A guide to unsupervised image segmentation of mCT-scanned cellular metals with mixture modelling and Markov random fields
Characterising the structure of cellular metals is a difficult task. The internal structure of cellular metals can be determined using micro-computed tomography (mCT). However, mCT scanning provides digital images in greyscale with various problematic artefacts. In addition, the grey intensity of ce...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-03-01
|
| Series: | Materials & Design |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0264127524001229 |
| _version_ | 1797256401330896896 |
|---|---|
| author | Branislav Panić Matej Borovinšek Matej Vesenjak Simon Oman Marko Nagode |
| author_facet | Branislav Panić Matej Borovinšek Matej Vesenjak Simon Oman Marko Nagode |
| author_sort | Branislav Panić |
| collection | DOAJ |
| description | Characterising the structure of cellular metals is a difficult task. The internal structure of cellular metals can be determined using micro-computed tomography (mCT). However, mCT scanning provides digital images in greyscale with various problematic artefacts. In addition, the grey intensity of cellular metals usually varies greatly due to the internal porosity of the material. Therefore, binary image segmentation to extract material segments from digital images is quite difficult. Our contribution can be summarised as follows. A comprehensive evaluation of various mixture models that have been shown in the literature to be useful for tomography, but for the purpose of binary image segmentation of cellular metals and internal porosity assessment. We propose a novel merging technique to merge different components of the mixture model for the purpose of binary image segmentation of cellular metals. Finally, to enforce spatial regularisation and further improve the binary image segmentation, we combine the obtained two-segment mixture model (material-void mixture model) with Markov random fields and evaluate the effects of different strengths of spatial regularisation. Our proposals are thoroughly investigated using five different types of cellular metals. The reported results are promising and competitive and speak in favour of the relevance of our proposals. |
| first_indexed | 2024-03-07T22:55:06Z |
| format | Article |
| id | doaj.art-3427725c4bf04f42a0ffd79f04b8dcce |
| institution | Directory Open Access Journal |
| issn | 0264-1275 |
| language | English |
| last_indexed | 2024-04-24T22:21:09Z |
| publishDate | 2024-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Materials & Design |
| spelling | doaj.art-3427725c4bf04f42a0ffd79f04b8dcce2024-03-20T06:08:13ZengElsevierMaterials & Design0264-12752024-03-01239112750A guide to unsupervised image segmentation of mCT-scanned cellular metals with mixture modelling and Markov random fieldsBranislav Panić0Matej Borovinšek1Matej Vesenjak2Simon Oman3Marko Nagode4Faculty of Mechanical Engineering, University of Ljubljana, Aškerčeva ulica 6, Ljubljana, 1000, SloveniaFaculty of Mechanical Engineering, University of Maribor, Smetanova 17, Maribor, 2000, SloveniaFaculty of Mechanical Engineering, University of Maribor, Smetanova 17, Maribor, 2000, SloveniaFaculty of Mechanical Engineering, University of Ljubljana, Aškerčeva ulica 6, Ljubljana, 1000, SloveniaFaculty of Mechanical Engineering, University of Ljubljana, Aškerčeva ulica 6, Ljubljana, 1000, Slovenia; Corresponding author.Characterising the structure of cellular metals is a difficult task. The internal structure of cellular metals can be determined using micro-computed tomography (mCT). However, mCT scanning provides digital images in greyscale with various problematic artefacts. In addition, the grey intensity of cellular metals usually varies greatly due to the internal porosity of the material. Therefore, binary image segmentation to extract material segments from digital images is quite difficult. Our contribution can be summarised as follows. A comprehensive evaluation of various mixture models that have been shown in the literature to be useful for tomography, but for the purpose of binary image segmentation of cellular metals and internal porosity assessment. We propose a novel merging technique to merge different components of the mixture model for the purpose of binary image segmentation of cellular metals. Finally, to enforce spatial regularisation and further improve the binary image segmentation, we combine the obtained two-segment mixture model (material-void mixture model) with Markov random fields and evaluate the effects of different strengths of spatial regularisation. Our proposals are thoroughly investigated using five different types of cellular metals. The reported results are promising and competitive and speak in favour of the relevance of our proposals.http://www.sciencedirect.com/science/article/pii/S0264127524001229Mixture modelSpatial regularisationMarkov random fieldsCellular metalsPorosity |
| spellingShingle | Branislav Panić Matej Borovinšek Matej Vesenjak Simon Oman Marko Nagode A guide to unsupervised image segmentation of mCT-scanned cellular metals with mixture modelling and Markov random fields Materials & Design Mixture model Spatial regularisation Markov random fields Cellular metals Porosity |
| title | A guide to unsupervised image segmentation of mCT-scanned cellular metals with mixture modelling and Markov random fields |
| title_full | A guide to unsupervised image segmentation of mCT-scanned cellular metals with mixture modelling and Markov random fields |
| title_fullStr | A guide to unsupervised image segmentation of mCT-scanned cellular metals with mixture modelling and Markov random fields |
| title_full_unstemmed | A guide to unsupervised image segmentation of mCT-scanned cellular metals with mixture modelling and Markov random fields |
| title_short | A guide to unsupervised image segmentation of mCT-scanned cellular metals with mixture modelling and Markov random fields |
| title_sort | guide to unsupervised image segmentation of mct scanned cellular metals with mixture modelling and markov random fields |
| topic | Mixture model Spatial regularisation Markov random fields Cellular metals Porosity |
| url | http://www.sciencedirect.com/science/article/pii/S0264127524001229 |
| work_keys_str_mv | AT branislavpanic aguidetounsupervisedimagesegmentationofmctscannedcellularmetalswithmixturemodellingandmarkovrandomfields AT matejborovinsek aguidetounsupervisedimagesegmentationofmctscannedcellularmetalswithmixturemodellingandmarkovrandomfields AT matejvesenjak aguidetounsupervisedimagesegmentationofmctscannedcellularmetalswithmixturemodellingandmarkovrandomfields AT simonoman aguidetounsupervisedimagesegmentationofmctscannedcellularmetalswithmixturemodellingandmarkovrandomfields AT markonagode aguidetounsupervisedimagesegmentationofmctscannedcellularmetalswithmixturemodellingandmarkovrandomfields AT branislavpanic guidetounsupervisedimagesegmentationofmctscannedcellularmetalswithmixturemodellingandmarkovrandomfields AT matejborovinsek guidetounsupervisedimagesegmentationofmctscannedcellularmetalswithmixturemodellingandmarkovrandomfields AT matejvesenjak guidetounsupervisedimagesegmentationofmctscannedcellularmetalswithmixturemodellingandmarkovrandomfields AT simonoman guidetounsupervisedimagesegmentationofmctscannedcellularmetalswithmixturemodellingandmarkovrandomfields AT markonagode guidetounsupervisedimagesegmentationofmctscannedcellularmetalswithmixturemodellingandmarkovrandomfields |