Changes in Facial Expression as Biometric: A Database and Benchmarks of Identification

Rain Eric Haamer, Kaustubh Kulkarni, Nasrin Imanpour, Mohammad Ahsanul Haque, Egils Avots, Michelle Breisch, Kamal Nasrollahi, Sergio Escalera Guerrero, Cagri Ozcinar, Xavier Baro, Ahmad Reza Naghsh-Nilchi, Thomas B. Moeslund, Gholamreza Anbarjafari

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

5 Citationer (Scopus)
110 Downloads (Pure)

Resumé

Facial dynamics can be considered as unique signatures for discrimination between people. These have started to become important topic since many devices have the possibility of unlocking using face recognition or verification. In this work, we evaluate the efficacy of the transition frames of video in emotion as compared to the peak emotion frames for identification. For experiments with transition frames we extract features from each frame of the video from a fine-tuned VGG-Face Convolutional Neural Network (CNN) and geometric features from facial landmark points. To model the temporal context of the transition frames we train a Long-Short Term Memory (LSTM) on the geometric and the CNN features. Furthermore, we employ two fusion strategies: first, an early fusion, in which the geometric and the CNN features are stacked and fed to the LSTM. Second, a late fusion, in which the prediction of the LSTMs, trained
independently on the two features, are stacked and used with a Support Vector Machine (SVM). Experimental results show that the late fusion strategy gives the best results and the transition frames give better identification results as compared to the peak emotion frames.
OriginalsprogEngelsk
Titel13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018)
Antal sider8
ForlagIEEE
Publikationsdato2018
Sider621-628
Artikelnummer8373891
ISBN (Trykt)978-1-5386-2336-7
ISBN (Elektronisk)978-1-5386-2335-0
DOI
StatusUdgivet - 2018
BegivenhedIEEE Conf. on Automatic Face and Gesture Recognition Workshops - X'ian, Kina
Varighed: 15 maj 201819 maj 2018
https://fg2018.cse.sc.edu

Konference

KonferenceIEEE Conf. on Automatic Face and Gesture Recognition Workshops
LandKina
ByX'ian
Periode15/05/201819/05/2018
Internetadresse

Fingeraftryk

Biometrics
Fusion reactions
Neural networks
Face recognition
Support vector machines
Experiments
Long short-term memory

Emneord

    Citer dette

    Haamer, R. E., Kulkarni, K., Imanpour, N., Haque, M. A., Avots, E., Breisch, M., ... Anbarjafari, G. (2018). Changes in Facial Expression as Biometric: A Database and Benchmarks of Identification. I 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018) (s. 621-628). [8373891] IEEE. https://doi.org/10.1109/FG.2018.00098
    Haamer, Rain Eric ; Kulkarni, Kaustubh ; Imanpour, Nasrin ; Haque, Mohammad Ahsanul ; Avots, Egils ; Breisch, Michelle ; Nasrollahi, Kamal ; Guerrero, Sergio Escalera ; Ozcinar, Cagri ; Baro, Xavier ; Naghsh-Nilchi, Ahmad Reza ; Moeslund, Thomas B. ; Anbarjafari, Gholamreza . / Changes in Facial Expression as Biometric : A Database and Benchmarks of Identification. 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018). IEEE, 2018. s. 621-628
    @inproceedings{a81113492dac49ef85f80d0158a816bd,
    title = "Changes in Facial Expression as Biometric: A Database and Benchmarks of Identification",
    abstract = "Facial dynamics can be considered as unique signatures for discrimination between people. These have started to become important topic since many devices have the possibility of unlocking using face recognition or verification. In this work, we evaluate the efficacy of the transition frames of video in emotion as compared to the peak emotion frames for identification. For experiments with transition frames we extract features from each frame of the video from a fine-tuned VGG-Face Convolutional Neural Network (CNN) and geometric features from facial landmark points. To model the temporal context of the transition frames we train a Long-Short Term Memory (LSTM) on the geometric and the CNN features. Furthermore, we employ two fusion strategies: first, an early fusion, in which the geometric and the CNN features are stacked and fed to the LSTM. Second, a late fusion, in which the prediction of the LSTMs, trainedindependently on the two features, are stacked and used with a Support Vector Machine (SVM). Experimental results show that the late fusion strategy gives the best results and the transition frames give better identification results as compared to the peak emotion frames.",
    keywords = "Facial expression, biometric, database, benchmark, Deep Learning, CNN, LSTM, Multimodal, Spatio-temporal, SVM",
    author = "Haamer, {Rain Eric} and Kaustubh Kulkarni and Nasrin Imanpour and Haque, {Mohammad Ahsanul} and Egils Avots and Michelle Breisch and Kamal Nasrollahi and Guerrero, {Sergio Escalera} and Cagri Ozcinar and Xavier Baro and Naghsh-Nilchi, {Ahmad Reza} and Moeslund, {Thomas B.} and Gholamreza Anbarjafari",
    year = "2018",
    doi = "10.1109/FG.2018.00098",
    language = "English",
    isbn = "978-1-5386-2336-7",
    pages = "621--628",
    booktitle = "13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018)",
    publisher = "IEEE",
    address = "United States",

