Multimodal Fuzzy Fusion for Biometric Identity Management

Girija Chetty; Dat Tran; Dharmendra Sharma

Multimodal Fuzzy Fusion for Biometric Identity Management

Girija Chetty, Dat Tran, Dharmendra Sharma

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

Abstract

Biometric identity management based only on the single biometric modality is not accurate or robust enough to be used in uncontrolled environments. This paper describes a fusion of face and voice biometric traits, based on fuzzy logic approach for speaker identity verification. In this approach, a scheme based on membership function and fuzzy integral is proposed to fuse information from the two modalities. Equal Error rate is used to evaluate the fusion scheme. Experimental results show the fusion scheme improves identity verification performance substantially and makes the system robust to environmental degradations such as acoustic noise and visual compression artefacts

Original language	English
Title of host publication	CEA'07: Proceedings of the 2007 annual Conference on International Conference on Computer Engineering and Applications
Editors	Dharmendra Sharma, L.C Jain, Dat Tran, Wanli Ma
Place of Publication	Wisconsin, USA
Publisher	World Scientific and Engineering Academy and Society Press (WSEAS)
Pages	1111-1114
Number of pages	4
ISBN (Electronic)	9789608457584
Publication status	Published - 2007
Event	International Conference on Computer Engineering and Applications, CEA 2007 - Queensland, Gold Coast, Australia Duration: 17 Jan 2007 → 19 Jan 2007 http://worldses.org/reports/2007/australia/

Conference

Conference	International Conference on Computer Engineering and Applications, CEA 2007
Abbreviated title	CEA 2007
Country/Territory	Australia
City	Gold Coast
Period	17/01/07 → 19/01/07
Internet address	http://worldses.org/reports/2007/australia/

Access to Document

https://dl.acm.org/doi/abs/10.5555/1348258.1348313

Cite this

Chetty, G., Tran, D., & Sharma, D. (2007). Multimodal Fuzzy Fusion for Biometric Identity Management. In D. Sharma, L. C. Jain, D. Tran, & W. Ma (Eds.), CEA'07: Proceedings of the 2007 annual Conference on International Conference on Computer Engineering and Applications (pp. 1111-1114). World Scientific and Engineering Academy and Society Press (WSEAS). https://dl.acm.org/doi/abs/10.5555/1348258.1348313

Chetty, Girija ; Tran, Dat ; Sharma, Dharmendra. / Multimodal Fuzzy Fusion for Biometric Identity Management. CEA'07: Proceedings of the 2007 annual Conference on International Conference on Computer Engineering and Applications. editor / Dharmendra Sharma ; L.C Jain ; Dat Tran ; Wanli Ma. Wisconsin, USA : World Scientific and Engineering Academy and Society Press (WSEAS), 2007. pp. 1111-1114

@inproceedings{968a69316c5041e3b9b6e52fab6ec05b,

title = "Multimodal Fuzzy Fusion for Biometric Identity Management",

abstract = "Biometric identity management based only on the single biometric modality is not accurate or robust enough to be used in uncontrolled environments. This paper describes a fusion of face and voice biometric traits, based on fuzzy logic approach for speaker identity verification. In this approach, a scheme based on membership function and fuzzy integral is proposed to fuse information from the two modalities. Equal Error rate is used to evaluate the fusion scheme. Experimental results show the fusion scheme improves identity verification performance substantially and makes the system robust to environmental degradations such as acoustic noise and visual compression artefacts",

author = "Girija Chetty and Dat Tran and Dharmendra Sharma",

year = "2007",

language = "English",

pages = "1111--1114",

editor = "Dharmendra Sharma and L.C Jain and Dat Tran and Wanli Ma",

booktitle = "CEA'07: Proceedings of the 2007 annual Conference on International Conference on Computer Engineering and Applications",

publisher = "World Scientific and Engineering Academy and Society Press (WSEAS)",

note = "International Conference on Computer Engineering and Applications, CEA 2007, CEA 2007 ; Conference date: 17-01-2007 Through 19-01-2007",

url = "http://worldses.org/reports/2007/australia/",

}

Chetty, G , Tran, D & Sharma, D 2007, Multimodal Fuzzy Fusion for Biometric Identity Management. in D Sharma, LC Jain, D Tran & W Ma (eds), CEA'07: Proceedings of the 2007 annual Conference on International Conference on Computer Engineering and Applications. World Scientific and Engineering Academy and Society Press (WSEAS), Wisconsin, USA, pp. 1111-1114, International Conference on Computer Engineering and Applications, CEA 2007, Gold Coast, Queensland, Australia, 17/01/07. <https://dl.acm.org/doi/abs/10.5555/1348258.1348313>

Multimodal Fuzzy Fusion for Biometric Identity Management. / Chetty, Girija ; Tran, Dat ; Sharma, Dharmendra.
CEA'07: Proceedings of the 2007 annual Conference on International Conference on Computer Engineering and Applications. ed. / Dharmendra Sharma; L.C Jain; Dat Tran; Wanli Ma. Wisconsin, USA: World Scientific and Engineering Academy and Society Press (WSEAS), 2007. p. 1111-1114.

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

TY - GEN

T1 - Multimodal Fuzzy Fusion for Biometric Identity Management

AU - Chetty, Girija

AU - Tran, Dat

AU - Sharma, Dharmendra

PY - 2007

Y1 - 2007

N2 - Biometric identity management based only on the single biometric modality is not accurate or robust enough to be used in uncontrolled environments. This paper describes a fusion of face and voice biometric traits, based on fuzzy logic approach for speaker identity verification. In this approach, a scheme based on membership function and fuzzy integral is proposed to fuse information from the two modalities. Equal Error rate is used to evaluate the fusion scheme. Experimental results show the fusion scheme improves identity verification performance substantially and makes the system robust to environmental degradations such as acoustic noise and visual compression artefacts

AB - Biometric identity management based only on the single biometric modality is not accurate or robust enough to be used in uncontrolled environments. This paper describes a fusion of face and voice biometric traits, based on fuzzy logic approach for speaker identity verification. In this approach, a scheme based on membership function and fuzzy integral is proposed to fuse information from the two modalities. Equal Error rate is used to evaluate the fusion scheme. Experimental results show the fusion scheme improves identity verification performance substantially and makes the system robust to environmental degradations such as acoustic noise and visual compression artefacts

M3 - Conference contribution

SP - 1111

EP - 1114

BT - CEA'07: Proceedings of the 2007 annual Conference on International Conference on Computer Engineering and Applications

A2 - Sharma, Dharmendra

A2 - Jain, L.C

A2 - Tran, Dat

A2 - Ma, Wanli

PB - World Scientific and Engineering Academy and Society Press (WSEAS)

CY - Wisconsin, USA

T2 - International Conference on Computer Engineering and Applications, CEA 2007

Y2 - 17 January 2007 through 19 January 2007

ER -