全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于多分辨率下节点图像融合的人脸识别方法

DOI: 10.11834/jig.20090836

Keywords: 人脸识别,多分辨率,小波包分解,(2D)2PCA,特征矩阵,节点图像

Full-Text   Cite this paper   Add to My Lib

Abstract:

人脸识别是人机接口和生物信息领域研究的重要方面,得到广泛的关注,人脸特征提取是其重要环节之一。为了克服人脸光照和表情变化对特征提取的影响,提出在小波包分解后的多分辨率下利用(2D)2PCA提取人脸特征进行识别的方法,主要创新包括:(1)以小波包分解所有节点图像为研究对象;(2)提出以识别率来选取“成功”节点;(3)提出一种融合节点图像的方法。首先通过二层小波包分解获取节点图像,采用(2D)2PCA方法提取所有节点图像的特征矩阵,并利用最邻近分类器获取其识别率,然后在选取“成功”节点图像的基础上,构建了一个融合方法进行人脸识别。用CMUPIE和Yale库中的样本进行对比测试,结果表明本方法的高效性,同时也说明融合多分辨率下的节点图像能有效提高识别率。

References

[1]  Turk M,Pentland A,Eigenfaces for recognition,Cognitive Neurosci,1991(1).
[2]  Kong Hui,Wang Lei,Teoh Earn Khwang,Generalized 2D principal component analysis for face image representation and recognition,Neural Networks,2005(5-6).
[3]  Yang J,Zhang D,Frangi A F,Two-dimensional PCA:A new approach to appearance-based face representation and recognition,IEEE Transactions on Pattern Analysis and Machine Intelligence,2004(1).
[4]  Zhang D,Zhou Z H,(2D)2PCA:two-directional two-dimensional PCA for efficient face representation and recognition,Neurocomputing,2005(1-3).
[5]  Chien J T,Wu C C,Diacriminant waveletfaces and nearest feature classifiers for face recognition,IEEE Transactions on Pattern Analysis and Machine Intelligence,2002(12).
[6]  Vinod Pathangay.Sukhendu Das Exploring the Use of Selective Wavelet Subbands for PCA Based Face Recognition 2008
[7]  Garcia C,Zikos G,Tziritas G,Wavelet packet analysis for face recognition,Image and Vision Computing,2000(4).
[8]  Nicholl P,Amira A,Bouchaffra D,Multiresolution hybrid approaches for automated face recognition,Edinburgh,Scotland,England,2007.
[9]  Hazim Kemal Ekenel,Bulent Sankur,multiresolution face recognition,Image and Vision Computing,2005(5).
[10]  吴清江.周晓彦.郑文明 一种基于2D-DWT和2D-PCA的人脸识别方法 [J].-计算机应用2006(9)
[11]  Sire T,Baker S,Bsat M,The CMU pose,illumination and expression database,IEEE Transactions on Pattern Analysis and Machine Intelligence,2003(12).

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133