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...

采用后验信息构建稀疏原子库的超分辨率人脸重建

Keywords: 人脸超分辨率,幻觉脸,稀疏表示,鲁棒性超分辨率

Full-Text   Cite this paper   Add to My Lib

Abstract:

为了提高监控噪声环境下人脸图像的重建质量,提出基于后验信息的鲁棒性原子库构建方法及基于该原子库的超分辨率的方法,通过事后采集现场图像,训练只对输入图像的清晰内容稀疏而对噪声内容不稀疏的低维原子集和与之相对应的高维原子集,计算低维空间的稀疏系数并映射到高维空间以合成出重建人脸图像,从而提高基于稀疏表示的局部脸超分辨率对于监控噪声的鲁棒性.实验结果表明:对于实际拍摄的监控图像输入,提出的基于后验信息的原子库具有很好的鲁棒性能,重建结果比传统方法有更好的主观效果.

References

[1]  ELAD Michael,DATSENKO Dmitry.Example-basedregularization deployed to super-resolution reconstruction ofa single image[J].The Computer Journal,2007,52(1):15-30.
[2]  PARK S C,PARK M K,KANG M G.Super-resolutionimage reconstruction:a technical overview[J].IEEESignal Processing Magazine,2003,20(3):21-36.
[3]  JIA Kui,GONG Hao-gang.Generalized face super-resolution[J].IEEE Transactions on Image Processing,2008,17(6):873-886.
[4]  LIU C,SHUM H,FREEMAN W T.Face hallucination:theory and practice[J].International Journal of ComputerVision,2007,75(1):115-134.
[5]  GUNTURK B K,BATUR A U,ALTUNBASAK Y,et al.Eigenface-domain super-resolution for face recognition[J].IEEE Transactions on Image Processing,2003,12(5):597-606.
[6]  WANG X,TANG X.Hallucinating face by eigentransform[J].IEEE Transactions on Systems,Man,andCybernetics-Part C:Applications and Reviews,2005,35(3):425-434.
[7]  FREEMAN W T,PASZTOR E C,CARMICHAEL O T.Learning low-level vision[J].International Journal ofComputer Vision,2000,40(1):25-47.
[8]  BAKER S,KANADE T.Limits on super-resolution andhow to break them[J].IEEE Transactions on PatternAnalysis and Machine Intelligence,2002,24(9):1167-1183.
[9]  SUN Jian,ZHENG Nan-ning,TAO Hai,et al.Imagehallucination with primal sketch priors[C]∥IEEEInternational Conference on Computer Vision and PatternRecognition.Madison:IEEE Computer Society Press,2003,2:1063-1069.
[10]  CHANG Hong,YEUNG Dit-yan,XIONG Yi-min.Super-resolution through neighbor embedding[C]∥IEEEInternational Conference on Computer Vision and PatternRecognition.Washington,D.C.:IEEE Computer SocietyPress,2004,1:275-282.
[11]  YANG Jian-chao,WRIGHT John,HUANG Thomas,etal.Image super-resolution via sparse representation[J].IEEE Transactions on Image Processing,2010,19(11):2861-2873.
[12]  WRIGHT J,YANG A Y,GANESH A,et al.Robustface recognition via sparse representation[J].IEEETransactions on Pattern Analysis and MachineIntelligence,2009,31(2):210-227.
[13]  TROPP Joel A,GILBERT Anna C.Signal recovery fromrandom measurements via orthogonal matching pursuit[J].IEEE Transaction on Information Theory,2007,53(12):4655-4666.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133