“Facekit”—Toward an Automated Facial Analysis App Using a Machine Learning–Derived Facial Recognition Algorithm
Bibliographic record
Abstract
Introduction: Multiple tools have been developed for facial feature measurements and analysis using facial recognition machine learning techniques. However, several challenges remain before these will be useful in the clinical context for reconstructive and aesthetic plastic surgery. Smartphone-based applications utilizing open-access machine learning tools can be rapidly developed, deployed, and tested for use in clinical settings. This research compares a smartphone-based facial recognition algorithm to direct and digital measurement performance for use in facial analysis. Methods: Facekit is a camera application developed for Android that utilizes ML Kit, an open-access computer vision Application Programing Interface developed by Google. Using the facial landmark module, we measured 4 facial proportions in 15 healthy subjects and compared them to direct surface and digital measurements using intraclass correlation (ICC) and Pearson correlation. Results: Measurement of the naso-facial proportion achieved the highest ICC of 0.321, where ICC > 0.75 is considered an excellent agreement between methods. Repeated measures analysis of variance of proportion measurements between ML Kit, direct and digital methods, were significantly different ( F[2,14] = 6-26, P<<.05). Facekit measurements of orbital, orbitonasal, naso-oral, and naso-facial ratios had overall low correlation and agreement to both direct and digital measurements ( R<<0.5, ICC<<0.75). Conclusion: Facekit is a smartphone camera application for rapid facial feature analysis. Agreement between Facekit's machine learning measurements and direct and digital measurements was low. We conclude that the chosen pretrained facial recognition software is not accurate enough for conducting a clinically useful facial analysis. Custom models trained on accurate and clinically relevant landmarks may provide better performance.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".