Face recognition from unconstrained images: Progress with prototypes

Rob Jenkins; A. Mike Burton; David White

doi:10.1109/FGR.2006.45

Face recognition from unconstrained images: Progress with prototypes

Rob Jenkins^*, A. Mike Burton, David White

^*Corresponding author for this work

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

16 Citations (Scopus)

Abstract

Artificial face recognition systems typically do not attempt to handle very variable images. By comparison, human perceivers can recognize familiar faces over much more varied conditions. We describe a prototype face representation based on simple image-averaging. We have argued that this forms a good candidate for understanding human face perception. Here we examine the stability of these representations by asking (i) how quickly they converge; and (ii) how resistant they are to contamination due to previous mis identifications. We conclude that face averages provide promising representations for use in artificial recognition.

Original language	English
Title of host publication	Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition (FGR'06)
Publisher	IEEE Computer Society
Pages	25-30
Number of pages	6
ISBN (Print)	0769525032, 9780769525037
DOIs	https://doi.org/10.1109/FGR.2006.45
Publication status	Published - 2006
Externally published	Yes
Event	FGR 2006: 7th International Conference on Automatic Face and Gesture Recognition - Southampton, United Kingdom Duration: 10 Apr 2006 → 12 Apr 2006

Publication series

Name	FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
Volume	2006

Conference

Conference	FGR 2006: 7th International Conference on Automatic Face and Gesture Recognition
Country/Territory	United Kingdom
City	Southampton
Period	10/04/06 → 12/04/06

Access to Document

10.1109/FGR.2006.45

Cite this

Jenkins, R., Mike Burton, A., & White, D. (2006). Face recognition from unconstrained images: Progress with prototypes. In Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition (FGR'06) (pp. 25-30). Article 1612992 (FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition; Vol. 2006). IEEE Computer Society. https://doi.org/10.1109/FGR.2006.45

@inproceedings{c7af9e85d13640b5b53729cc38ce829f,

title = "Face recognition from unconstrained images: Progress with prototypes",

abstract = "Artificial face recognition systems typically do not attempt to handle very variable images. By comparison, human perceivers can recognize familiar faces over much more varied conditions. We describe a prototype face representation based on simple image-averaging. We have argued that this forms a good candidate for understanding human face perception. Here we examine the stability of these representations by asking (i) how quickly they converge; and (ii) how resistant they are to contamination due to previous mis identifications. We conclude that face averages provide promising representations for use in artificial recognition.",

author = "Rob Jenkins and {Mike Burton}, A. and David White",

note = "Copyright: Copyright 2011 Elsevier B.V., All rights reserved.; FGR 2006: 7th International Conference on Automatic Face and Gesture Recognition ; Conference date: 10-04-2006 Through 12-04-2006",

year = "2006",

doi = "10.1109/FGR.2006.45",

language = "English",

isbn = "0769525032",

series = "FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition",

publisher = "IEEE Computer Society",

pages = "25--30",

booktitle = "Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition (FGR'06)",

address = "United States",

}

Jenkins, R, Mike Burton, A & White, D 2006, Face recognition from unconstrained images: Progress with prototypes. in Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition (FGR'06)., 1612992, FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition, vol. 2006, IEEE Computer Society, pp. 25-30, FGR 2006: 7th International Conference on Automatic Face and Gesture Recognition, Southampton, United Kingdom, 10/04/06. https://doi.org/10.1109/FGR.2006.45

Face recognition from unconstrained images: Progress with prototypes. / Jenkins, Rob; Mike Burton, A.; White, David.
Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition (FGR'06). IEEE Computer Society, 2006. p. 25-30 1612992 (FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition; Vol. 2006).

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

TY - GEN

T1 - Face recognition from unconstrained images: Progress with prototypes

AU - Jenkins, Rob

AU - Mike Burton, A.

AU - White, David

PY - 2006

Y1 - 2006

N2 - Artificial face recognition systems typically do not attempt to handle very variable images. By comparison, human perceivers can recognize familiar faces over much more varied conditions. We describe a prototype face representation based on simple image-averaging. We have argued that this forms a good candidate for understanding human face perception. Here we examine the stability of these representations by asking (i) how quickly they converge; and (ii) how resistant they are to contamination due to previous mis identifications. We conclude that face averages provide promising representations for use in artificial recognition.

AB - Artificial face recognition systems typically do not attempt to handle very variable images. By comparison, human perceivers can recognize familiar faces over much more varied conditions. We describe a prototype face representation based on simple image-averaging. We have argued that this forms a good candidate for understanding human face perception. Here we examine the stability of these representations by asking (i) how quickly they converge; and (ii) how resistant they are to contamination due to previous mis identifications. We conclude that face averages provide promising representations for use in artificial recognition.

UR - http://www.scopus.com/inward/record.url?scp=33750813782&partnerID=8YFLogxK

U2 - 10.1109/FGR.2006.45

DO - 10.1109/FGR.2006.45

M3 - Conference contribution

AN - SCOPUS:33750813782

SN - 0769525032

SN - 9780769525037

T3 - FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition

SP - 25

EP - 30

BT - Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition (FGR'06)

PB - IEEE Computer Society

T2 - FGR 2006: 7th International Conference on Automatic Face and Gesture Recognition

Y2 - 10 April 2006 through 12 April 2006

ER -

Jenkins R, Mike Burton A, White D. Face recognition from unconstrained images: Progress with prototypes. In Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition (FGR'06). IEEE Computer Society. 2006. p. 25-30. 1612992. (FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition). doi: 10.1109/FGR.2006.45

Face recognition from unconstrained images: Progress with prototypes

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this