Nonparametric Discriminant Analysis for Face Recognition
Publication in refereed journal


摘要In this paper, we develop a new framework for face recognition based on nonparametric discriminant analysis (NDA) and multiclassifier integration. Traditional LDA-based methods suffer a fundamental limitation originating from the parametric nature of scatter matrices, which are based on the Gaussian distribution assumption. The performance of these methods notably degrades when the actual distribution is non-Gaussian. To address this problem, we propose a new formulation of scatter matrices to extend the two-class NDA to multiclass cases. Then, in order to exploit the discriminant information in both the principal space and the null space of the intraclass scatter matrix, we develop two improved multiclass NDA-based algorithms (NSA and NFA) with each one having two complementary methods that are based on the principal space and the null space of the intraclass scatter matrix, respectively. Comparing to the NSA, the NFA is more effective in the utilization of the classification boundary information. In order to exploit the complementary nature of the two kinds of NFA (PNFA and NNFA), we finally develop a dual NFA-based multiclassifier fusion framework by employing the overcomplete Gabor representation for face images to boost the recognition performance. We show the improvements of the developed new algorithms over the traditional subspace methods through comparative experiments on two challenging face databases, the Purdue AR database and the XM2VTS database.
著者Li ZF, Lin DH, Tang XO
期刊名稱IEEE Transactions on Pattern Analysis and Machine Intelligence
出版社Institute of Electrical and Electronics Engineers (IEEE)
頁次755 - 761
關鍵詞classifier design and evaluation; Face recognition; multiclassifier fusion; nonparametric discriminant analysis (NDA)
Web of Science 學科類別Computer Science; Computer Science, Artificial Intelligence; COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE; Engineering; Engineering, Electrical & Electronic; ENGINEERING, ELECTRICAL & ELECTRONIC

上次更新時間 2021-14-01 於 23:54