[1]蔡金收,陈铁军,郭丽.基于投票极限学习机的人脸识别混合算法研究[J].郑州大学学报(工学版),2016,37(02):37-41.[doi:10.3969/j.issn.1671-6833.201505016]
 Chen Tiejun,Cai Jinshou,Guo Li.Research on Hybrid Face Recognition Algorithm Based on Voting Extreme Learning Machine[J].Journal of Zhengzhou University (Engineering Science),2016,37(02):37-41.[doi:10.3969/j.issn.1671-6833.201505016]
点击复制

基于投票极限学习机的人脸识别混合算法研究()
分享到:

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
37卷
期数:
2016年02期
页码:
37-41
栏目:
出版日期:
2016-04-18

文章信息/Info

Title:
Research on Hybrid Face Recognition Algorithm Based on Voting Extreme Learning Machine
作者:
蔡金收陈铁军郭丽
郑州大学电气工程学院,河南郑州,450001
Author(s):
Chen Tiejun Cai Jinshou Guo Li
School of Electrical Engineering, Zhengzhou University, Zhengzhou, Henan 450001
关键词:
Keywords:
curvelet transformB2DPCAvotingELMface recognition
DOI:
10.3969/j.issn.1671-6833.201505016
文献标志码:
A
摘要:
针对小波分析在处理多维图形时不能充分利用数据本身特有几何特征的缺陷,使用第二代曲渡变换(the second generation of curvelet transform,SGCT)方法进行人脸图像的处理,选取具有最大标准差的尺度层系数,以完成对人脸图像的特征提取,同时结合基于双向二维主成分分析(bidirectional two dimensional principal component analysis,B2DPCA)的数据降维,构造一种基于混合投票机制极限学习机(voting extreme learning machine,VELM)的人脸识别算法.通过与其他算法的分类结果对比,证明该算法具有更高的识别正确率.
Abstract:
Aiming at the defect that wavelet analysis cannot make full use of the unique geometric features of the data itself when dealing with multi-dimensional graphics, the second generation of curvelet transform (SGCT) method is used to process face images, and the image with the largest standard deviation is selected. Scale layer coefficients are used to complete the feature extraction of face images, and combined with data dimensionality reduction based on bidirectional two-dimensional principal component analysis (B2DPCA), a hybrid voting mechanism-based extreme learning machine (voting Extreme learning machine, VELM) face recognition algorithm. By comparing with the classification results of other algorithms, it is proved that the algorithm has a higher recognition accuracy.
更新日期/Last Update: