SFC-YOLOv8: Enhanced Strip Steel Surface Defect Detection Using Spatial-Frequency Domain-Optimized YOLOv8
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
Steel strips, renowned for their exceptional strength, durability, and impact resistance, are ubiquitous in various manufacturing sectors, notably aerospace, shipbuilding, and automotive industries. However, surface defects on these strips are inevitable due to various factors, including processing and environmental conditions. As a result, the efficient detection of these defects is paramount. This study introduces SFC-YOLOv8, a novel method for detecting surface defects on steel strips that leverages an improved YOLOv8 framework in the spatial-frequency domain. Initially, by exploiting the distinct high-frequency features of defect images, we extract mixed spatial-frequency domain features before applying YOLOv8, enhancing its sensitivity to low-contrast defects. Furthermore, we incorporate a global-local information-enhanced attention module into YOLOv8’s neck, which integrates high-frequency, low-frequency, and local perceptual information to capture defect features more effectively, boosting the model’s capability to detect minute and subtle defects. Additionally, we propose a frequency domain feature adaptive module that adaptively adjusts the soft threshold based on image frequency domain information, filtering out background noise while preserving the underlying semantic information of the image, thereby enhancing defect detection precision under varying lighting conditions. Comparative evaluations with conventional detection methods reveal that SFC-YOLOv8 achieves a mean average precision of 85.6%, a detection speed of 203 frames per second, and a compact model parameter of 4.36 MB, showcasing its superior overall performance. Ablation studies further confirm that SFC-YOLOv8 outperforms traditional YOLOv8 by enhancing detection precision by 6.6%.
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 | 0.001 |
| Science and technology studies | 0.001 | 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