Research Article
Subpattern Complete Two Dimensional Locality Preserving Principal Component Analysis and Its Application to Gait Recognition
@INPROCEEDINGS{10.1109/ChinaCom.2011.6158253, author={Xianye Ben and Shi An and Weixiao Meng and Ze Wang}, title={Subpattern Complete Two Dimensional Locality Preserving Principal Component Analysis and Its Application to Gait Recognition}, proceedings={6th International ICST Conference on Communications and Networking in China}, publisher={IEEE}, proceedings_a={CHINACOM}, year={2012}, month={3}, keywords={subpattern complete two dimensional locality preserving principal component analysis (spc2dlppca) two dimensional principal component analysis (2dpca) two dimensional locality preserving projections (2dlpp) gait recognition}, doi={10.1109/ChinaCom.2011.6158253} }- Xianye Ben
Shi An
Weixiao Meng
Ze Wang
Year: 2012
Subpattern Complete Two Dimensional Locality Preserving Principal Component Analysis and Its Application to Gait Recognition
CHINACOM
IEEE
DOI: 10.1109/ChinaCom.2011.6158253
Abstract
In this paper, a novel algorithm for feature extraction ——Subpattern Complete Two Dimensional Locality Preserving Principal Component Analysis (SpC2DLPPCA) is proposed. The improved SpC2DLPPCA algorithm over C2DLPPCA and Subpattern Complete Two Dimensional Principal Component Analysis (SpC2DPCA) methods benefits greatly to three points: (1) SpC2DLPPCA can overcome a failing that larger dimension matrix may bring about more consuming time on computing its eigenvalues and eigenvectors. (2) SpC2DLPPCA can extract local information to implement recognition. (3)The idea of subblock is introduced into Two Dimensional Principal Component Analysis (2DPCA) and Two Dimensional Locality Preserving projection (2DLPP), so SpC2DLPPCA can preserve local neighbor graph structure and compact the expression of features. Finally, experiments on the CASIA(B) gait database show that SpC2DLPPCA has higher recognition accuracies than C2DLPPCA and SpC2DPCA.