学术报告
报告题目:A Discriminative Projection and Sparse Representation-based Classification Framework for Face Recognition
主讲人:彭拯教授
报告时间:2021年4月21日,周三下午3:00
地 点:威尼斯886699学术报告厅5511
摘 要:The sparse representation-based classifier (SRC) has been developed and verified having great potential for real-world face recognition. In this paper, we propose a discriminative projection and representation-based classification (DPRC) method to enhance the discriminant ability of the SRC. The proposed method first obtains a discriminative projection matrix not only maximizing the ratio of the distance within inter-class over the distance within intra-class, but also minimizing the linear approximation error within intra-class. Then it maps the original data onto the discriminative space, and adopts a SRC method to obtain the final solution. An inexact augmented Lagrangian method of multiplier is proposed for finding the optimal representation vector in our framework, and a proximal alternating minimization method is adopted to the iteration subproblems of the proposed method. The proposed method is proven having the sub-sequence convergence property. Experimental results on Yale, ORL,and AR face image databases demonstrate that, compared with some existing feature extraction methods based on the SRC, the proposed DPRC method is more efficient.
主讲人简介:彭拯,湘潭大学数学与计算科学学院教授,博士生导师,当前主要研究兴趣为数据科学中的流形优化问题算法及其应用、卫星遥感数据融合、芯片设计与仿真等领域的工程优化问题及其高效率算法。彭拯教授于2008年获上海大学博士学位(运筹学与控制论),2010年从南京大学数学系博士后出站,2013年晋升教授,在数学优化及其应用相关主流期刊发表学术论文40多篇,其中SCI、EI检索30多篇,主持或参与完成国家、省部级科研项目10余项,当前主持在研国家自然科学基金面上项目1项,湖南省自然科学基金面上项目1项。