A Lagrange Multiplier-based Regularization Algorithm for Image Super-resolution

In this article, we propose a Lagrange multiplier-based model for the regularization problem encountered in the image super-resolution. By establishing the equivalent relationship between the regularization model and the Lagrange multiplier-based model, we provide another version of the physical meaning of the regularization parameter. The nonlinearly monotonic relationship between the regularization parameter and the Lagrange multiplier is proved by contradiction. To solve the regularization parameters, a two-phase iterative method based on the Lagrange multiplier-based model is presented. Furthermore, we apply the propagation filtering method to smoothen the super-resolution image. A QR code image super-resolution is employed to validate the effectiveness of the proposed method.

[1]  A. Kirsch.  An Introduction to the Mathematical Theory of Inverse Problems , 1996, Applied Mathematical Sciences.

[2]  H. Engl,et al.  Regularization of Inverse Problems , 1996 .

[3]  Peyman Milanfar,et al.  Efficient generalized cross-validation with applications to parametric image restoration and resolution enhancement , 2001, IEEE Trans. Image Process..

[4]  A Tikhonov,et al.  Solution of Incorrectly Formulated Problems and the Regularization Method , 1963 .

[5]  Per Christian Hansen,et al.  Regularization methods for large-scale problems , 1993 .

[6]  ProblemsPer Christian HansenDepartment.  The L-curve and its use in the numerical treatment of inverse problems , 2000 .

[7]  C. Vogel.  Non-convergence of the L-curve regularization parameter selection method , 1996 .

[8]  Xiao-Jun Yang,et al.  Generalized Sampling Theorem for Fractal Signals , 2012 .

[9]  Thomas Bonesky.  Morozov's discrepancy principle and Tikhonov-type functionals , 2008 .

[10]  Stefan Kindermann,et al.  On the convergence of the quasioptimality criterion for (iterated) Tikhonov regularization , 2008 .

[11]  Yu-Chiang Frank Wang,et al.  Propagated image filtering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Yang-Ming Zhu.  Generalized sampling theorem , 1992 .

[13]  Michael Elad,et al.  Super-Resolution Reconstruction of Image Sequences , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Moon Gi Kang,et al.  Super-resolution image reconstruction: a technical overview , 2003, IEEE Signal Process. Mag..

[15]  Xuelong Li,et al.  Learning Multiple Linear Mappings for Efficient Single Image Super-Resolution , 2015, IEEE Transactions on Image Processing.

[16]  Takeo Kanade,et al.  Limits on super-resolution and how to break them , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).