Next Article in Journal
New Aspects for Non-Existence of Kneser Solutions of Neutral Differential Equations with Odd-Order
Next Article in Special Issue
Spectrally Sparse Tensor Reconstruction in Optical Coherence Tomography Using Nuclear Norm Penalisation
Previous Article in Journal
Existence of Solutions for a System of Integral Equations Using a Generalization of Darbo’s Fixed Point Theorem
Open AccessFeature PaperArticle

Efficient Hyper-Parameter Selection in Total Variation-Penalised XCT Reconstruction Using Freund and Shapire’s Hedge Approach

1
National Physical Laboratory, Teddington, Middlesex TW11 0LW, UK
2
Laboratoire ERIC, Université Lyon 2, 69500 Bron, France
3
Engineering Tomography Laboratory, Department of Electronics and Electrical Engineering, University of Bath, Bath BA2 7AY, UK
*
Author to whom correspondence should be addressed.
Current address: Affiliation 2.
These authors contributed equally to this work.
Mathematics 2020, 8(4), 493; https://doi.org/10.3390/math8040493
Received: 16 January 2020 / Revised: 10 March 2020 / Accepted: 13 March 2020 / Published: 1 April 2020
(This article belongs to the Special Issue New Trends in Machine Learning: Theory and Practice)
This paper studies the problem of efficiently tuning the hyper-parameters in penalised least-squares reconstruction for XCT. Discovered through the lens of the Compressed Sensing paradigm, penalisation functionals such as Total Variation types of norms, form an essential tool for enforcing structure in inverse problems, a key feature in the case where the number of projections is small as compared to the size of the object to recover. In this paper, we propose a novel hyper-parameter selection approach for total variation (TV)-based reconstruction algorithms, based on a boosting type machine learning procedure initially proposed by Freund and Shapire and called Hedge. The proposed approach is able to select a set of hyper-parameters producing better reconstruction than the traditional Cross-Validation approach, with reduced computational effort. Traditional reconstruction methods based on penalisation can be made more efficient using boosting type methods from machine learning. View Full-Text
Keywords: hyper-parameter selection; image reconstruction; limited data reconstruction; total variation regularisation; cone-beam computed tomography hyper-parameter selection; image reconstruction; limited data reconstruction; total variation regularisation; cone-beam computed tomography
Show Figures

Figure 1

MDPI and ACS Style

Chrétien, S.; Lohvithee, M.; Sun, W.; Soleimani, M. Efficient Hyper-Parameter Selection in Total Variation-Penalised XCT Reconstruction Using Freund and Shapire’s Hedge Approach. Mathematics 2020, 8, 493.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop