TY - JOUR
T1 - Block linear discriminant analysis for visual tensor objects with frequency or time information
AU - Li, Xutao
AU - Ng, Michael K.
AU - Ye, Yunming
AU - Wang, Eric Ke
AU - Xu, Xiaofei
N1 - Funding Information:
The research was supported in part by NSFC under Grant Nos. 61602132and 61572158, and Shenzhen Science and Technology Program under Grant Nos. JCYJ20160330163900579 and JSGG20150512145714247, and by HKRGC GRF Grant Nos. 202013 and 12302715, HKBU FRG2/14-15/087, HKBU12306616 and HKBU12302715.
PY - 2017/11
Y1 - 2017/11
N2 - Recently, due to the advancement of acquisition techniques, visual tensor data have been accumulated in a great variety of engineering fields, e.g., biometrics, neuroscience, surveillance and remote sensing. How to analyze and learn with such tensor objects thus becomes an important and growing interest in machine learning community. In this paper, we propose a block linear discriminant analysis (BLDA) algorithm to extract features for visual tensor objects such as multichannel/hyperspectral face images or human gait videos. Taking the inherent characteristic of such tensor data into account, we unfold tensor objects according to their spatial information and frequency/time information, and represent them in a block matrix form. As a result, the block form between-class and within-class scatter matrices are constructed, and a related block eigen-decomposition is solved to extract features for classification. Comprehensive experiments have been carried out to test the effectiveness of the proposed method, and the results show that BLDA outperforms existing algorithms like DATER, 2DLDA, GTDA, UMLDA, STDA and MPCA for visual tensor object analysis.
AB - Recently, due to the advancement of acquisition techniques, visual tensor data have been accumulated in a great variety of engineering fields, e.g., biometrics, neuroscience, surveillance and remote sensing. How to analyze and learn with such tensor objects thus becomes an important and growing interest in machine learning community. In this paper, we propose a block linear discriminant analysis (BLDA) algorithm to extract features for visual tensor objects such as multichannel/hyperspectral face images or human gait videos. Taking the inherent characteristic of such tensor data into account, we unfold tensor objects according to their spatial information and frequency/time information, and represent them in a block matrix form. As a result, the block form between-class and within-class scatter matrices are constructed, and a related block eigen-decomposition is solved to extract features for classification. Comprehensive experiments have been carried out to test the effectiveness of the proposed method, and the results show that BLDA outperforms existing algorithms like DATER, 2DLDA, GTDA, UMLDA, STDA and MPCA for visual tensor object analysis.
KW - Between-class scatter
KW - Discriminant analysis
KW - Gait recognition
KW - Hyperspectral face recognition
KW - Visual tensors
KW - Within-class scatter
UR - http://www.scopus.com/inward/record.url?scp=85026915794&partnerID=8YFLogxK
U2 - 10.1016/j.jvcir.2017.08.004
DO - 10.1016/j.jvcir.2017.08.004
M3 - Journal article
AN - SCOPUS:85026915794
SN - 1047-3203
VL - 49
SP - 38
EP - 46
JO - Journal of Visual Communication and Image Representation
JF - Journal of Visual Communication and Image Representation
ER -