Recognizing Human Races through Machine Learning—A Multi-Network, Multi-Features Study
Open accessThe DOI matches its Crossref record; 57 of the 57 references it cites were found in a registry or an index.
Abstract
The human face holds a privileged position in multi-disciplinary research as it conveys much information—demographical attributes (age, race, gender, ethnicity), social signals, emotion expression, and so forth. Studies have shown that due to the distribution of ethnicity/race in training datasets, biometric algorithms suffer from “cross race effect”—their performance is better on subjects closer to the “country of origin” of the algorithm. The contributions of this paper are two-fold: (a) first, we gathered, annotated and made public a large-scale database of (over 175,000) facial images by automatically crawling the Internet for celebrities’ images belonging to various ethnicity/races, and (b) we trained and compared four state of the art convolutional neural networks on the problem of race and ethnicity classification. To the best of our knowledge, this is the largest, data-balanced, publicly-available face database annotated with race and ethnicity information. We also studied the impact of various face traits and image characteristics on the race/ethnicity deep learning classification methods and compared the obtained results with the ones extracted from psychological studies and anthropomorphic studies. Extensive tests were performed in order to determine the facial features to which the networks are sensitive to. These tests and a recognition rate of 96.64% on the problem of human race classification demonstrate the effectiveness of the proposed solution.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures






























Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“In [4], the authors developed and made available a large-scale library of over 175,000 photos of faces of celebrities from multiple ethnicities and races, which were used for training and testing.”
From Face Recognition Based on Deep Learning and FPGA for Ethnicity Identification (2022) · cites this paper as [4]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 9×
“The best results are obtained by the Inception Resnet-v2 network (96.36% accuracy).”
MethodInfluentialVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 2×
“The Visual Geometry Group (VGG) from the Oxford University [22] performed a thorough evaluation of CNNs and their performance, by modifying and evaluating the performance of the VGG architecture by iteratively increasing its depth, that is, adding more convolutional layers (up to 19 layers).”
MethodImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“In order to make this approach feasible, the size of the convolutional layers was significantly reduced (to 3 × 3 convolutional filters with 1 stride in all layers, as opposed to 11 × 11 receptive field with stride 4 in [29]).”
MethodImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 1×
“SENet architecture [24] is ranked first in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) in 2017 [26], bringing a relative improvement of roughly 25% over the winner of the previous year.”
BackgroundSqueeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00474 · Cited by 28,755 · cited 1×
“Its successor, Mobilenet v2 [35] further improves the by introducing the inverted residual block.”
BackgroundBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 1×
“The original architecture was iteratively improved [32,33], until the latest version Inception-v4 [23], which achieved 3.”
MethodRobust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., et al. (2016) · arXiv · doi:10.48550/arxiv.1603.04467 · Cited by 9,408 · cited 1×
“The code was written in python, and the CNNs were trained on Nvidia Tesla K40 GPUs using Google‘s tensorflow framework [46].”
Method
Research works printed but not linked: 2
- Tin, H.H.K., and Sein, M.M. (2013, January 21–23). Automatic Race Identification from Face Images in Myanmar. Proceedings of the The First International Conference on Energy Environment and Human Engineering (ICEEHE 2013), Yangon, Myanmar.
- Howard, A., Sandler, M., Chu, G., Chen, L.C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for mobilenetv3. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Korea.
Cited by
Intelligent deep learning based ethnicity recognition and classification using facial images
Sunitha, G., Geetha, K., Neelakandan, S., Pundir, A. K. S., Hemalatha, S., & Kumar, V. (2022) · Image and Vision Computing · doi:10.1016/j.imavis.2022.104404 · Cited by 91
Face Recognition Based on Deep Learning and FPGA for Ethnicity Identification
AlBdairi, A. J. A., Xiao, Z., Alkhayyat, A., Humaidi, A. J., Fadhel, M. A., Taher, B. H., Alzubaidi, L., Santamaría, J., & Al-Shamma, O. (2022) · Applied Sciences · doi:10.3390/app12052605 · Cited by 54
Performance Analysis of Long Short-Term Memory Predictive Neural Networks on Time Series Data
Bolboacă, R., & Haller, P. (2023) · Mathematics · doi:10.3390/math11061432 · Cited by 58
Miao, H., Zhang, Y., Wang, D., & Feng, S. (2021) · Mathematics · doi:10.3390/math9121437 · Cited by 25
Automatic Ethnicity Classification from Middle Part of the Face Using Convolutional Neural Networks
Belcar, D., Grd, P., & Tomičić, I. (2022) · Informatics · doi:10.3390/informatics9010018 · Cited by 32
Development of Apple Detection System and Reinforcement Learning for Apple Manipulator
Andriyanov, N. A. (2023) · Electronics · doi:10.3390/electronics12030727 · Cited by 22
Surveying Racial Bias in Facial Recognition: Balancing Datasets and Algorithmic Enhancements
Sumsion, A. W., Torrie, S. A., Lee, D.-J., & Sun, Z. (2024) · Electronics · doi:10.3390/electronics13122317 · Cited by 23
Optimal deep transfer learning based ethnicity recognition on face images
Obayya, M. I., Alotaibi, S. S., Dhahb, S., Alabdan, R., Duhayyim, M. A., Hamza, M. A., Rizwanullah, M., & Motwakel, A. (2022) · Image and Vision Computing · doi:10.1016/j.imavis.2022.104584 · Cited by 17
Chaudhary, M., Kosyluk, K. A., Thomas, S. W., & Neal, T. J. (2023) · Scientific Reports · doi:10.1038/s41598-023-37592-1 · Cited by 13
“The CNN model achieved an 85% macro-average F 1 score on the FaceARG dataset and an 89% macro-average F 1 score on the UTKFace dataset.”
