TY - GEN
T1 - SeLENet
T2 - 2019 International Conference on Biometrics, ICB 2019
AU - Le, Ha A.
AU - Kakadiaris, Ioannis A.
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - Facial recognition is becoming a standard feature on new smartphones. However, the face unlocking feature of devices using regular 2D camera sensors exhibits poor performance in low light environments. In this paper, we propose a semi-supervised low light face enhancement method to improve face verification performance on low light face images. The proposed method is a network with two components: decomposition and reconstruction. The decomposition component splits an input low light face image into face normals and face albedo, while the reconstruction component enhances and reconstructs the lighting condition of the input image using the spherical harmonic lighting coefficients of a direct ambient white light. The network is trained in a semi-supervised manner using both labeled synthetic data and unlabeled real data. Qualitative results demonstrate that the proposed method produces more realistic images than the state-of-the-art low light enhancement algorithms. Quantitative experiments confirm the effectiveness of our low light face enhancement method for face verification. By applying the proposed method, the gap of verification accuracy between extreme low light and neutral light face images is reduced from approximately 3% to 0.5%.
AB - Facial recognition is becoming a standard feature on new smartphones. However, the face unlocking feature of devices using regular 2D camera sensors exhibits poor performance in low light environments. In this paper, we propose a semi-supervised low light face enhancement method to improve face verification performance on low light face images. The proposed method is a network with two components: decomposition and reconstruction. The decomposition component splits an input low light face image into face normals and face albedo, while the reconstruction component enhances and reconstructs the lighting condition of the input image using the spherical harmonic lighting coefficients of a direct ambient white light. The network is trained in a semi-supervised manner using both labeled synthetic data and unlabeled real data. Qualitative results demonstrate that the proposed method produces more realistic images than the state-of-the-art low light enhancement algorithms. Quantitative experiments confirm the effectiveness of our low light face enhancement method for face verification. By applying the proposed method, the gap of verification accuracy between extreme low light and neutral light face images is reduced from approximately 3% to 0.5%.
UR - http://www.scopus.com/inward/record.url?scp=85081055371&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85081055371&partnerID=8YFLogxK
U2 - 10.1109/ICB45273.2019.8987344
DO - 10.1109/ICB45273.2019.8987344
M3 - Conference contribution
AN - SCOPUS:85081055371
T3 - 2019 International Conference on Biometrics, ICB 2019
BT - 2019 International Conference on Biometrics, ICB 2019
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 4 June 2019 through 7 June 2019
ER -