A facile methodology to identify microstructural grains on etched surfaces using panoptic segmentation
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The advancement of manufacturing processes demands the deployment of new innovative solutions to control polycrystalline material microstructures in cheap, safe and rapid manner. Analysing polycrystalline microstructures requires grain segmentation, which is typically performed on image data or spatially resolved diffraction data collected from carefully prepared specimens. Recently, machine learning (ML) models have been developed to identify grain boundaries and defects from acquired image data. Despite existing ML-based methods showing an improvement over classical computational methods, there is still a significant structure error due to the necessity to have a high accuracy in detected boundaries to avoid grain misidentification. This investigation deploys a simple and open panoptic model, YOLO (You only look once), to directly identify grains from etched surfaces. The model performance was evaluated after appropriate data preparation and training. Even with a limited number of samples, the model outperformed computational methods like the Canny edge algorithm with an intersection-over-union ( IoU ) score 45 % higher and an aggregated Jaccard index score three times higher. Additionally, an index to measure segmentation quality was introduced, particularly suited for objects with a wide range of sizes, such as microstructural grains. By detecting grains directly instead of relying on boundary detection, common issues—such as failed grains reconstruction due to missing grain boundaries—are avoided, resulting in more accurate grain structures with reduced sensitivity to surface defects. The proposed approach offers significant potential for application to various materials and grain sizes, facilitating the detection of grains, defects, and microstructural artefacts.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it