TY - GEN
T1 - Pore-scale facial features matching under 3D morphable model constraint
AU - Zeng, Xianxian
AU - Li, Dong
AU - Zhang, Yun
AU - Lam, Kin Man
PY - 2017/1/1
Y1 - 2017/1/1
N2 - 2017. Similar to irises and fingerprints, pore-scale facial features are effective features for distinguishing human identities. Recently, the local feature extraction based on deep network architecture has been proposed, which needs a large dataset for training. However, there are no large databases for pore-scale facial features. Actually, it is hard to set up a large pore-scale facial-feature dataset, because the images from existing high-resolution face databases are uncalibrated and nonsynchronous, and human faces are nonrigid. To solve this problem, we propose a method to establish a large pore-to-pore correspondence dataset. We adopt Pore Scale-Invariant Feature Transform (PSIFT) to extract pore-scale facial features from face images, and use 3D Dense Face Alignment (3DDFA) to obtain a fitted 3D morphable model, which is constrained by matching keypoints. From our experiments, a large pore-to-pore correspondence dataset, including 17,136 classes of matched pore-keypoint pairs, is established.
AB - 2017. Similar to irises and fingerprints, pore-scale facial features are effective features for distinguishing human identities. Recently, the local feature extraction based on deep network architecture has been proposed, which needs a large dataset for training. However, there are no large databases for pore-scale facial features. Actually, it is hard to set up a large pore-scale facial-feature dataset, because the images from existing high-resolution face databases are uncalibrated and nonsynchronous, and human faces are nonrigid. To solve this problem, we propose a method to establish a large pore-to-pore correspondence dataset. We adopt Pore Scale-Invariant Feature Transform (PSIFT) to extract pore-scale facial features from face images, and use 3D Dense Face Alignment (3DDFA) to obtain a fitted 3D morphable model, which is constrained by matching keypoints. From our experiments, a large pore-to-pore correspondence dataset, including 17,136 classes of matched pore-keypoint pairs, is established.
KW - 3D morphable model
KW - 3DDFA
KW - Dataset
KW - Pore-scale facial features
KW - PSIFT
UR - http://www.scopus.com/inward/record.url?scp=85038004108&partnerID=8YFLogxK
U2 - 10.1007/978-981-10-7302-1_3
DO - 10.1007/978-981-10-7302-1_3
M3 - Conference article published in proceeding or book
SN - 9789811073014
T3 - Communications in Computer and Information Science
SP - 29
EP - 39
BT - Computer Vision - 2nd CCF Chinese Conference, CCCV 2017, Proceedings
PB - Springer Verlag
T2 - 2nd Chinese Conference on Computer Vision, CCCV 2017
Y2 - 11 October 2017 through 14 October 2017
ER -