Back to Search
Start Over
Deep learning for improving non-destructive grain mapping in 3D
- Source :
- IUCrJ, Fang, H, Hovad, E, Zhang, Y, Clemmensen, L K H, Kjaer Ersbøll, B & Juul Jensen, D 2021, ' Deep learning for improving non-destructive grain mapping in 3D ', IUCrJ, vol. 8, pp. 719-731 . https://doi.org/10.1107/S2052252521005480, IUCrJ, Vol 8, Iss 5, Pp 719-731 (2021)
- Publication Year :
- 2021
- Publisher :
- International Union of Crystallography, 2021.
-
Abstract
- A deep learning neural network has been developed to efficiently and accurately clean the background noise in experimental lab-based X-ray diffraction images. A better spot segmentation is obtained and thus grain mapping in 3D is improved compared with the conventional method.<br />Laboratory X-ray diffraction contrast tomography (LabDCT) is a novel imaging technique for non-destructive 3D characterization of grain structures. An accurate grain reconstruction critically relies on precise segmentation of diffraction spots in the LabDCT images. The conventional method utilizing various filters generally satisfies segmentation of sharp spots in the images, thereby serving as a standard routine, but it also very often leads to over or under segmentation of spots, especially those with low signal-to-noise ratios and/or small sizes. The standard routine also requires a fine tuning of the filtering parameters. To overcome these challenges, a deep learning neural network is presented to efficiently and accurately clean the background noise, thereby easing the spot segmentation. The deep learning network is first trained with input images, synthesized using a forward simulation model for LabDCT in combination with a generic approach to extract features of experimental backgrounds. Then, the network is applied to remove the background noise from experimental images measured under different geometrical conditions for different samples. Comparisons of both processed images and grain reconstructions show that the deep learning method outperforms the standard routine, demonstrating significantly better grain mapping.
- Subjects :
- Diffraction
Fine-tuning
Computer science
0211 other engineering and technologies
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
02 engineering and technology
Background noise
tomography
Biochemistry
computer vision
03 medical and health sciences
Grain mapping
grain mapping
General Materials Science
Segmentation
spot segmentation
Tomography
030304 developmental biology
021102 mining & metallurgy
0303 health sciences
Crystallography
Artificial neural network
business.industry
Deep learning
Spot segmentation
background noise
deep learning
Pattern recognition
General Chemistry
Condensed Matter Physics
Research Papers
Characterization (materials science)
X-ray diffraction
QD901-999
Computer vision
Artificial intelligence
business
LabDCT
Subjects
Details
- Language :
- English
- ISSN :
- 20522525
- Volume :
- 8
- Issue :
- Pt 5
- Database :
- OpenAIRE
- Journal :
- IUCrJ
- Accession number :
- edsair.doi.dedup.....c46f3bf5ad4797b0da7be869884bd205