Real time contaminants detection in wood panel manufacturing process using YOLO algorithms
Bibliographic record
Abstract
Recent technological advancements have significantly increased the autonomy of daily tasks within industries. These technologies are currently enabling the accomplishment of tasks previously deemed impossible for humans, such as continuous surveillance and detection of contamination at any stage of the production chain. For instance, in wood panel manufacturing, where metal particles may inadvertently be introduced before pressing the panel, causing wear and failure of pressing and cutting tools. This paper presents a methodology utilizing the YOLO (You Only Look Once) algorithms, to detect contaminants in the wood panel manufacturing chain. A combination of seven image quality degradation methods is proposed to increase the difficulty of detecting the objects. Resulting in the development of a detection tool with enhanced generalization capabilities. The results were compared using degraded and regular training datasets. It is demonstrated that training on degraded images improve precision, recall, mAP50, and mAP50-95. YOLOv9 surpasses all examined models, achieving a F1 score of 99.8%. An experimental investigation is also conducted to showcase the effectiveness of the YOLOv9 trained with a degraded dataset present a good capability for real object detection with the highest F1 score of 98%. The results with real data exhibit a strong agreement with numerical results.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".