broad-area image analysis.

KW - Brain computer interface

KW - EEG

KW - Rapid Serial Visual Presentation (RSVP)

KW - Visual search

UR - http://www.scopus.com/inward/record.url?scp=57049175945&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57049175945&partnerID=8YFLogxK

U2 - 10.1145/1358628.1358849

DO - 10.1145/1358628.1358849

M3 - Conference contribution

AN - SCOPUS:57049175945

SP - 3309

EP - 3314

BT - Conference on Human Factors in Computing Systems - Proceedings

ER -