摘要
针对目前基于韦伯特征的人脸识别算法没有充分利用方向信息且提取信息不充分的问题,提出一种多方向韦伯梯度直方图的人脸识别方法。在原始差分激励的基础上增加邻域像素梯度,提取改进的差分激励和韦伯梯度特征;将改进的差分激励与韦伯方向进行量化并分块提取二维直方图,进而转化为一维直方图特征,将韦伯梯度分块后沿韦伯方向累积提取直方图特征;连接两个特征形成组合特征,并利用最近邻分类器分类。通过在不同人脸库的实验可看出,所提算法具有良好的识别效果,且对光照、表情和部分遮挡变化有较好的稳健性。
Aiming at the problems in the face recognition algorithm based on Weber features that the directional information is not made full use and the extracted information is also insufficient, we propose a novel face recognition method based on multi-directional Weber gradient histograms. On the basis of original differential excitation, the neighborhood pixel gradient is increased, and the improved differential excitation and Weber gradient features are extracted. The improved differential excitation and Weber direction are quantized, and the two- dimensional histograms are extracted in blocks, which are further converted into one-dimensional histogram features. The histogram features are extracted along the Weber direction. Two features are connected to form a compound feature and simultaneously the nearest neighbor classifier is used for classifying. The experiments on different face databases show that the proposed method has not only a good recognition effect, but also a relatively strong robustness to illumination, expression and partial occlusion.
作者
杨恢先
徐唱
曾金芳
陶霞
Yang Huixian;Xu Change;Zeng Jinfang;Tao Xia(School of Physics and Optoelectronics,Xiangtan University,Xiangtan,Hunan 411105,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2018年第11期190-198,共9页
Laser & Optoelectronics Progress
基金
湖南省自然科学基金(2018JJ3486)
关键词
图像处理
人脸识别
韦伯特征
多方向韦伯梯度直方图
image processing
face recognition
Weber feature
multi-directional Weber gradient histogram
