Micro-Expression-Based Facial Analysis for Automated Pain Recognition in Dairy Cattle: An Early-Stage Evaluation
Bibliographic record
Abstract
Timely, objective pain recognition in dairy cattle is essential for welfare assurance, productivity, and ethical husbandry, yet remains elusive because evolutionary pressure renders bovine distress signals brief and inconspicuous. Without verbal self‑report, cows suppress overt cues, so automated vision is indispensable for on‑farm triage. Earlier systems tracked whole‑body posture or static grimace scales; frame‑level detection of facial micro‑expressions has not been demonstrated in livestock. We translate micro‑expression analytics from automotive driver monitoring to the barn, linking modern computer vision with veterinary ethology. Our two‑stage pipeline first detects faces and 30 landmarks with a custom YOLOv8‑Pose network, achieving 96.9 % mAP@0.50 for detection and 83.8 % OKS for keypoint placement. Cropped eye, ear, and muzzle patches are encoded by a pretrained MobileNetV2, generating 3 840‑dimensional descriptors that capture millisecond muscle twitches. Sequences of five consecutive frames feed a 128‑unit long short‑term memory classifier that outputs pain probabilities. On a held‑out validation set of 1 700 frames the system records 99.65 % accuracy and an F1‑score of 0.997, with only three false positives and three false negatives. Tested on 14 unseen barn videos, it attains 64.3 % clip‑level accuracy and 83 % precision for the pain class, using a hybrid aggregation rule that combines a 30 % mean‑probability threshold with micro‑burst counting to temper false alarms. These results show that micro‑expression mining can deliver scalable, non‑invasive pain surveillance across variations in illumination, camera angle, background, and individual morphology. Future work will explore attention‑based temporal pooling, curriculum learning for variable window lengths, domain‑adaptive fine‑tuning, and multimodal fusion with accelerometry to elevate performance toward clinical deployment.
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 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".