高技术通讯2025，Vol.35Issue(2)：134-144,11.DOI:10.3772/j.issn.1002-0470.2025.02.003
基于扩展的PCANet的有遮挡人脸识别方法
Occluded face recognition via extended PCANet
摘要
Abstract
To solve the problem of occluded face recognition,an extended principal component analysis network(xPC A-Net)model is proposed by combining the existing convolutional neural networks(CNN)model with PCANet.In order to effectively eliminate the influence caused by facial occlusions,it is usually necessary to make full use of the low-level features of the network and build rich features.Two disadvantages of PCANet are:(1)due to the orthog-onality constraint,the filters of each convolution layer are highly similar,which reduces the diversity of the filter re-sponse;(2)to get the pattern maps,the feature maps are binarized,and the encoding method with a large stride is adopted,so that many useful features are discarded.In order to make PCANet better fit into the existing CNN models,two dense connections are introduced into the PCANet model:(1)the dense connections introduced be-tween convolutional layers are used to make full use of the features extracted by the low-level convolutional layers,and reduce the similarity of filters between convolutional layers as much as possible;(2)in the pattern-map enco-ding stage,weighted dense encoding is introduced to make full use of the features produced by the convolutional layers to generate more pattern maps.These two dense connections enhance the dimension of the final output of PCANet histogram features and generate richer features.Experiments on face datasets(AR face dataset)with real occlusions acquired in the controlled environment,on face datasets(LFW and CFP)with synthetic occlusions ac-quired in the uncontrolled environment,and on face datasets(MFR2 and PKU-Masked Face)with real occlusions acquired in the uncontrolled environment show that,compared with existing methods the proposed xPCANet can ef-fectively deal with physical occlusions and illumination-caused occlusions,and can also be an effective supplement to the cutting-edge methods to improve their robustness against occlusions.关键词
有遮挡人脸识别/主成分分析模型/稠密连接/稠密编码/滤波器多样性Key words
face recognition with occlusion/principal component analysis network(PCANet)/dense connec-tions/dense encoding/filter diversity引用本文复制引用
秦娥,卢天宇,李卫锋,刘银伟,朱娅妮,李小薪..基于扩展的PCANet的有遮挡人脸识别方法[J].高技术通讯,2025,35(2):134-144,11.基金项目
国家自然科学基金(62271448)和浙江省自然科学基金(LGF22F020027)资助项目. （62271448）
