On the existence of face quality measures

P. Jonathon Phillips; J. Ross Beveridge; David S. Bolme; Bruce A. Draper; Geof H. Given; Yui Man Lui; Su Cheng; Mohammad Nayeem Teli; Hao Zhang

doi:10.1109/BTAS.2013.6712715

On the existence of face quality measures

P. Jonathon Phillips
, J. Ross Beveridge
, David S. Bolme
, Bruce A. Draper
, Geof H. Given
, Yui Man Lui
, Su Cheng
, Mohammad Nayeem Teli
, Hao Zhang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

35 Scopus citations

Abstract

We investigate the existence of quality measures for face recognition. First, we introduce the concept of an oracle for image quality in the context of face recognition. Next we introduce greedy pruned ordering (GPO) as an approximation to an image quality oracle. GPO analysis provides an estimated upper bound for quality measures, given a face recognition algorithm and data set. We then assess the performance of 12 commonly proposed face image quality measures against this standard. In addition, we investigate the potential for learning new quality measures via supervised learning. Finally, we show that GPO analysis is applicable to other biometrics.

Original language	English
Title of host publication	IEEE 6th International Conference on Biometrics
Subtitle of host publication	Theory, Applications and Systems, BTAS 2013
Publisher	IEEE Computer Society
ISBN (Print)	9781479905270
DOIs	https://doi.org/10.1109/BTAS.2013.6712715
State	Published - 2013
Event	6th IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013 - Washington, DC, United States Duration: Sep 29 2013 → Oct 2 2013

Publication series

Name	IEEE 6th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013

Conference

Conference	6th IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013
Country/Territory	United States
City	Washington, DC
Period	09/29/13 → 10/2/13

Access to Document

10.1109/BTAS.2013.6712715

Cite this

Phillips, P. J., Beveridge, J. R., Bolme, D. S., Draper, B. A., Given, G. H., Lui, Y. M., Cheng, S., Teli, M. N., & Zhang, H. (2013). On the existence of face quality measures. In IEEE 6th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013 Article 6712715 (IEEE 6th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013). IEEE Computer Society. https://doi.org/10.1109/BTAS.2013.6712715

@inproceedings{9f93efe45ed642dfb15aea1afe9181eb,

title = "On the existence of face quality measures",

abstract = "We investigate the existence of quality measures for face recognition. First, we introduce the concept of an oracle for image quality in the context of face recognition. Next we introduce greedy pruned ordering (GPO) as an approximation to an image quality oracle. GPO analysis provides an estimated upper bound for quality measures, given a face recognition algorithm and data set. We then assess the performance of 12 commonly proposed face image quality measures against this standard. In addition, we investigate the potential for learning new quality measures via supervised learning. Finally, we show that GPO analysis is applicable to other biometrics.",

author = "Phillips, \{P. Jonathon\} and Beveridge, \{J. Ross\} and Bolme, \{David S.\} and Draper, \{Bruce A.\} and Given, \{Geof H.\} and Lui, \{Yui Man\} and Su Cheng and Teli, \{Mohammad Nayeem\} and Hao Zhang",

year = "2013",

doi = "10.1109/BTAS.2013.6712715",

language = "English",

isbn = "9781479905270",

series = "IEEE 6th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013",

publisher = "IEEE Computer Society",

booktitle = "IEEE 6th International Conference on Biometrics",

note = "6th IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013 ; Conference date: 29-09-2013 Through 02-10-2013",

}

Phillips, PJ, Beveridge, JR, Bolme, DS, Draper, BA, Given, GH, Lui, YM, Cheng, S, Teli, MN & Zhang, H 2013, On the existence of face quality measures. in IEEE 6th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013., 6712715, IEEE 6th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013, IEEE Computer Society, 6th IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013, Washington, DC, United States, 09/29/13. https://doi.org/10.1109/BTAS.2013.6712715

On the existence of face quality measures. / Phillips, P. Jonathon; Beveridge, J. Ross; Bolme, David S. et al.
IEEE 6th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013. IEEE Computer Society, 2013. 6712715 (IEEE 6th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - On the existence of face quality measures

AU - Phillips, P. Jonathon

AU - Beveridge, J. Ross

AU - Bolme, David S.

AU - Draper, Bruce A.

AU - Given, Geof H.

AU - Lui, Yui Man

AU - Cheng, Su

AU - Teli, Mohammad Nayeem

AU - Zhang, Hao

PY - 2013

Y1 - 2013

N2 - We investigate the existence of quality measures for face recognition. First, we introduce the concept of an oracle for image quality in the context of face recognition. Next we introduce greedy pruned ordering (GPO) as an approximation to an image quality oracle. GPO analysis provides an estimated upper bound for quality measures, given a face recognition algorithm and data set. We then assess the performance of 12 commonly proposed face image quality measures against this standard. In addition, we investigate the potential for learning new quality measures via supervised learning. Finally, we show that GPO analysis is applicable to other biometrics.

AB - We investigate the existence of quality measures for face recognition. First, we introduce the concept of an oracle for image quality in the context of face recognition. Next we introduce greedy pruned ordering (GPO) as an approximation to an image quality oracle. GPO analysis provides an estimated upper bound for quality measures, given a face recognition algorithm and data set. We then assess the performance of 12 commonly proposed face image quality measures against this standard. In addition, we investigate the potential for learning new quality measures via supervised learning. Finally, we show that GPO analysis is applicable to other biometrics.

UR - https://www.scopus.com/pages/publications/84893719942

U2 - 10.1109/BTAS.2013.6712715

DO - 10.1109/BTAS.2013.6712715

M3 - Conference contribution

AN - SCOPUS:84893719942

SN - 9781479905270

T3 - IEEE 6th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013

BT - IEEE 6th International Conference on Biometrics

PB - IEEE Computer Society

T2 - 6th IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013

Y2 - 29 September 2013 through 2 October 2013

ER -

Phillips PJ, Beveridge JR, Bolme DS, Draper BA, Given GH, Lui YM et al. On the existence of face quality measures. In IEEE 6th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013. IEEE Computer Society. 2013. 6712715. (IEEE 6th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2013). doi: 10.1109/BTAS.2013.6712715

On the existence of face quality measures

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this