摘要
为了提高高校管理的效率和质量,实现对全天时的人员监测十分重要。由此,论文提出结合全局和局部字典稀疏表示的人脸识别方法并将其应用于高校信息化管理中。全局字典上的稀疏表示体现了测试样本与各训练类别的相似性的相对大小。局部字典的稀疏表示则体现了测试样本与某一类的绝对相似性。通过线性加权融合的方法结合全局和局部稀疏表示的结果,有效提升了人脸识别的稳健性。在AR和Yale-B人脸库上的实验证明了提出方法的有效性。
To enhance the efficiency and effectiveness of information management of university library,it is important to monitor the concerned in all day long. Hence,this paper proposes a face recognition method based on combination of global and local representations. Global sparse representation describes the relative description capabilities of different classes for the test sample while local sparse representation evaluates the absolute description capabilities. The decision value vectors from global and local representations are combined based on the linear fusion for robust face recognition. To validate the effeteness of the proposed method,experiments are conducted on AR and Yale-B face databases and compared with other face recognition methods.
作者
刘嘎琼
LIU Gaqiong(Marine Equipment and Technology Institute,Jiangsu University of Science and Technology,Zhenjiang 212003)
出处
《计算机与数字工程》
2018年第11期2333-2335,2379,共4页
Computer & Digital Engineering
基金
国家自然科学基金(编号:61603243)
江苏省创新能力建设计划(联合载体类)-联合重大创新载体项目(编号:BY2015083)资助
关键词
高校管理
人脸识别
全局稀疏表示
局部稀疏表示
university management
face recognition
global sparse representation
local sparse representation
