TY - JOUR
T1 - A Double-Deep Spatio-Angular Learning Framework for Light Field based Face Recognition
AU - Sepas-Moghaddam, Alireza
AU - Haque, Mohammad Ahsanul
AU - Correia, Paulo Lobato
AU - Nasrollahi, Kamal
AU - Moeslund, Thomas B.
AU - Pereira, Fernando
PY - 2020
Y1 - 2020
N2 - Face recognition has attracted increasing attention due to its wide range of applications, but it is still challenging when facing large variations in the biometric data characteristics. Lenslet light field cameras have recently come into prominence to capture rich spatio-angular information, thus offering new possibilities for advanced biometric recognition systems. This paper proposes a double-deep spatio-angular learning framework for light field based face recognition, which is able to model both the intra-view/spatial and inter-view/angular information using two deep networks in sequence. This is a novel recognition framework that has never been proposed in the literature for face recognition or any other visual recognition task. The proposed double-deep learning framework includes a long short-term memory (LSTM) recurrent network whose inputs are VGG-Face descriptions, computed using a VGG- 16 convolutional neural network (CNN). The VGG-Face spatial descriptions are extracted from a selected set of 2D sub-aperture (SA) images rendered from the light field image, corresponding to different observation angles. A sequence of the VGG-Face spatial descriptions is then be analysed by the LSTM network. A comprehensive set of experiments has been conducted using the IST-EURECOM light field face database, addressing varied and challenging recognition tasks. Results show that the proposed framework achieves superior face recognition performance when compared to the state-of-the-art.
AB - Face recognition has attracted increasing attention due to its wide range of applications, but it is still challenging when facing large variations in the biometric data characteristics. Lenslet light field cameras have recently come into prominence to capture rich spatio-angular information, thus offering new possibilities for advanced biometric recognition systems. This paper proposes a double-deep spatio-angular learning framework for light field based face recognition, which is able to model both the intra-view/spatial and inter-view/angular information using two deep networks in sequence. This is a novel recognition framework that has never been proposed in the literature for face recognition or any other visual recognition task. The proposed double-deep learning framework includes a long short-term memory (LSTM) recurrent network whose inputs are VGG-Face descriptions, computed using a VGG- 16 convolutional neural network (CNN). The VGG-Face spatial descriptions are extracted from a selected set of 2D sub-aperture (SA) images rendered from the light field image, corresponding to different observation angles. A sequence of the VGG-Face spatial descriptions is then be analysed by the LSTM network. A comprehensive set of experiments has been conducted using the IST-EURECOM light field face database, addressing varied and challenging recognition tasks. Results show that the proposed framework achieves superior face recognition performance when compared to the state-of-the-art.
KW - Face Recognition
KW - Lenslet Light Field Imaging
KW - Spatio-Angular Information
KW - Deep Learning
KW - VGG-Face Descriptor
KW - VGG-Very-Deep-16 CNN
KW - Long Short-Term Memory Network
UR - http://www.scopus.com/inward/record.url?scp=85097726674&partnerID=8YFLogxK
U2 - 10.1109/TCSVT.2019.2916669
DO - 10.1109/TCSVT.2019.2916669
M3 - Journal article
SN - 1051-8215
VL - 30
SP - 4496
EP - 4512
JO - I E E E Transactions on Circuits and Systems for Video Technology
JF - I E E E Transactions on Circuits and Systems for Video Technology
IS - 12
M1 - 8713930
ER -