    }

    Haamer, RE, Kulkarni, K, Imanpour, N, Haque, MA, Avots, E, Breisch, M, Nasrollahi, K, Guerrero, SE, Ozcinar, C, Baro, X, Naghsh-Nilchi, AR, Moeslund, TB & Anbarjafari, G 2018, Changes in Facial Expression as Biometric: A Database and Benchmarks of Identification. i 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018)., 8373891, IEEE, s. 621-628, X'ian, Kina, 15/05/2018. https://doi.org/10.1109/FG.2018.00098

    Changes in Facial Expression as Biometric : A Database and Benchmarks of Identification. / Haamer, Rain Eric; Kulkarni, Kaustubh; Imanpour, Nasrin; Haque, Mohammad Ahsanul; Avots, Egils; Breisch, Michelle; Nasrollahi, Kamal; Guerrero, Sergio Escalera; Ozcinar, Cagri; Baro, Xavier; Naghsh-Nilchi, Ahmad Reza; Moeslund, Thomas B.; Anbarjafari, Gholamreza .

    13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018). IEEE, 2018. s. 621-628 8373891.

    Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

    TY - GEN

    T1 - Changes in Facial Expression as Biometric

    T2 - A Database and Benchmarks of Identification

    AU - Haamer, Rain Eric

    AU - Kulkarni, Kaustubh

    AU - Imanpour, Nasrin

    AU - Haque, Mohammad Ahsanul

    AU - Avots, Egils

    AU - Breisch, Michelle

    AU - Nasrollahi, Kamal

    AU - Guerrero, Sergio Escalera

    AU - Ozcinar, Cagri

    AU - Baro, Xavier

    AU - Naghsh-Nilchi, Ahmad Reza

    AU - Moeslund, Thomas B.

    AU - Anbarjafari, Gholamreza

    PY - 2018

    Y1 - 2018

    N2 - Facial dynamics can be considered as unique signatures for discrimination between people. These have started to become important topic since many devices have the possibility of unlocking using face recognition or verification. In this work, we evaluate the efficacy of the transition frames of video in emotion as compared to the peak emotion frames for identification. For experiments with transition frames we extract features from each frame of the video from a fine-tuned VGG-Face Convolutional Neural Network (CNN) and geometric features from facial landmark points. To model the temporal context of the transition frames we train a Long-Short Term Memory (LSTM) on the geometric and the CNN features. Furthermore, we employ two fusion strategies: first, an early fusion, in which the geometric and the CNN features are stacked and fed to the LSTM. Second, a late fusion, in which the prediction of the LSTMs, trainedindependently on the two features, are stacked and used with a Support Vector Machine (SVM). Experimental results show that the late fusion strategy gives the best results and the transition frames give better identification results as compared to the peak emotion frames.

    AB - Facial dynamics can be considered as unique signatures for discrimination between people. These have started to become important topic since many devices have the possibility of unlocking using face recognition or verification. In this work, we evaluate the efficacy of the transition frames of video in emotion as compared to the peak emotion frames for identification. For experiments with transition frames we extract features from each frame of the video from a fine-tuned VGG-Face Convolutional Neural Network (CNN) and geometric features from facial landmark points. To model the temporal context of the transition frames we train a Long-Short Term Memory (LSTM) on the geometric and the CNN features. Furthermore, we employ two fusion strategies: first, an early fusion, in which the geometric and the CNN features are stacked and fed to the LSTM. Second, a late fusion, in which the prediction of the LSTMs, trainedindependently on the two features, are stacked and used with a Support Vector Machine (SVM). Experimental results show that the late fusion strategy gives the best results and the transition frames give better identification results as compared to the peak emotion frames.

    KW - Facial expression

    KW - biometric

    KW - database

    KW - benchmark

    KW - Deep Learning

    KW - CNN

    KW - LSTM

    KW - Multimodal

    KW - Spatio-temporal

    KW - SVM

    U2 - 10.1109/FG.2018.00098

    DO - 10.1109/FG.2018.00098

    M3 - Article in proceeding

    SN - 978-1-5386-2336-7

    SP - 621

    EP - 628

    BT - 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018)

    PB - IEEE

    ER -

    Haamer RE, Kulkarni K, Imanpour N, Haque MA, Avots E, Breisch M et al. Changes in Facial Expression as Biometric: A Database and Benchmarks of Identification. I 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018). IEEE. 2018. s. 621-628. 8373891 https://doi.org/10.1109/FG.2018.00098