[1]赵庆敏,欧阳欢,辜道平.Curvelet变换在人脸识别中的应用研究[J].江西师范大学学报(自然科学版),2013,(04):397-400.
 ZHAO Qing-min,OUYANG Huan,GU Dao-ping.Application Study on Curvelet Transform in Face Recognition[J].,2013,(04):397-400.
点击复制

Curvelet变换在人脸识别中的应用研究()
分享到:

《江西师范大学学报》(自然科学版)[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2013年04期
页码:
397-400
栏目:
出版日期:
2013-09-01

文章信息/Info

Title:
Application Study on Curvelet Transform in Face Recognition
作者:
赵庆敏;欧阳欢;辜道平
南昌大学信息工程学院,江西南昌,330031
Author(s):
ZHAO Qing-min;OUYANG Huan;GU Dao-ping
关键词:
小波人脸识别第2代Curvelet双向2维主成分分析
Keywords:
waveletface recognitionsecond-generation curveletwo-directional two-dimensional principal component analysis ((2D)2 PCA)
分类号:
TP391.41
文献标志码:
A
摘要:
针对小波只能反映信号的点奇异性,无法实现人脸图像面部轮廓和五官曲线信息的最优稀疏表示,提出了一种基于第2代Curvelet的人脸识别算法.通过对人脸图像进行第2代Curvelet变换,分解得到表征人脸基本信息的低频系数,再利用双向2维主成分分析(《2D)2PCA)进行降维,并结合最近邻算法进行人脸识别.以ORL人脸数据库进行试验,结果表明:与基于小波变换的算法相比,该算法具有更高识别率和更短的识别时间.
Abstract:
As wavelet can only reflect the zero-dimensional singularities of signal and cannot provide an optimally sparse representation of facial contour and five sense organs' curve information of face image,a face recognition algorithm based on second-generation curvelet transform is proposed.The proposed method firstly transforms face image with second-generation curvelet to get low frequency coefficients with facial basic information,and then reduce dimensions with the two-directional two-dimensional principal component analysis((2D)PCA),at last the test face is recognized by using the nearest distance algorithm.Experimental results on ORL and Yale face database show that the proposed method has higher recognition rate and less recognition time than the method based on wavelet.

参考文献/References:

[1] 王映辉.人脸识别:原理、方法与技术 [M].北京:科学出版社,2010.
[2] Amira A,Farrell P.An automatic face recognition system based on wavelet transforms [J].IEEE International Symposium on Circuits and Systems,2005,5:6252-6255.
[3] Candès E J,Donoho D L.Curvelet-A surprisingly effective nonadaptive representation for objects with edges [C].TN:Vanderbilt University Press,2000:105-120.
[4] Donoho D L,Duncan M R.Digital curvelet transform:strategy,implementation and experiments [EB/OL].
[2012-11-16].http:∥spie.org/x648.html?product_id=381679.
[5] Candès E J,Demanet L,Donoho D,et al.Fast discrete curvelettransforms [J].Multiscale Modeling & Simulation,2005,5(3):861-899.
[6] Zhang Daoqiang,Zhou Zhihua.(2D)PCA:two-directional two-dimensional PCA for efficient face representation and recognition [J].Neurocomputing,2005,69(1/2/3):224-231.
[7] 焦李成.图像多尺度几何分析 [M].西安:西安电子科技大学出版社,2008.
[8] 杨家红,许灿辉,王耀南.基于快速曲波变换的图像去噪算法 [J].计算机工程与应用,2007,43(6):31-33.
[9] 赵晓花,张贵仓.一种基于边缘检测和正负量化的盲水印算法 [J].江西师范大学学报:自然科学版,2013,37(1):42-45.
[10] 王俊杰,张宇波.基于线性回归的图像边缘处理算法的研究 [J].江西师范大学学报:自然科学版,2013,37(1):56-59.

相似文献/References:

[1]彭春华,刘 刚.基于粗糙集的人脸识别改进方法[J].江西师范大学学报(自然科学版),2016,40(05):487.
 PENG Chunhua,LIU Gang.The Improved Method for Face Recognition Based On Rough Set[J].,2016,40(04):487.

备注/Memo

备注/Memo:
江西省科技支撑计划(2009BGB01900)
更新日期/Last Update: 1900-01-01