2018
DOI: 10.1049/iet-ipr.2016.0842
|View full text |Cite
|
Sign up to set email alerts
|

Investigating local orientation methods to segment microstructure with 3D solid texture

Abstract: This study investigates local orientation-based approaches to the complex problem of pattern segmentation in threedimensional (3D) texture image. The current problem focuses on the extraction of so-called lamellar colonies in titanium alloy, which, from the materials science and engineering point of view, are microstructural features that play a fundamental role on crack propagation and bifurcation during mechanical loading. Methods based on local orientation estimation extend the notion of using local gradien… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2018
2018
2024
2024

Publication Types

Select...
1
1

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(1 citation statement)
references
References 36 publications
0
1
0
Order By: Relevance
“…Interesting feature is that the reconstructed images based analysis outperform both compared methods for low flow rates while is giving worse results for more dynamic flow regimes while the other two gain more accuracy for higher flow rates. It will be interesting to verify performance of the proposed model for a truly large data sample, especially of mixed origins of different experimental installations [23] [24]. On the other hand, it is noticeable that CDPM beats direct estimation based on raw data records by a small difference yet with much lower variance as well.…”
Section: B Discussion and Directions For Future Workmentioning
confidence: 95%
“…Interesting feature is that the reconstructed images based analysis outperform both compared methods for low flow rates while is giving worse results for more dynamic flow regimes while the other two gain more accuracy for higher flow rates. It will be interesting to verify performance of the proposed model for a truly large data sample, especially of mixed origins of different experimental installations [23] [24]. On the other hand, it is noticeable that CDPM beats direct estimation based on raw data records by a small difference yet with much lower variance as well.…”
Section: B Discussion and Directions For Future Workmentioning
confidence: 95%