3D Human Facial Traits’ Analysis for Ethnicity Recognition Using Deep Learning
Bibliographic record
Abstract
Among different recent technologies proposed for human face classification and recognition, solutions based on analyzing the 3D geometric facial features emerged as a promising academic and practical direction.Researchers have examined both holistic and local approaches to analyzing the 3D face regions to study the impact of facial features in real-life applications such as medical and security implementations.However, a few works have investigated the relevant impact of the extracted geometric features from the descriptive local regions of the human face on identifying human ethnicity.This work proposes a classifier to categorize individuals into their distinctive ethnic groups and deeply analyzes the facial feature variations to highlight the most descriptive parts and features of the human face in race classification.The proposed ML-based classifier is preceded by extracting the 3D facial features from 3D meshes using the recent SIFT and Geodesic distance calculations.In addition, it implements and discusses the initial important preprocessing steps including, cropping the frontal parts, correcting the head pose, selecting the suitable initial key points, aligning the 3D meshes, and implementing the suitable template-based 3D registration.The proposed NN race classifiers are built and evaluated using Headspace, a well-known multi-ethnic dataset, and achieved high accuracy (90% globally, and 100% for the mouth area) especially while using the SIFT features.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".