TY - GEN
T1 - The CASIA NIR-VIS 2.0 face database
AU - Li, Stan Z.
AU - Yi, Dong
AU - Lei, Zhen
AU - Liao, Shengcai
PY - 2013
Y1 - 2013
N2 - In recent years, heterogeneous face biometrics has attracted more attentions in the face recognition community. After published in 2009, the HFB database has been applied by tens of research groups and widely used for Near infrared vs. Visible light (NIR-VIS) face recognition. Despite its success the HFB database has two disadvantages: a limited number of subjects, lacking specific evaluation protocols. To address these issues we collected the NIRVIS 2.0 database. It contains 725 subjects, imaged by VIS and NIR cameras in four recording sessions. Because the 3D modality in the HFB database was less used in the literature, we don't consider it in the current version. In this paper, we describe the composition of the database, evaluation protocols and present the baseline performance of PCA on the database. Moreover, two interesting tricks, the facial symmetry and heterogeneous component analysis (HCA) are also introduced to improve the performance.
AB - In recent years, heterogeneous face biometrics has attracted more attentions in the face recognition community. After published in 2009, the HFB database has been applied by tens of research groups and widely used for Near infrared vs. Visible light (NIR-VIS) face recognition. Despite its success the HFB database has two disadvantages: a limited number of subjects, lacking specific evaluation protocols. To address these issues we collected the NIRVIS 2.0 database. It contains 725 subjects, imaged by VIS and NIR cameras in four recording sessions. Because the 3D modality in the HFB database was less used in the literature, we don't consider it in the current version. In this paper, we describe the composition of the database, evaluation protocols and present the baseline performance of PCA on the database. Moreover, two interesting tricks, the facial symmetry and heterogeneous component analysis (HCA) are also introduced to improve the performance.
UR - http://www.scopus.com/inward/record.url?scp=84884964806&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84884964806&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2013.59
DO - 10.1109/CVPRW.2013.59
M3 - Conference contribution
AN - SCOPUS:84884964806
SN - 9780769549903
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 348
EP - 353
BT - Proceedings - 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2013
T2 - 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2013
Y2 - 23 June 2013 through 28 June 2013
ER -