摘要
论文提出了一种基于局部相位量化(Local Phase Quantization,LPQ)和独立成分分析(Independent Component Analysis,ICA)的人脸识别新方法。该方法首先采用LPQ算子提取分块人脸图像的LPQ直方图序列(LPQ Histogram Sequence,LPQHS),然后采用ICA方法对采样后的特征进行特征选择,最后利用最近邻分类器进行识别。在YALE和FERET人脸数据库上的实验结果验证了该方法的有效性。
A novel face recognition method based on Local Phase Quantization and ICA is proposed in this paper.Firstly,LPQ operator is used to extract the LPQ Histogram Sequence from face images.Secondly,ICA method is applied to extract feature subspace.Finally,nearest neighbor classifier is used to realize face recognition.Experiments on YALE and FERET face database demonstrate the performance of the proposed method.
出处
《信息化研究》
2015年第2期11-15,共5页
INFORMATIZATION RESEARCH
关键词
局部相位量化
独立成分分析
人脸识别
local phase quantization
independent component analysis
face recognition
