期刊文献+

基于学习的彩色人脸图像超分辨率重构研究 被引量:5

Color Face Image Super-Resolution Reconstruction Based on Learning
下载PDF
导出
摘要 提出了一种基于四元数模型的彩色人脸图像超分辨率重构算法.该算法利用主成分分析的主要思想,同时结合插值算法的理论,前期进行整体约束,后期进行分块处理,对人脸图像进行超分辨率重构.同时使用奇异值分解去除彩色图像中的噪声,针对主成分分析算法不太忠实于原图像的弱点进行改进;使用四元数表示彩色图像,将R,G,B三个分量同时进行处理.分析结果表明,该算法既利用了彩色分量的相关性,又提高了运算效率. Proposes a super-resolution algorithm on color face image based on quaternion,combining with the ideas of principal component analysis(PCA) and interpolation.By using singular value decomposition to de-noise the color image,improves the quality of the result,and improves the algorithms when the result is not so faithful to the original face image.Quaternion is used to deal with the three components of R,G,B at the same time to increase the efficiency of the operation and used fully the correction of the three components.
出处 《北京理工大学学报》 EI CAS CSCD 北大核心 2010年第2期193-196,共4页 Transactions of Beijing Institute of Technology
基金 国家自然科学基金资助项目(60472110)
关键词 彩色人脸图像 超分辨率重构 四元数 主成分分析(PCA) 插值 color image super-resolution reconstruction quaternion principal component analysis(PCA) interpolation
  • 相关文献

参考文献8

  • 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.
  • 8雷印杰,余艳梅,周激流,杨柱中,罗代升.四元数奇异值分解与彩色图像去噪[J].四川大学学报(自然科学版),2007,44(6):1268-1274. 被引量:9

二级参考文献16

  • 1叶佳,张建秋,胡波.客观评估彩色图像质量的超复数奇异值分解法[J].电子学报,2007,35(1):28-33. 被引量:13
  • 2胡玉平.基于奇异值分解的自嵌入图像认证水印算法[J].计算机工程,2007,33(16):106-108. 被引量:6
  • 3Konsstantinides K, Yao K. Statistical analysis of effective singular values in matrix rank determination [J]. IEEE Trans on Acoustics, Speech, and Signal Process, 1988, 36(5):757.
  • 4Shnayderman A, Gusev A, Eskicioglu A M. An SVD- based grayscale image quality measure for local and global assessment [J]. IEEE Transactions on Image Process, 2005,14 (2) : 422.
  • 5Howland P, Park H. Generalizing diseriminant analysis using the generalized slgular value deoomposition [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2004,26(8):995.
  • 6Konstantinides K, Natarajan B, Yovanof G S. Noise estimation and filtering using block-based singular value decomposition [J]. IEEE Trans Image Processing, 1997, 6(4): 479.
  • 7Natarajan B K. Filtering random noise from deterministic signal via data compression [J ]. IEEE Transactions on Signal Processing, 1995, 43(11):2595.
  • 8Hamilton W R. Elements of quatemions [M]. London: Longmans, Green and Co, 1866.
  • 9Wolf L A. Similarity of matrics in which elements are real quaternion [D]. USA: University of Wisconsin- Madison, Bull Amer Math Soc, 1936.
  • 10Pei S C, Ding J J,Chang J H. Efficient implementation of quatemion Fourier transform, convolution,and correlation by 2-D FFT [J]. IEEE Trensaetions on Signal Procssing, 2001,49( 11 ) : 2783.

共引文献8

同被引文献67

  • 1郭六生,冯前进,贠照强,李慧慧.一种基于感兴趣点旋转不变性特征的图像配准新方法[J].中国医学物理学杂志,2011,28(1):2364-2368. 被引量:1
  • 2Eekeren 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.
  • 3Kim 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.
  • 4Ma Xiang,Zhang Junping,Qi Chun.Hallucinating Face byPosition-patch[J].Pattern Recognition,2010,43(6):2224-2236.
  • 5Park 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.
  • 6Wang Xiaogang,Tang Xiaoou.Hallucinating Face by Eigentrans-formation[J].IEEE Trans.on Systems Man and Cybernetic,2005,35(3):425-434.
  • 7Philips 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.
  • 8刘松涛,杨绍清.图像配准技术研究进展[J].电光与控制,2007,14(6):99-105. 被引量:14
  • 9Baker S, Kanade T. Limits on Super-resolution and How to Break Them [J ]. Computer Vision and Pattern Recognition, 2000, 9(2):372-379.
  • 10Hertzmann A, Jacobs CE, Oliver N, et al. Image analogies[C] //Proceedings of Computer Graphics, Annual Conferences Series, ACMSIGGTAPH. Los Angeles, Califomia:[ s.n ], 2001:327-340.

引证文献5

二级引证文献20

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