Password less system security using multimodal biometric fusion

Research output: A Conference proceeding or a Chapter in BookConference contribution

Abstract

In this paper, we propose the use of audio visual features for person identity verification instead of traditional passwords and pins for secure access. Experiments performed on different gender specific subsets of data from VidTIMIT and UCB N multimodal databases under clean and noisy conditions show that with audio-visual fusion, about 25-40% improvement in performance can be achieved with multimodal fusion as compared to single mode-audio only or visual only mode even under noisy acoustic conditions.

Original languageEnglish
Title of host publicationProceedings of the 3rd Indian International Conference on Artificial Intelligence, Pune, India, December 17-19, 2007
Subtitle of host publicationIICAI 2007
Pages1-10
Number of pages10
Publication statusPublished - 2007
Event3rd Indian International Conference on Artificial Intelligence, IICAI 2007 - Pune, India
Duration: 17 Dec 200719 Dec 2007

Conference

Conference3rd Indian International Conference on Artificial Intelligence, IICAI 2007
CountryIndia
CityPune
Period17/12/0719/12/07

Fingerprint

Biometrics
Security systems
Fusion reactions
Acoustics
Experiments

Cite this

Chetty, G., Tran, D., Sharma, D., & Balachandran, B. (2007). Password less system security using multimodal biometric fusion. In Proceedings of the 3rd Indian International Conference on Artificial Intelligence, Pune, India, December 17-19, 2007: IICAI 2007 (pp. 1-10)
Chetty, Girija ; Tran, Dat ; Sharma, Dharmendra ; Balachandran, Bala. / Password less system security using multimodal biometric fusion. Proceedings of the 3rd Indian International Conference on Artificial Intelligence, Pune, India, December 17-19, 2007: IICAI 2007. 2007. pp. 1-10
@inproceedings{5eec9f1860d9479ea936274804efe12c,
title = "Password less system security using multimodal biometric fusion",
abstract = "In this paper, we propose the use of audio visual features for person identity verification instead of traditional passwords and pins for secure access. Experiments performed on different gender specific subsets of data from VidTIMIT and UCB N multimodal databases under clean and noisy conditions show that with audio-visual fusion, about 25-40{\%} improvement in performance can be achieved with multimodal fusion as compared to single mode-audio only or visual only mode even under noisy acoustic conditions.",
author = "Girija Chetty and Dat Tran and Dharmendra Sharma and Bala Balachandran",
year = "2007",
language = "English",
isbn = "9780972741224",
pages = "1--10",
booktitle = "Proceedings of the 3rd Indian International Conference on Artificial Intelligence, Pune, India, December 17-19, 2007",

}

Chetty, G, Tran, D, Sharma, D & Balachandran, B 2007, Password less system security using multimodal biometric fusion. in Proceedings of the 3rd Indian International Conference on Artificial Intelligence, Pune, India, December 17-19, 2007: IICAI 2007. pp. 1-10, 3rd Indian International Conference on Artificial Intelligence, IICAI 2007, Pune, India, 17/12/07.

Password less system security using multimodal biometric fusion. / Chetty, Girija; Tran, Dat; Sharma, Dharmendra; Balachandran, Bala.

Proceedings of the 3rd Indian International Conference on Artificial Intelligence, Pune, India, December 17-19, 2007: IICAI 2007. 2007. p. 1-10.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Password less system security using multimodal biometric fusion

AU - Chetty, Girija

AU - Tran, Dat

AU - Sharma, Dharmendra

AU - Balachandran, Bala

PY - 2007

Y1 - 2007

N2 - In this paper, we propose the use of audio visual features for person identity verification instead of traditional passwords and pins for secure access. Experiments performed on different gender specific subsets of data from VidTIMIT and UCB N multimodal databases under clean and noisy conditions show that with audio-visual fusion, about 25-40% improvement in performance can be achieved with multimodal fusion as compared to single mode-audio only or visual only mode even under noisy acoustic conditions.

AB - In this paper, we propose the use of audio visual features for person identity verification instead of traditional passwords and pins for secure access. Experiments performed on different gender specific subsets of data from VidTIMIT and UCB N multimodal databases under clean and noisy conditions show that with audio-visual fusion, about 25-40% improvement in performance can be achieved with multimodal fusion as compared to single mode-audio only or visual only mode even under noisy acoustic conditions.

UR - http://www.scopus.com/inward/record.url?scp=84872095131&partnerID=8YFLogxK

UR - https://dblp.org/db/conf/iicai/iicai2007.html

M3 - Conference contribution

SN - 9780972741224

SP - 1

EP - 10

BT - Proceedings of the 3rd Indian International Conference on Artificial Intelligence, Pune, India, December 17-19, 2007

ER -

Chetty G, Tran D, Sharma D, Balachandran B. Password less system security using multimodal biometric fusion. In Proceedings of the 3rd Indian International Conference on Artificial Intelligence, Pune, India, December 17-19, 2007: IICAI 2007. 2007. p. 1-10