Facial dynamic modelling using long short-term memory network: Analysis and application to face authentication

Seong Tae Kim; Dae Hoe Kim; Yong Man Ro

doi:10.1109/BTAS.2016.7791172

Facial dynamic modelling using long short-term memory network: Analysis and application to face authentication

Seong Tae Kim
, Dae Hoe Kim
, Yong Man Ro

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

12 Citations (Scopus)

Abstract

According to the supplementary information hypothesis in psychology, facial motion benefits the perception of identity for human. In this study, we propose a face authentication framework which exploits facial dynamics with appearance to effectively improve the authentication performance. In our face authentication scenario, users are guided to make smile expression and the identity behind smile dynamics has been utilized. In order to model the facial dynamics, the recurrent neural network with long short-term memory cells is adopted and the facial dynamics from onset to offset duration is encoded. Comparative experiment has showed that the combination of facial dynamic features with appearance features improves the accuracy of the face authentication system compared to conventional appearance features and spatio-temporal features by effectively capturing facial dynamic and appearance features.

Original language	English
Title of host publication	IEEE 8th International Conference on Biometrics
Subtitle of host publication	Theory, Applications and Systems, BTAS 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781467397339
DOIs	https://doi.org/10.1109/BTAS.2016.7791172
Publication status	Published - 19 Dec 2016
Event	8th IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2016 - Niagara Falls, United States Duration: 6 Sept 2016 → 9 Sept 2016

Publication series

Name	2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016

Conference

Conference	8th IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2016
Country/Territory	United States
City	Niagara Falls
Period	6/09/16 → 9/09/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Access to Document

10.1109/BTAS.2016.7791172

Cite this

Kim, S. T., Kim, D. H., & Ro, Y. M. (2016). Facial dynamic modelling using long short-term memory network: Analysis and application to face authentication. In IEEE 8th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2016 Article 7791172 (2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BTAS.2016.7791172

Kim, Seong Tae ; Kim, Dae Hoe ; Ro, Yong Man. / Facial dynamic modelling using long short-term memory network : Analysis and application to face authentication. IEEE 8th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2016. Institute of Electrical and Electronics Engineers Inc., 2016. (2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016).

@inproceedings{d30d1b245ef448afad8f3f7883ec71d5,

title = "Facial dynamic modelling using long short-term memory network: Analysis and application to face authentication",

abstract = "According to the supplementary information hypothesis in psychology, facial motion benefits the perception of identity for human. In this study, we propose a face authentication framework which exploits facial dynamics with appearance to effectively improve the authentication performance. In our face authentication scenario, users are guided to make smile expression and the identity behind smile dynamics has been utilized. In order to model the facial dynamics, the recurrent neural network with long short-term memory cells is adopted and the facial dynamics from onset to offset duration is encoded. Comparative experiment has showed that the combination of facial dynamic features with appearance features improves the accuracy of the face authentication system compared to conventional appearance features and spatio-temporal features by effectively capturing facial dynamic and appearance features.",

author = "Kim, \{Seong Tae\} and Kim, \{Dae Hoe\} and Ro, \{Yong Man\}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 8th IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2016 ; Conference date: 06-09-2016 Through 09-09-2016",

year = "2016",

month = dec,

day = "19",

doi = "10.1109/BTAS.2016.7791172",

language = "English",

series = "2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "IEEE 8th International Conference on Biometrics",

address = "United States",

}

Kim, ST, Kim, DH & Ro, YM 2016, Facial dynamic modelling using long short-term memory network: Analysis and application to face authentication. in IEEE 8th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2016., 7791172, 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016, Institute of Electrical and Electronics Engineers Inc., 8th IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2016, Niagara Falls, United States, 6/09/16. https://doi.org/10.1109/BTAS.2016.7791172

Facial dynamic modelling using long short-term memory network: Analysis and application to face authentication. / Kim, Seong Tae; Kim, Dae Hoe; Ro, Yong Man.
IEEE 8th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2016. Institute of Electrical and Electronics Engineers Inc., 2016. 7791172 (2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016).

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

TY - GEN

T1 - Facial dynamic modelling using long short-term memory network

T2 - 8th IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2016

AU - Kim, Seong Tae

AU - Kim, Dae Hoe

AU - Ro, Yong Man

PY - 2016/12/19

Y1 - 2016/12/19

N2 - According to the supplementary information hypothesis in psychology, facial motion benefits the perception of identity for human. In this study, we propose a face authentication framework which exploits facial dynamics with appearance to effectively improve the authentication performance. In our face authentication scenario, users are guided to make smile expression and the identity behind smile dynamics has been utilized. In order to model the facial dynamics, the recurrent neural network with long short-term memory cells is adopted and the facial dynamics from onset to offset duration is encoded. Comparative experiment has showed that the combination of facial dynamic features with appearance features improves the accuracy of the face authentication system compared to conventional appearance features and spatio-temporal features by effectively capturing facial dynamic and appearance features.

AB - According to the supplementary information hypothesis in psychology, facial motion benefits the perception of identity for human. In this study, we propose a face authentication framework which exploits facial dynamics with appearance to effectively improve the authentication performance. In our face authentication scenario, users are guided to make smile expression and the identity behind smile dynamics has been utilized. In order to model the facial dynamics, the recurrent neural network with long short-term memory cells is adopted and the facial dynamics from onset to offset duration is encoded. Comparative experiment has showed that the combination of facial dynamic features with appearance features improves the accuracy of the face authentication system compared to conventional appearance features and spatio-temporal features by effectively capturing facial dynamic and appearance features.

UR - https://www.scopus.com/pages/publications/85011299459

U2 - 10.1109/BTAS.2016.7791172

DO - 10.1109/BTAS.2016.7791172

M3 - Conference contribution

AN - SCOPUS:85011299459

T3 - 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016

BT - IEEE 8th International Conference on Biometrics

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 6 September 2016 through 9 September 2016

ER -

Kim ST, Kim DH, Ro YM. Facial dynamic modelling using long short-term memory network: Analysis and application to face authentication. In IEEE 8th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2016. Institute of Electrical and Electronics Engineers Inc. 2016. 7791172. (2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016). doi: 10.1109/BTAS.2016.7791172

Facial dynamic modelling using long short-term memory network: Analysis and application to face authentication

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this