Some Approaches Based on Interval-Valued Images and L-Fuzzy Mathematical Morphology for Segmenting Images Reconstructed from Noisy Sinograms

DOI

10.2991/asum.k.210827.060How to use a DOI?

Keywords

Image reconstruction, Signal noise, Fuzzy and interval-valued fuzzy mathematical morphology, Morphological gradient, Image segmentation

Abstract

Two-dimensional image reconstruction from projections is a well known research field with different applications and using different sources, e.g., varying from medical imaging to a synchrotron laboratory. In the mathematical sense, we are looking for a two dimensional piecewise function with compact support for which a set of signals - the measurements, so called projections or sino-grams - are known a priori. After solving the corresponding inverse problem using an appropriate numerical scheme, a collection of reconstructed (gray-scale) images are provided for the final user for further analysis. In practice, the sinogram is often affected by various source of noise which lead to artefacts in the reconstructed images. In this paper, we first convert the resulting gray-scale image that can be viewed as an 𝕃-fuzzy set, where 𝕃 is a finite chain, into an interval-valued image whose values are non-empty, closed intervals of 𝕃, so as to express the uncertainty about its values. Subsequently, we apply four approaches of morphological image segmentation, all of which make use of the interval values of the image. Each of these approaches employs some type of morphological gradient and the watershed algorithm. We only consider transmission sinograms for this paper, as emission problems are beyond the scope of this paper.

Copyright

© 2021, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Peter Sussner
AU  - Lisbeth Corbacho Carazas
AU  - Eduardo X. Miqueles
PY  - 2021
DA  - 2021/08/30
TI  - Some Approaches Based on Interval-Valued Images and L-Fuzzy Mathematical Morphology for Segmenting Images Reconstructed from Noisy Sinograms
BT  - Joint Proceedings of the 19th World Congress of the International Fuzzy Systems Association (IFSA), the 12th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT), and the 11th International Summer School on Aggregation Operators (AGOP)
PB  - Atlantis Press
SP  - 452
EP  - 462
SN  - 2589-6644
UR  - https://doi.org/10.2991/asum.k.210827.060
DO  - 10.2991/asum.k.210827.060
ID  - Sussner2021
ER  -