TY - JOUR
T1 - Robust tensor analysis with L1-norm
AU - Pang, Yanwei
AU - Li, Xuelong
AU - Yuan, Yuan
PY - 2010/2
Y1 - 2010/2
N2 - Tensor analysis plays an important role in modern image and vision computing problems. Most of the existing tensor analysis approaches are based on the Frobenius norm, which makes them sensitive to outliers. In this paper, we propose L1-norm-based tensor analysis (TPCA-L1), which is robust to outliers. Experimental results upon face and other datasets demonstrate the advantages of the proposed approach.
AB - Tensor analysis plays an important role in modern image and vision computing problems. Most of the existing tensor analysis approaches are based on the Frobenius norm, which makes them sensitive to outliers. In this paper, we propose L1-norm-based tensor analysis (TPCA-L1), which is robust to outliers. Experimental results upon face and other datasets demonstrate the advantages of the proposed approach.
KW - L1-norm
KW - outlier
KW - tensor analysis
UR - http://www.scopus.com/inward/record.url?scp=76649139002&partnerID=8YFLogxK
UR - http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=4812108
U2 - 10.1109/TCSVT.2009.2020337
DO - 10.1109/TCSVT.2009.2020337
M3 - Article
AN - SCOPUS:76649139002
SN - 1051-8215
VL - 20
SP - 172
EP - 178
JO - IEEE Transactions on Circuits and Systems For Video Technology
JF - IEEE Transactions on Circuits and Systems For Video Technology
IS - 2
ER -