摘要
因遮挡、光照等变化因素所引发的协变量偏移问题是面向现实的人脸识别系统需要重点解决的问题。从字典编码的角度探讨了这一问题。通过对现有的结构化误差编码方法的回顾,指出几种主流的结构化误差编码方法都可以转化为训练字典与遮挡字典联合表示的形式,只需对不同的误差编码方法建立合适的遮挡字典即可。鉴于遮挡字典在结构化误差编码方法中的重要作用,针对一种重要的基于字典表示的误差校正方法——基于Gabor特征的鲁棒表示与分类方法(GRRC)展开研究,指出其基于K-SVD的遮挡字典学习方法的主要不足在于:计算代价较高、冗余性较强、缺乏针对自然遮挡的结构,并提出了一种基于奇异值分解(SVD)的Gabor遮挡字典学习方法。在Extended Yale B,UMBDB和AR 3个人脸数据库上的实验结果表明,相对于基于K-SVD字典学习方法的GRRC,基于SVD字典学习方法的GRRC在各种情形下都具有更好的时间性能和识别性能。
Covariate shift incurred by occlusion and illumination variations is an important problem for real-world face recognition systems.This paper explored this problem from the perspective of dictionary coding.By reviewing several extant structured error coding methods,this paper indicated that these error coding methods can be rewritten as a linear system by combining training dictionary and well-designed occlusion dictionary.Due to the importance of occlusion dictionary in structured error coding,this paper studied the dictionary learning method,K-SVD（Singular Value Decomposition）,which is used in the Gabor feature based robust representation and classification（GRRC）method,and has been paid great attentions in the field of error coding.The K-SVD learned occlusion dictionary is strongly redundant and lack of natural structures.In addition,K-SVD is time-consuming.This paper proposed an SVD-based occlusion dictionary learning method.It is simple,but generates a more compacted and structured occlusion dictionary.Experiments on three face datasets,including Extended Yale B,UMBDB and AR,demonstrates that the proposed SVD-based GRRC consistently outperforms the K-SVD-based GRRC in several challenging situations.
作者
李小薪
周元申
周旋
李晶晶
刘志勇
LI Xiao-xin;ZHOU Yuan-shen;ZHOU Xuan;LI Jing-jing;LIU Zhi-yong(College of Computer Science and Technology,Zhejiang University of Technolog;Industry Center,Shenzhen Polytechni)
出处
《计算机科学》
CSCD
北大核心
2018年第6期275-283,共9页
Computer Science
基金
国家自然科学基金(61402411)
浙江省自然科学基金(LY18F020031
LQ14C010001
LY18F020028)
深圳市科技项目(JCYJ20150630114140642)资助
