Tomography analysis tool: an application for image analysis based on unsupervised machine learning

Article Article scientifique Article Tomography analysis tool: an application for image analysis based on unsupervised machine learning eng 2022-02-24 2022-02-24 author Bagni Tommaso 0000-0001-8654-783X 929717 author Haldi Hugo Maximilien 877999 author Mauro Diego 0000-0002-8290-1165 839317 author Senatore Carmine 0000-0002-9191-5016 561307 015201 10.1088/2633-1357/ac54bf 2633-1357 https://iopscience.iop.org/article/10.1088/2633-1357/ac54bf We developed a graphical user interface (GUI) to analyse tomographic images of superconducting Nb 3 Sn wires designed for the next generation accelerator magnets. The Tomography Analysis Tool (TAT) relies on the k -means algorithm, an unsupervised machine learning technique which is widely used to partition images into separated clusters. The GUI is compatible with both Linux and Windows operating systems. The software reliability was tested by optical inspecting the tomographic images superimposed on the clustered image obtained by the k-means algorithm. TAT was proven to correctly segment the various components of the Nb 3 Sn superconducting wires with single pixel precision. Finally, this software can be a useful tool for the scientific community to segment and analyse quickly and reproducibly tomographic images. Dewey 025.063 Dewey 500.2 33 Département de physique de la matière quantique 131 32 Département d'informatique 18 false 679 Groupe Senatore IOP SciNotes 3 1 a5026b58-ee5f-4c05-8d04-3eb6d9392492 Article (Published version) Public Bagni_2022_IOP_SciNotes_3_015201.pdf 3575342 application/pdf CC BY openAccess Faculté des sciences / Section de physique / Département de physique de la matière quantique Faculté des sciences / Département d'informatique

Title	Published in	Access level	OA Policy	Year	Views	Downloads

Tomography analysis tool: an application for image analysis based on unsupervised machine learning	IOP SciNotes			2022	317	116

Archive ouverte UNIGE

Haldi, Hugo Maximilien