Learning features from covariance matrix of gabor wavelet for face recognition under adverse conditions

作者：

Highlights：

• We proposed LCMoG-CNN for face recognition under adverse conditions.

• LCMoG-CNN uses CNN to learn the face features from Gabor wavelet subbands.

• WPCA is used to learning the discriminative features from fused covariance matrix.

摘要

•We proposed LCMoG-CNN for face recognition under adverse conditions.•LCMoG-CNN uses CNN to learn the face features from Gabor wavelet subbands.•WPCA is used to learning the discriminative features from fused covariance matrix.

论文关键词：Face recognition,Gabor wavelet,Covariance matrix,Convolutional neural network

论文评审过程：Received 26 September 2020, Revised 28 May 2021, Accepted 29 May 2021, Available online 4 June 2021, Version of Record 17 June 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108085