非局部二值模式人脸表示与识别方法  

Robust Face Recognition and Representation by Non-local Binary Pattern

作　　者：王宇[1] 林成德[1] 

机构地区：[1]厦门大学信息科学与技术学院,福建厦门361005

出　　处：《厦门大学学报（自然科学版）》2009年第2期207-211,共5页Journal of Xiamen University：Natural Science

摘　　要：人脸表示/特征提取是人脸识别技术中最重要的步骤,局部二值模式(LBP)在人脸识别问题中受到了越来越多的关注和研究.为了克服原始LBP算子存在的固有缺陷,本文在其基础上提出了非局部二值模式NLBP算子.相对于原始LBP算子,新的NLBP算子能够实现多尺度分析能力,突出了人脸的关键特征,并能增强人脸表示与识别的鲁棒性.实验验证了新NLBP算子的有效性.Face Representation/Feature Selection is the most important step in Face Recognition process, Local Binary Pattern （LBP） has received more and more attention from researchers. In order to overcome its inherent deficiencies,a new operator named Non-Local Binary Pattern （NLBP） is proposed in this paper. Compared to the original LBP operator, the NLBP operator can implement multi-scale face analysis,and thus,enhances the salient features of the face and increases the robustness of face representation and recognition. Experiments demonstrate well the effectiveness of this newly proposed operator.

关 键 词：人脸识别 人脸表示 局部二值模式LBP 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]