采用自适应加权扩展LBP的单样本人脸识别  

Single sample face recognition using adaptively weighted extended local binary pattern

作　　者：高涛[1] 马祥[1] 白璘[1] 

机构地区：[1]长安大学信息工程学院,陕西西安710072

出　　处：《光电子．激光》2012年第4期782-790,共9页Journal of Optoelectronics·Laser

基　　金：国家自然科学基金(61101215/F010401);中央高校基本科研业务费专项资金(CHD2011JC067;CHD2011JC084;CHD2012TD011);长安大学基础研究支持计划专项基金资助项目

摘　　要：提出了一种采用自适应加权扩展LBP(AWELBP,adaptively weighted extended local binarypattern)的单样本人脸描述方法,首先对单样本的人脸图像进行多尺度分块,对子块的图像进行扩展均匀LBP算子运算,同时同步生成图像局部熵图谱(LEM,local entropy map),计算每一子块对整体人脸图像纹理描述的贡献度图谱,根据贡献度图谱对每个子块的LBP直方图进行自适应加权,最后将各子块的LBP直方图进行连接形成人脸特征。本算法在ORL、Yale、Yale B人脸库上对部分遮挡、表情变化、光照变化等环境进行测试,并与传统算法以及与多种LBP改进算法进行比较,结果表明该算法对部分遮挡、表情变化和光照等环境下单样本人脸描述具有较好的效果。This paper presents a novel method for face description with single sample by adaptively weighted extended local binary pattern（AWELBP）.The proposed algorithm utilizes an extended local binary pattern（ELBP） to represent faces partitioned into sub-patterns.Especially,in order to perform matching in the sense of the richness of identity information and to handle the partial occlusion problem,the proposed algorithm employs an adaptively weighting map to weight the sub-ELBP（SELBP） extracted from local areas based on the contribution of each sub-pattern to the final similarity measurement.Simulated experiments and comparisons on a subset of Yale face databases,a subset of Yale B face databases and ORL face databases under ideal condition,different illumination condition,different facial expression and partial occlusion show that the proposed algorithm is an outstanding method for single sample face recognition.

关 键 词：人脸识别 局域二进模式(LBP) 自适应加权扩展(AWE) 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]