期刊文献+

基于PCA与残差补偿的人脸超分辨率算法

Face Super-resolution Algorithm Based on PCA and Residue Compensation
下载PDF
导出
摘要 提出一种基于主成分分析(PCA)与相似递归残差补偿的人脸超分辨率算法。基于PCA获得高低分辨率人脸图像特征空间的映射系数,通过该系数重建初步的高分辨率人脸图像。利用高低分辨率人脸图像空间同一区域图像块的内容相似性,递归计算残差补偿图像。采用该残差图像对初步重建的全局人脸进行细节补偿。实验结果表明,该算法的重建效果较优。 This paper proposes a face super-resolution algorithm based on Principle Component Analysis(PCA) and similar recursive residue compensation. The mapping coefficients of low-resolution facial space are obtained based on PCA and preliminary face is reconstructed through these coefficients. Using the similar contents of the same face region in high and low resolution face image, a residual image is computed by recursive linear combination. It uses the residue image to compensate the global image reconstructed. Experimental results show that the proposed method produces high quality images.
作者 马祥 刘军辉
出处 《计算机工程》 CAS CSCD 2012年第13期196-198,共3页 Computer Engineering
基金 国家自然科学基金资助项目(61101215) 中央高校基本科研业务费专项基金资助项目(CHD2011JC146) 长安大学基础研究支持计划专项基金资助项目
关键词 人脸图像 超分辨率 递归 主成分分析 残差补偿 face image super-resolution recursion Principle Component Analysis(PCA) residue compensation
  • 相关文献

参考文献9

  • 1Eekeren A W M,Schutte K,Vliet L J.Multiframe Super-reso-lution Reconstruction of Small Moving Objects[J].IEEE Trans.onImage Processing,2010,19(11):2901-2912.
  • 2Kim K I,Kown Y.Single-image Super-resolution Using SparseRegression and Natural Image Prior[J].IEEE Trans.on PatternAnalysis and Machine Intelligence,2010,32(6):1127-1133.
  • 3Ma Xiang,Zhang Junping,Qi Chun.Hallucinating Face byPosition-patch[J].Pattern Recognition,2010,43(6):2224-2236.
  • 4Park J S,Lee S W.An Example-based Face Hallucination Methodfor Single-frame,Low-resolution Facial Images[J].IEEE Trans.onImage Processing,2008,17(10):1806-1816.
  • 5Wang Xiaogang,Tang Xiaoou.Hallucinating Face by Eigentrans-formation[J].IEEE Trans.on Systems Man and Cybernetic,2005,35(3):425-434.
  • 6李涛,王晓华,宋桂芹,李军科,闫雪梅.基于学习的彩色人脸图像超分辨率重构研究[J].北京理工大学学报,2010,30(2):193-196. 被引量:5
  • 7兰诚栋,胡瑞敏,卢涛,韩镇.低质量监控图像鲁棒性人脸超分辨率算法[J].计算机辅助设计与图形学学报,2011,23(9):1474-1480. 被引量:4
  • 8卫保国,康娱.基于约束块重建的人脸超分辨率方法[J].计算机仿真,2011,28(12):277-280. 被引量:2
  • 9Philips P,Moon H,Pauss P,et al.The FERET Evaluation Metho-dology for Face Recognition Algorithms[C]//Proc.of IEEEConference on Computer Vision and Pattern Recognition.[S.l.]:IEEE Press,1997.

二级参考文献31

  • 1Freeman W T, Pasztor E C, Carmichael O T. Example- based super-resolution [J].IEEE Computer Graphics and Application, 2002,22(2) :56 - 65.
  • 2Baker S, Kanada T. Hallucinating faces[C] //Proc IEEE Inc Conj Automatic Face and Gesture Recog.Grenoble. [S. l. ] : IEEE, 2000: 83 - 88.
  • 3Baker S, Kanade T. Limits on super-resolution and hoe to break them[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,24(9):1167- 1183.
  • 4Elad M, Feue A. Super resolution of an image sequence- adaptive filtering approach[J]. IEEE Trans Image Pro- cessing, 1999,8(3):387 - 395.
  • 5Liu C, Shum H, Zhang C. A two-step approach to hallucinating faces., global parametric model and local non- parametric model[C]//Proc IEEE Int Conf Computer Vision and Pattern Recognition. Hawaii, USA:[s. n. ], 2001:192 - 198.
  • 6Wang Xiaogang, Tang Xiaooi. Hallucinating face by Eigen-transformation[C] // Proc IEEE JNL Systems Man and Cubernetics. Hawaii, USA: Hilton Waikoloa Village, 2005:425 - 434.
  • 7Tang X, Wang X. Face photo recognition using sketch [C]//Proc of ICIP. Rochester, USA: [s. n. ], 2002: 257 - 260.
  • 8Capel D, Zisserman A. Super resolution from multiple views using learnt image models [C] //Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society Press, 2001, 2:627-634.
  • 9Gunturk B K, Batur A U, Altunbasak Y, et al. Eigenfacedomain super-resolution for face recognition [J].IEEE Transactions on Image Processing, 2003, 12(5): 597-606.
  • 10Wang X G, Tang X O. Hallucinating face by eigentransformation[J]. IEEE Transactions on Systems,Man, and Cybernetics, Part C: Applications and Reviews, 2005, 35(3): 425-434.

共引文献8

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部