In this paper, Nearest Regularized Subspace (NRS) is introduced into the field of Face Recognition to address the problems of multicollinearity and lack of selectivity of LRC classifiers over data. The NRS-LDA classifier is also constructed through the LDA construction Tikhonov matrix. At the same time, the advantages and disadvantages of classifiers such as LRC, CRC-Pre, NRS, and NRS-LDA are elaborated through experiments and the reasons for its generation are analyzed. The Adaptive Nearest Regularized Subspace (ANRS) classifier is proposed by combining the advantages of LRC and NRS.
Face Recognition Based on Adaptive Nearest Regularized Subspace
2022-10-12
2055048 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Joint regularized nearest points for image set based face recognition
British Library Online Contents | 2017
|Joint regularized nearest points for image set based face recognition
British Library Online Contents | 2017
|Unified Subspace Analysis for Face Recognition
British Library Conference Proceedings | 2003
|Random Sampling for Subspace Face Recognition
British Library Online Contents | 2006
|Nonparametric subspace analysis for face recognition
IEEE | 2005
|