计算机科学 ›› 2014, Vol. 41 ›› Issue (Z6): 178-180.
胡伟,张少华,郭晓丽
HU Wei,ZHANG Shao-hua and GUO Xiao-li
摘要: 针对光照变换产生的阴影、反光等原因,提出了一种差异性稀疏表示的人脸识别算法。首先利用非下采样contourlet变换(NSCT,nonsubsampled contourlet transformation)将测试图像分解。利用不同子带系数特点,依据子带对图像分类的贡献度分类,并将子带信息进行融合,得到具有差异性的特征,最后用于人脸识别。在人脸数据库上的实验结果表明,该算法对于光照和表情变换具有较好的鲁棒性。
[1] Yang M,Zhang L,Shiu S,et al.Monogenic Binary Coding:An Efficient Local Feature Extraction Approach to Face Recognition [J].IEEE Trans.on Information Forensics and Security,2012,7(6):1738-1751 [2] 朱杰,杨万扣,唐振民.基于字典学习的核稀疏表示人脸识别方法[J].模式识别与人工智能,2012,5(5):859-864 [3] Wright J,Yang A,Ganesh A,et al.Robust face recognition via sparse representation[J].IEEE Trans.Pattern Anal.Mach.Intell.,2009,30(2):210-227 [4] Yang Meng,Zhang Lei.Gabor feature based sparse representation for face recognition with gabor occlusion dictionary[C]∥Proceedings of the 11th European conference on Computer vision.Crete,Greece,2010,8-461 [5] Cunha A L,Zhou J,Do M N.The nonsubsampled Contourlettransform:theory,design and applications[J].IEEE Transactions on Image Processing,2006,15(10):3089-3101 [6] Li Hong-jun,Zhao Zhi-min,Yu Xiao-lei.Grey theory applied in non-subsampled Contourlet transform[J].IET Image Proces-sing,2012,6(3):264-272 [7] 杨萌,张弓.自适应超完备字典学习的SAR图像降噪[J].中国图象图形学报,2012,7(4):596-602 [8] 李洪均,谢正光,李蕴华,等.图像字典的盲构造算法[J].光电子·激光,2013,4(9):1825-1831 [9] Wang Z,Bovik A C.A universal image quality index[J].IEEE signal Processing Letters,2002,9(3):81-84 [10] Naseem I,Togneri R,Bennamoun M.Linear regression for face recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(11):2106-2112 |
No related articles found! |
|