.png){kind=icon}
.png){kind=icon}
Return
Human perception-inspired grain segmentation refinement using conditional random fields
.png){kind=icon}
OA
AI
DOI：10.1016/j.matchar.2025.115694.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Enhanced Accuracy: The post-processing method significantly improves segmentation accuracy, verified by IoU and DSC metrics. • Time Efficiency: Drastically reduces segmentation time vs. manual labeling, enabling rapid analysis for in-situ experiments. • New Grain Alignment Metric: Provides a more robust accuracy measure for segmented region accuracy, especially for thin masks. • Applicability Across Domains: Robust post-processing method is generalizable to a wide range of crystalline materials.
Keywords:
Grain segmentation
Grain boundary networks
Computer vision
Conditional random fields
Microstructure
Electron microscopy
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
5.5
Papers:
1.1W
Citations:
3.4W