Race Classification by Facial Features Using Convolutional Neural Networks and Capsule Networks: A Study on a Multi-Ethnic Dataset
Bibliographic record
Abstract
Determining a person's ethnicity from facial imagery plays a significant role in fields such as biometric authentication, demographic studies, and human-computer interaction.While convolutional neural networks (CNNs) have shown great success in many vision tasks, they often struggle when facial images vary in angle, illumination, or subtle feature arrangement, which can reduce classification reliability.To address this limitation, we developed a hybrid deep learning framework that combines CNN-based face detection with a Capsule Network (CapsNet) classifier, enabling better preservation of spatial relationships among facial features.For this study, we assembled a balanced dataset of 500 images for each ethnic group-African, Asian, and Latino-and expanded it to 3,500 samples using augmentation techniques including rotation, scaling, and controlled adjustments to brightness and contrast.The CNN module handled face detection and cropping, after which the CapsNet module performed the classification.Experimental results showed accuracies of 98% for African, and 97% for both Asian and Latino groups, with macro-averaged precision, recall, and F1-scores all at 0.97.Compared to CNN-only baselines, the proposed approach exhibited greater robustness to pose and lighting variations, while maintaining high performance on a balanced dataset.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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".