TY - GEN
T1 - Low-Resolution Face Recognition Based on Identity-Preserved Face Hallucination
AU - Lai, Shun Cheung
AU - He, Chen Hang
AU - Lam, Kin Man
PY - 2019/9
Y1 - 2019/9
N2 - The state-of-the-art Convolutional Neural Network (CNN)-based methods have achieved promising recognition performance on human face images. However, the accuracy cannot be retained when face images are at very low resolution (LR). In this paper, we propose a novel loss function, called identity-preserved loss, which combines with the image-content loss to jointly supervise CNNs, for performing face hallucination and recognition simultaneously. Therefore, the trained network is able to perform face hallucination and identity preservation, even if the query face is of very low resolution. More importantly, experimental results show that our proposed method can preserve the identities for the LR images from unknown subjects, who are not included in the training set. The source code of our proposed method is available at: https://github.com/johnnysclai/SR-LRFR.
AB - The state-of-the-art Convolutional Neural Network (CNN)-based methods have achieved promising recognition performance on human face images. However, the accuracy cannot be retained when face images are at very low resolution (LR). In this paper, we propose a novel loss function, called identity-preserved loss, which combines with the image-content loss to jointly supervise CNNs, for performing face hallucination and recognition simultaneously. Therefore, the trained network is able to perform face hallucination and identity preservation, even if the query face is of very low resolution. More importantly, experimental results show that our proposed method can preserve the identities for the LR images from unknown subjects, who are not included in the training set. The source code of our proposed method is available at: https://github.com/johnnysclai/SR-LRFR.
KW - deep learning
KW - Face hallucination
KW - identity-preserved loss
KW - low-resolution face recognition
UR - http://www.scopus.com/inward/record.url?scp=85076814515&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2019.8803782
DO - 10.1109/ICIP.2019.8803782
M3 - Conference article published in proceeding or book
AN - SCOPUS:85076814515
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 1173
EP - 1177
BT - 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
PB - IEEE Computer Society
T2 - 26th IEEE International Conference on Image Processing, ICIP 2019
Y2 - 22 September 2019 through 25 September 2019
ER -