Large-scale image database triage via EEG evoked responses

Yonghong Huang, Deniz Erdogmus, Santosh Mathan, Misha Pavel

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

18 Citations (Scopus)

Abstract

This paper describes an approach for target image search using human brain signals generated by perceptual processes in the brain. The human brain generates event related potentials (ERPs) in response to critical events, such as interesting/novel visual stimuli in the form of a target image. In this paper, we describe experiments involving six professional image analysts and summarize the ERP detection performance as they search for targets within a large image database. We develop a disjoint windowing scheme for data preprocessing to discard irrelevant and redundant information from the raw data to get clean training data. We apply support vector machines to detect ERPs and conduct 10-fold cross validation for parameter regularization. The results demonstrate that the ERP pattern recognition can provide reliable inference for image triage.

Original languageEnglish (US)
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages429-432
Number of pages4
DOIs
StatePublished - 2008
Event2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP - Las Vegas, NV, United States
Duration: Mar 31 2008Apr 4 2008

Other

Other2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
CountryUnited States
CityLas Vegas, NV
Period3/31/084/4/08

Fingerprint

electroencephalography
Electroencephalography
Brain
brain
Pattern recognition
Support vector machines
visual stimuli
preprocessing
inference
pattern recognition
education
Experiments

Keywords

  • Brain computer interface
  • EEG
  • Event related potentials
  • Image triage
  • Pattern recognition

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing
  • Acoustics and Ultrasonics

Cite this

Huang, Y., Erdogmus, D., Mathan, S., & Pavel, M. (2008). Large-scale image database triage via EEG evoked responses. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 429-432). [4517638] https://doi.org/10.1109/ICASSP.2008.4517638

Large-scale image database triage via EEG evoked responses. / Huang, Yonghong; Erdogmus, Deniz; Mathan, Santosh; Pavel, Misha.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2008. p. 429-432 4517638.

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

Huang, Y, Erdogmus, D, Mathan, S & Pavel, M 2008, Large-scale image database triage via EEG evoked responses. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 4517638, pp. 429-432, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, Las Vegas, NV, United States, 3/31/08. https://doi.org/10.1109/ICASSP.2008.4517638
Huang Y, Erdogmus D, Mathan S, Pavel M. Large-scale image database triage via EEG evoked responses. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2008. p. 429-432. 4517638 https://doi.org/10.1109/ICASSP.2008.4517638
Huang, Yonghong ; Erdogmus, Deniz ; Mathan, Santosh ; Pavel, Misha. / Large-scale image database triage via EEG evoked responses. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2008. pp. 429-432
@inproceedings{c977b6b92f364df0b5789bfc2a7affe8,
title = "Large-scale image database triage via EEG evoked responses",
abstract = "This paper describes an approach for target image search using human brain signals generated by perceptual processes in the brain. The human brain generates event related potentials (ERPs) in response to critical events, such as interesting/novel visual stimuli in the form of a target image. In this paper, we describe experiments involving six professional image analysts and summarize the ERP detection performance as they search for targets within a large image database. We develop a disjoint windowing scheme for data preprocessing to discard irrelevant and redundant information from the raw data to get clean training data. We apply support vector machines to detect ERPs and conduct 10-fold cross validation for parameter regularization. The results demonstrate that the ERP pattern recognition can provide reliable inference for image triage.",
keywords = "Brain computer interface, EEG, Event related potentials, Image triage, Pattern recognition",
author = "Yonghong Huang and Deniz Erdogmus and Santosh Mathan and Misha Pavel",
year = "2008",
doi = "10.1109/ICASSP.2008.4517638",
language = "English (US)",
isbn = "1424414849",
pages = "429--432",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

}

TY - GEN

T1 - Large-scale image database triage via EEG evoked responses

AU - Huang, Yonghong

AU - Erdogmus, Deniz

AU - Mathan, Santosh

AU - Pavel, Misha

PY - 2008

Y1 - 2008

N2 - This paper describes an approach for target image search using human brain signals generated by perceptual processes in the brain. The human brain generates event related potentials (ERPs) in response to critical events, such as interesting/novel visual stimuli in the form of a target image. In this paper, we describe experiments involving six professional image analysts and summarize the ERP detection performance as they search for targets within a large image database. We develop a disjoint windowing scheme for data preprocessing to discard irrelevant and redundant information from the raw data to get clean training data. We apply support vector machines to detect ERPs and conduct 10-fold cross validation for parameter regularization. The results demonstrate that the ERP pattern recognition can provide reliable inference for image triage.

AB - This paper describes an approach for target image search using human brain signals generated by perceptual processes in the brain. The human brain generates event related potentials (ERPs) in response to critical events, such as interesting/novel visual stimuli in the form of a target image. In this paper, we describe experiments involving six professional image analysts and summarize the ERP detection performance as they search for targets within a large image database. We develop a disjoint windowing scheme for data preprocessing to discard irrelevant and redundant information from the raw data to get clean training data. We apply support vector machines to detect ERPs and conduct 10-fold cross validation for parameter regularization. The results demonstrate that the ERP pattern recognition can provide reliable inference for image triage.

KW - Brain computer interface

KW - EEG

KW - Event related potentials

KW - Image triage

KW - Pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=51449117620&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51449117620&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2008.4517638

DO - 10.1109/ICASSP.2008.4517638

M3 - Conference contribution

AN - SCOPUS:51449117620

SN - 1424414849

SN - 9781424414840

SP - 429

EP - 432

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ER -