鲁棒可预测判别字典学习人脸识别方法  

Robust discriminative K-SVD network for face recognition

作　　者：张健 米建勋[1,2] Zhang Jian;Mi Jianxun(School of Computer Science&Technology,Chongqing University of Posts&Telecommunications,Chongqing 400065,China;Chongqing Key Laboratory of Image Cognition,Chongqing University of Posts&Telecommunications,Chongqing 400065,China)

机构地区：[1]重庆邮电大学计算机科学与技术学院,重庆400065 [2]重庆邮电大学图像认知重庆市重点实验室,重庆400065

出　　处：《计算机应用研究》2021年第4期1245-1249,共5页Application Research of Computers

基　　金：重庆市自然科学基金资助项目(cstc2018jcyjAX0532);国家自然科学基金资助项目(61906024)。

摘　　要：提出一种可预测判别K-SVD网络模型(DKSVDN)并用于人脸识别问题。该模型构造了一种新颖的字典结构,包含类别标签字典和描述字典,以兼顾判别和重构性能。相应的稀疏编码向量由标签编码向量和描述编码向量组成。针对样本稀疏编码时间效率低的问题,利用预测神经网络与判别字典学习模型协同训练的方法来加速预测稀疏编码。此外,针对DKSVDN还特别引入一种拟梦境的训练方法用于提升模型在训练集多样性不足时的鲁棒性。通过在主流人脸数据集上的对比实验证明了该模型的优良性能。This paper presented a novel discriminative K-SVD network(DKSVDN)for face recognition.It embedded discriminative information into traditional K-SVD algorithm by special design of dictionary as well as sparse representation coefficients on the dictionary.The dictionary consisted of label specific atoms and descriptive atoms,while sparse codes contained one-hot label vectors and descriptive codes.In addition,as sparse representation algorithms were time-consuming,DKSVDN attached a co-trained feed-forward neural network to discriminative dictionary learning model to predict sparse codes.More-over,with generative module in DKSVDN,this method also designed a new dreaming training phase to improve the robustness of DKSVDN for unknown pattern in known class.The experiment results on public face image datasets verify the effectiveness of this method.

关 键 词：字典学习 稀疏表示 人脸识别 神经网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]