Gutenberg Open


Titelanzeige

Personen: Khan, Faisal (Autor) 
Enzmann, Frieder (Autor) 
Kersten, Michael (Autor) 
  
Titel: Multi-phase classification by a least-squares support vector machine approach in tomography images of geological samples
  
Dokument:
54508.pdf (3.785 KB) PDF
Quelle: Solid earth. Bd. 7. H. 2. Göttingen : Copernicus Publ. S. 481 - 492
Erscheinungsjahr:    2016
ISBN / ISSN: 1869-9529 ; 1869-9510
URN: urn:nbn:de:hebis:77-publ-545088
URL der Originalveröffentlichung doi:10.5194/se-7-481-2016
  
Dokumentart:
Zeitschriftenaufsatz Zeitschriftenaufsatz
Sprache: Englisch
Open Access: OpenAccess
Person der Universität:    Enzmann, Frieder  In UnivIS suchen ; Kersten, Michael  In UnivIS suchen 
Einrichtung: Institut für Geowissenschaften
DDC-Sachgruppe:    Geowissenschaften
DFG-Fachgebiet: Geologie und Paläontologie
ID: 54508  Universitätsbibliothek Mainz
Hinweis:
Informationen zu den Nutzungsrechten unserer Inhalte Informationen zu den Nutzungsrechten unserer Inhalte
Abstract: Image processing of X-ray-computed polychromatic cone-beam micro-tomography (µXCT) data of geological samples mainly involves artefact reduction and phase segmentation. For the former, the main beam-hardening (BH) artefact is removed by applying a best-fit quadratic surface algorithm to a given image data set (reconstructed slice), which minimizes the BH offsets of the attenuation data points from that surface. A Matlab code for this approach is provided in the Appendix. The final BH-corrected image is extracted from the residual data or from the difference between the surface elevation values and the original grey-scale values. For the segmentation, we propose a novel least-squares support vector machine (LS-SVM, an algorithm for pixelbased multi-phase classification) approach. A receiver operating characteristic (ROC) analysis was performed on BHcorrected and uncorrected samples to show that BH correction is in fact an important prerequisite for accurate multiphase classification. The combination of the two approaches was thus used to classify successfully three different more or less complex multi-phase rock core samples.
   
  
Verfügbarkeit prüfen:    Rechercheportal Mainz: 1869-9529/1869-9510
  KatalogPortal Mainz (inklusive FB 06): 1869-9529/1869-9510
  Elektronische Zeitschriftenbibliothek (EZB): 1869-9529 oder 1869-9510
  URN (urn:nbn:de:hebis:77-publ-545088)
 


Im   
Impressum