TY - JOUR
T1 - Generative face inpainting hashing for occluded face retrieval
AU - YANG, Yuxiang
AU - TIAN, Xing
AU - NG, Wing W. Y.
AU - WANG, Ran
AU - GAO, Ying
AU - KWONG, Sam
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
PY - 2023/5
Y1 - 2023/5
N2 - COVID-19 has resulted in a significant impact on individual lives, bringing a unique challenge for face retrieval under occlusion. In this paper, an occluded face retrieval method which consists of generator, discriminator, and deep hashing retrieval network is proposed for face retrieval in a large-scale face image dataset under variety of occlusion situations. In the proposed method, occluded face images are firstly reconstructed using a face inpainting model, in which the adversarial loss, reconstruction loss and hash bits loss are combined for training. With the trained model, hash codes of real face images and corresponding reconstructed face images are aimed to be as similar as possible. Then, a deep hashing retrieval network is used to generate compact similarity-preserving hashing codes using reconstructed face images for a better retrieval performance. Experimental results show that the proposed method can successfully generate the reconstructed face images under occlusion. Meanwhile, the proposed deep hashing retrieval network achieves better retrieval performance for occluded face retrieval than existing state-of-the-art deep hashing retrieval methods.
AB - COVID-19 has resulted in a significant impact on individual lives, bringing a unique challenge for face retrieval under occlusion. In this paper, an occluded face retrieval method which consists of generator, discriminator, and deep hashing retrieval network is proposed for face retrieval in a large-scale face image dataset under variety of occlusion situations. In the proposed method, occluded face images are firstly reconstructed using a face inpainting model, in which the adversarial loss, reconstruction loss and hash bits loss are combined for training. With the trained model, hash codes of real face images and corresponding reconstructed face images are aimed to be as similar as possible. Then, a deep hashing retrieval network is used to generate compact similarity-preserving hashing codes using reconstructed face images for a better retrieval performance. Experimental results show that the proposed method can successfully generate the reconstructed face images under occlusion. Meanwhile, the proposed deep hashing retrieval network achieves better retrieval performance for occluded face retrieval than existing state-of-the-art deep hashing retrieval methods.
KW - Face retrieval
KW - Generative adversarial
KW - Inpainting
KW - Occlusion
UR - http://www.scopus.com/inward/record.url?scp=85143205146&partnerID=8YFLogxK
U2 - 10.1007/s13042-022-01723-3
DO - 10.1007/s13042-022-01723-3
M3 - Journal Article (refereed)
C2 - 36474954
SN - 1868-8071
VL - 14
SP - 1725
EP - 1738
JO - International Journal of Machine Learning and Cybernetics
JF - International Journal of Machine Learning and Cybernetics
IS - 5
ER -