Face Recognition Based on Adaptive Nearest Regularized Subspace
Zhenyue Zhang, Donghai Zhao · 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology (ICCASIT) · 2022
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.