Article

Splines in Higher Order TV Regularization

International Journal of Computer Vision (Impact Factor: 3.53). 12/2006; 70(3):241-255. DOI: 10.1007/s11263-006-8066-7
Source: DBLP

ABSTRACT Splines play an important role as solutions of various interpolation and approximation problems that minimize special functionals in some smoothness spaces. In this paper, we show in a strictly discrete setting that splines of degree m − 1 solve also a minimization problem with quadratic data term and m-th order total variation (TV) regularization term. In contrast to problems with quadratic regularization terms involving m-th order derivatives, the spline knots are not known in advance but depend on the input data and the regularization parameter �. More precisely, the spline knots are determined by the contact points of the m-th discrete antiderivative of the solution with the tube of width 2� around the m-th discrete antiderivative of the input data. We point out that the dual formulation of our minimization problem can be considered as support vector regression problem in the discrete counterpart of the Sobolev space W m 2,0. From this point of view, the solution of our minimization problem has a sparse representation in terms of discrete fundamental splines.

0 Followers
 · 
126 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: We introduce a family of novel regularization penalties to enable the recovery of discrete discontinuous piecewise polynomial signals from undersampled or degraded linear measurements. The penalties promote the group sparsity of the signal analyzed under a $n$th order derivative. We introduce an efficient alternating minimization algorithm to solve linear inverse problems regularized with the proposed penalties. Our experiments show that promoting group sparsity of derivatives enhances the compressed sensing recovery of discontinuous piecewise linear signals compared with an unstructured sparse prior. We also propose an extension to 2-D, which can be viewed as a group sparse version of higher degree total variation, and illustrate its effectiveness in denoising experiments.
    IEEE Signal Processing Letters 08/2015; 22(9):1414-1418. DOI:10.1109/LSP.2015.2407321 · 1.64 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper focuses on computational approaches for trend filtering, using the alternating direction method of multipliers (ADMM). We argue that, under an appropriate parametrization, ADMM is highly efficient for trend filtering, competitive with the specialized interior point methods that are currently in use. Furthermore, the proposed ADMM implementation is very simple, and importantly, it is flexible enough to extend to many interesting related problems, such as sparse trend filtering and isotonic trend filtering. Software for our method will be made freely available, written in C++ (see \url{http://www.stat.cmu.edu/~ryantibs/research.html}), and also in R (see the {\tt trendfilter} function in the R package {\tt genlasso}).
  • [Show abstract] [Hide abstract]
    ABSTRACT: The main focus of this paper is to introduce a computationally efficient algorithm for solving image recovery problems, regularized by the recently introduced higher degree total variation (HDTV) penalties. The anisotropic HDTV penalty is the fully separable L1 semi-norm of the directional image derivatives; the use of this penalty is seen to considerably improve image quality in biomedical inverse problems. We introduce a novel majorize minimize algorithm to solve the HDTV optimization problem, thus considerably speeding it over the previous implementation. Specifically, comparisons with previous iterative reweighted algorithm show an approximate ten fold speedup. The new algorithm enables us to obtain reconstructions that are free of patchy artifacts exhibited by classical TV schemes, while being comparable to state of the art total variation regularization schemes in run time.
    Biomedical Imaging (ISBI), 2013 IEEE 10th International Symposium on; 01/2013

Preview

Download
0 Downloads