一种融合改进LBP与主成分分析的人脸识别方法  

A Face Recognition Method Based on Improved LBP and Principal Component Analysis

作　　者：朱政 ZHU Zheng(School of Electrical and Information Engineering,Anhui University of Science and Technology,Huainan 232000,China)

机构地区：[1]安徽理工大大学电气与信息工程学院,安徽淮南232000

出　　处：《洛阳理工学院学报（自然科学版）》2022年第4期71-76,共6页Journal of Luoyang Institute of Science and Technology：Natural Science Edition

基　　金：国家自然科学基金项目(51274011,61772033).

摘　　要：针对传统的LBP算子局部纹理特征提取方式单一、未考虑邻域相关性等问题,提出一种改进的LBP算子与PCA主成分分析法相结合的人脸识别方法。该方法在特征提取的过程中削弱了噪声的影响,更好地突出了子块区域的特征信息,相比于PCA、LBP和PCA相结合的方法,在识别率上有显著提高。In view of the shortcomings of traditional LBP operator′s local texture feature extraction method is single,without considering theneighborhood correlation,this paper proposes an improved face recognition method combining LBP operator and PCA.This method reduces noise in the process of feature extraction and better highlights the feature information of sub-block area.Compared with PCA,LBP and PCA,the method significantly improves the recognition rate.

关 键 词：人脸识别 特征提取 主成分分析 MBLBP 识别率 

分 类 号：TP311.5[自动化与计算机技术—计算机软件与理论]