InfluentialZhang, T., Zhang, X., Liu, X., Guo, Z., & Tian, Y. (2024) · Journal of Software Engineering and Applications · doi:10.4236/jsea.2024.1712046 · Cited by 7
Fine-Grained Facial Ethnicity Recognition Based on Dual Convolutional Autoencoders
Ng, W. W. Y., Zhou, Z., & Wang, T. (2021) · International Conference on Intelligent Control and Information Processing · doi:10.1109/icicip53388.2021.9642208 · Cited by 5
Advancing Gender, Age and Ethnicity with YOLOv5 and Transfer Learning
Bhattacharya, V., & Tripathy, B. K. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-66410-6_23 · Cited by 4
Gender Classification Using CNN Transfer Learning and Fine-Tuning
Mustapha, M. F., Mohamad, N. M., & Hamid, S. H. A. (2023) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-99-0741-0_7 · Cited by 4
Multimodal Emotion Recognition with Factorized Bilinear Pooling and Adversarial Learning
Miao, H., Zhang, Y., Wang, D., & Feng, S. (2021) · International Conference on Computer Science and Application Engineering (CSAE) · doi:10.1145/3487075.3487164 · Cited by 4
Toward Intelligent Ethnicity Recognition and Face Anonymization: An IncepX-Ensemble Model
Jamil, F., & Jamil, H. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70819-0_19 · Cited by 2
Mustapha, M. F., Mohamad, N. M., Hamid, S. H. A., & Aziz, N. A. S. A. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-9005-4_62 · Cited by 2
A NEW MODEL FOR HUMAN ETHNICITY PREDICTION FROM FACIAL IMAGES
El-fatah, M. A., Sayed, H. Y. A.-N., & Taie, S. A. (2023) · Labyrinth : Fayoum University Journal Of Science and Interdisciplinary Studies · doi:10.21608/ifjsis.2023.217835.1030 · Cited by 1
Gone With the Bits: Revealing Racial Bias in Low-Rate Neural Compression for Facial Images
Qiu, T., Nichani, A., Tadayontahmasebi, R., & Jeong, H. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732124 · Cited by 3
Arab Face Recognition and Identification Based on Ethnicity and Gender Using Machine Learning
Abual-Rub, M. S., Nahar, K. M. O., Almomani, A., & AlZobi, F. I. (2025) · The International Arab Journal of Information Technology · doi:10.34028/iajit/22/4/5 · Cited by 2
Gone With the Bits: Revealing Racial Bias in Low-Rate Neural Compression for Facial ImagesPreprint
Qiu, T., Nichani, A., Tadayontahmasebi, R., & Jeong, H. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.02949 · Cited by 1
“Datasets: We train all neural compression models on the CelebA [22], FaceARG [23], and FairFace [24] datasets.”
A Comprehensive Review in Using the Advances of Deep Learning in the 3D Race Classification
Reda, N. H., & Abbas, H. H. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-35442-7_5
Lee, J.-H., & Kisang, S. (2025) · The Journal of Korean Association of Computer Education · doi:10.32431/kace.2025.28.1.002
Gone with the Bits: Revealing Racial Bias in Low-Rate Neural Compression for Facial Images
Qiu, T., Nichani, A., Tadayontahmasebi, R., & Jeong, H. (2025) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit63088.2025.11195694
“Datasets: We train all neural compression models on the CelebA [22], FaceARG [23], and FairFace [24] datasets.”
Multimodal Demographic Prediction: A Transfer Learning Framework with EfficientNet Model
Gehlot, L., Pooja, A., Kumar, E. R., Mohammad, M., Sambangi, S., & Kathirisetty, N. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-0269-1_121
Global soft biometrics in surveillance: benchmark in the field & open challenges
Hassan, B., Soudbakhsh, H., Bahrami, S., Das, S. R., Patel, P., Yasin, A., & Khan, U. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21204-x
Diversity Snapshots: Intermodal Analysis of Firm Diversity Discourse
Gagnon, J., & Mansurov, A. (2026) · Intelligent systems in accounting, finance and management/Intelligent systems in accounting, finance & management · doi:10.1002/isaf.70035
Metadata
- Authors
- Darabant, A. S., Borza, D., & Danescu, R.
- Affiliations
- Computer Science Department, Babes Bolyai University, 1st Mihail Kogălniceanu Street, 400084 Cluj-Napoca, Romania
- Babeș-Bolyai University (RO)
- Technical University of Cluj-Napoca (RO)
- Corresponding author
- Borza, Diana
- Venue
- Mathematics
- Publisher
- MDPI AG
- Published
- 2021-01-19
- Volume
- 9
- Issue
- 2
- Pages
- 195
- ISSN
- 2227-7390 (ISSN-L)
- OpenAlex
- W3122359801
- Cited by
- 24
- References
- 49
- Citations by year
- 2026: 2 · 2025: 4 · 2024: 5 · 2023: 6 · 2022: 4 · 2021: 3
- FWCI
- 1.62
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Mathematics (publishedVersion, cc-by)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face and Expression Recognition
- Life Sciences › Neuroscience › Cognitive Neuroscience › Face Recognition and Perception
- Keywords
- racial classification, ethnic classification, face images, cross-race effect, convolutional neural networks, facial image database, celebrity image, image annotation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.