A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Grain Boundary Detection and Phase Segmentation of SEM Ferrite–Pearlite Microstructure Using SLIC and Skeletonization
Abstract In this paper, we report an efficient segmentation and grain boundary detection process using modern image processing operators like simple linear iterative clustering and skeletonization. Accurate phase segmentation is the major requirement for any phase identification and quantification operations. The proposed image processing methods have been experimented on the in-house generated 48 scanning electron microscopy (SEM) microstructures obtained from plain carbon steel samples containing 0.1, 0.22, 0.35 and 0.48 wt%C and have been subjected to both annealing and normalizing treatments. The microstructures for dataset have been captured in SEM using secondary electron mode over a wide range of magnification × 500–× 5000. The experimental results significantly validate the segmentation of ferrite and pearlite regions. Also, the grain boundary detection results appear to be plausibly effective in case of ferrite–ferrite and ferrite–pearlite boundaries. However, the grain boundary detection efficiency is found to be relatively poor in case of pearlite–pearlite boundary. The overall performance of the proposed image processing technique in context of ferrite–pearlite steel SEM images shows promising results in all circumstances of compositional range, heat treatment and magnification.
Grain Boundary Detection and Phase Segmentation of SEM Ferrite–Pearlite Microstructure Using SLIC and Skeletonization
Abstract In this paper, we report an efficient segmentation and grain boundary detection process using modern image processing operators like simple linear iterative clustering and skeletonization. Accurate phase segmentation is the major requirement for any phase identification and quantification operations. The proposed image processing methods have been experimented on the in-house generated 48 scanning electron microscopy (SEM) microstructures obtained from plain carbon steel samples containing 0.1, 0.22, 0.35 and 0.48 wt%C and have been subjected to both annealing and normalizing treatments. The microstructures for dataset have been captured in SEM using secondary electron mode over a wide range of magnification × 500–× 5000. The experimental results significantly validate the segmentation of ferrite and pearlite regions. Also, the grain boundary detection results appear to be plausibly effective in case of ferrite–ferrite and ferrite–pearlite boundaries. However, the grain boundary detection efficiency is found to be relatively poor in case of pearlite–pearlite boundary. The overall performance of the proposed image processing technique in context of ferrite–pearlite steel SEM images shows promising results in all circumstances of compositional range, heat treatment and magnification.
Grain Boundary Detection and Phase Segmentation of SEM Ferrite–Pearlite Microstructure Using SLIC and Skeletonization
Gupta, Subir (author) / Sarkar, Jit (author) / Banerjee, Abhijit (author) / Bandyopadhyay, N. R. (author) / Ganguly, Subhas (author)
Journal of The Institution of Engineers (India): Series D ; 100 ; 203-210
2019-08-03
8 pages
Article (Journal)
Electronic Resource
English
| British Library Online Contents | 1994
Micromechanical modeling of ferrite-pearlite steels
| British Library Online Contents | 2010
Alternatives to the Ferrite-Pearlite Microstructures
| British Library Online Contents | 1998
Effect of Cooling History on Yield Ratio of Fine-grain Ferrite/Pearlite Steel
| British Library Online Contents | 2005
| TIBKAT | 1991