The Recognizability of Cropped Unilateral Upper Face Photographs
Bibliographic record
Abstract
PURPOSE: Facial photographs are invaluable medical teaching tools, but patient privacy must be respected. The degree to which unilateral cropped upper face photos are recognizable is not known. METHODS: Oculofacial surgeons were canvassed on a societal email to participate in an online study in February 2025. The surgeons were shown 4 famous individuals. Each of the 4 celebrities was presented initially as a cropped unilateral periorbital photograph with an iris mask, then without an iris mask, and then finally as a full face photograph. For each photograph, the surgeons were asked to identify the celebrity and rate how confident they were in the identification. RESULTS: Eighty-seven surgeons completed the study with a response rate of 62%. Overall, the cropped, unilateral upper face photographs of famous celebrities were correctly identified on average 4.9% of the time, with a mean prediction confidence level of 69 ± 15%. Unmasking the iris did not improve recognition. Mistaken identification of the cropped, iris-masked, unilateral upper face photographs occurred approximately 20% of the time. On average, there was a 16.8-fold increase in recognition of the full face of famous celebrities compared with the cropped unilateral upper face photo. CONCLUSION: In the vast majority of cases, the identity of cropped unilateral periorbital photos is not discernible. Notwithstanding, patient informed consent remains mandatory to obtain and use photos for publication.
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 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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.002 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".