Face recognition algorithm using collaborative sparse representation based on CNN features  

基于CNN特征的协同稀疏表示人脸识别算法

作　　者：ZHAO Shilin XU Chengjun LIU Changrong 赵世林;徐成俊;刘昌荣(兰州文理学院数字媒体学院,甘肃兰州730010;兰州交通大学自动化与电气工程学院,甘肃兰州730070)

机构地区：[1]School of Digital Media,Lanzhou University of Arts and Science,Lanzhou 730010,China [2]School of Automation and Electrical Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China

出　　处：《Journal of Measurement Science and Instrumentation》2025年第1期85-95,共11页测试科学与仪器(英文版)

基　　金：the financial support from Natural Science Foundation of Gansu Province(Nos.22JR5RA217,22JR5RA216);Lanzhou Science and Technology Program(No.2022-2-111);Lanzhou University of Arts and Sciences School Innovation Fund Project(No.XJ2022000103);Lanzhou College of Arts and Sciences 2023 Talent Cultivation Quality Improvement Project(No.2023-ZL-jxzz-03)。

摘　　要：Considering that the algorithm accuracy of the traditional sparse representation models is not high under the influence of multiple complex environmental factors,this study focuses on the improvement of feature extraction and model construction.Firstly,the convolutional neural network(CNN)features of the face are extracted by the trained deep learning network.Next,the steady-state and dynamic classifiers for face recognition are constructed based on the CNN features and Haar features respectively,with two-stage sparse representation introduced in the process of constructing the steady-state classifier and the feature templates with high reliability are dynamically selected as alternative templates from the sparse representation template dictionary constructed using the CNN features.Finally,the results of face recognition are given based on the classification results of the steady-state classifier and the dynamic classifier together.Based on this,the feature weights of the steady-state classifier template are adjusted in real time and the dictionary set is dynamically updated to reduce the probability of irrelevant features entering the dictionary set.The average recognition accuracy of this method is 94.45%on the CMU PIE face database and 96.58%on the AR face database,which is significantly improved compared with that of the traditional face recognition methods.针对传统稀疏表示模型在多种复杂环境因素影响下算法精度不高的问题,从特征提取和模型构建两方面加以改进。首先,利用训练好的深度学习网络提取人脸的卷积神经网络(Convolutional neural network,CNN)特征。其次,分别基于CNN特征和哈尔(Haar)特征构建人脸识别稳态和动态分类器:稳态分类器构建过程中引入两阶段稀疏表示,然后从CNN特征构建的稀疏表示模板字典集中动态选取可靠性高的特征模板作为备选模板。最后,基于稳态分类器和动态分类器的分类结果共同给出人脸识别结果,并根据识别结果实时调整稳态分类器模板特征权重,动态更新字典集,降低无关特征进入字典集的概率。实验结果表明,该方法在CMU PIE人脸库上的平均识别准确率为94.45%,在AR人脸库上的平均识别准确率为96.58%。相比传统人脸识别方法,其识别准确率显著提高。

关 键 词：sparse representation deep learning face recognition dictionary update feature extraction 

分 类 号：TP1[自动化与计算机技术—控制理论与控制工程]