基于B2DPCA和极端学习机的人脸识别  

Human Face Recognition Based on B2DPCA and ELM

作　　者：赵永卿[1] 安建成[1] 

机构地区：[1]太原理工大学计算机科学与技术学院,山西太原030024

出　　处：《电视技术》2013年第5期175-178,共4页Video Engineering

摘　　要：介绍一种新的基于双向二维主成分分析(B2DPCA)和极端学习机(ELM)的人脸识别方法,该方法是根据人脸曲波图像分解和一种改进的降维技术,通过B2DPCA生成识别特征集来提高分类精度。该方法还能够有效地提高分类正确率和降低对原型数量的依赖。通过做大量的实验,把结果和现存技术相比较。A new human face recognition algorithm based on bidirectional two dimensional principal component analysis（B2DPCA） and extreme learn- ing machine（ELM） is introduced. The proposed method is based on curvalet image decomposition of human faces and an improved dimensionality reduc- tion technique. Discriminative feature sets are generated using B2DPCA to ascertain classification accuracy. Other notable contributions of the proposed work include significant improvements in classification rate and minimal dependence on the number of prototypes. Extensive experiments are performed u- sing databases and results are comoared against state of the art techniques.

关 键 词：人脸识别 B2DPCA ELM 降维技术 识别率 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]