Face Recognition Based on Deep Learning and FPGA for Ethnicity Identification
Open accessThe DOI matches its Crossref record; 52 of the 52 references it cites were found in a registry or an index; 8 of the 16 sources its claims cite were checked for support.
Abstract
In the last decade, there has been a surge of interest in addressing complex Computer Vision (CV) problems in the field of face recognition (FR). In particular, one of the most difficult ones is based on the accurate determination of the ethnicity of mankind. In this regard, a new classification method using Machine Learning (ML) tools is proposed in this paper. Specifically, a new Deep Learning (DL) approach based on a Deep Convolutional Neural Network (DCNN) model is developed, which outperforms a reliable determination of the ethnicity of people based on their facial features. However, it is necessary to make use of specialized high-performance computing (HPC) hardware to build a workable DCNN-based FR system due to the low computation power given by the current central processing units (CPUs). Recently, the latter approach has increased the efficiency of the network in terms of power usage and execution time. Then, the usage of field-programmable gate arrays (FPGAs) was considered in this work. The performance of the new DCNN-based FR method using FPGA was compared against that using graphics processing units (GPUs). The experimental results considered an image dataset composed of 3141 photographs of citizens from three distinct countries. To our knowledge, this is the first image collection gathered specifically to address the ethnicity identification problem. Additionally, the ethnicity dataset was made publicly available as a novel contribution to this work. Finally, the experimental results proved the high performance provided by the proposed DCNN model using FPGAs, achieving an accuracy level of 96.9 percent and an F1 score of 94.6 percent while using a reasonable amount of energy and hardware resources.
Overview
CoChat Summary
TL;DR
The paper proposes a deep convolutional neural network for ethnicity identification from facial images and implements it on an FPGA DE1-SoC, comparing it with GPU execution and four pre-trained CNNs. It reports 96.9% accuracy and 94.6% F1 on a new 3,141-image dataset of Chinese, Pakistani, and Russian faces.
Key findings
- The proposed network achieved accuracy 0.969 and F1 score 0.946, outperforming ResNet50 (0.949 accuracy, 0.924 F1), DenseNet (0.957, 0.934), AlexNet (0.879, 0.799), and GoogleNet (0.940, 0.904) in Table 2.
- On the FPGA DE1-SoC, the proposed network’s execution time and power consumption were reported as 2.76 s and 10.7 W, compared with 5.21 s and 650 W on GPU (Table 3).
- The new dataset contained 3,141 face photographs: 1,081 Chinese, 1,021 Pakistani, and 1,039 Russian images, split into 60% training, 10% validation, and 30% test.
- The FPGA implementation used 25,671 total logic elements, 96,734 total block memory bits, and 64,523 total logic registers (Table 4).
Methods
- A new DCNN proposal with twelve deep learning layers: four convolutional layers each followed by max-pooling, dropout layers, two fully connected layers, a drop-connect layer, a flattening layer, and a SoftMax output layer; input images are 128 × 128 × 3 with 3 × 3 patches and stride 1.
- The dataset was collected from three countries and compared against four pre-trained CNN models—ResNet50, DenseNet, AlexNet, and GoogleNet—with the last four layers of each frozen; training used an Intel Core i7-10750H CPU, NVIDIA GeForce RTX 2070 GPU, and 16 GB RAM.
- FPGA acceleration used an FPGA DE1-SoC with a 64-computation array of 16-bit DSP; due to FPGA fabric limits, only 13 convolutional layers were employed. Evaluation included accuracy, F1, sensitivity, specificity, precision, false positive rate, execution time, power consumption, and DE1-SoC resource usage.
Limitations
- The paper states that a direct numerical comparison against all state-of-the-art methods was not feasible because several were trained and assessed on inaccessible private datasets.
- The paper states that only 13 convolutional layers were used because of the limits of FPGA fabrics on DE1-SoC.
- Evident from the text: the dataset is limited to 3,141 images from three national/ethnic groups (Chinese, Pakistani, Russian), and no cross-dataset or broader demographic validation is reported, so generalization to other ethnicities or conditions is untested.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures




















Verification
Claims the paper makes
7 Valid · 4 Not valid · 7 Not checked · 34 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The reported results in Table 1 demonstrated the higher performance achieved by our method with an accuracy rate of 96.9 percent.”
- Also stated in: § 6. Conclusions and Future Works · plain
“The experimental results reported that our model outperformed all the methods of state-of-the-art, achieving an accuracy and F1 score value of 96.9 percent and 94.6 percent, respectively.”
§ Face Recognition Based on Deep Learning and FPGA for Ethnicity Identification > 5.3. A Preliminary Comparitive Analysis
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 6. Conclusions and Future Works · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The accuracy and F1 score both reached a ratio rate of 96.9 percent and 94.6 percent, respectively.”
- Also stated in: § 6. Conclusions and Future Works · plain
“The experimental results reported that our model outperformed all the methods of state-of-the-art, achieving an accuracy and F1 score value of 96.9 percent and 94.6 percent, respectively.”
§ Face Recognition Based on Deep Learning and FPGA for Ethnicity Identification > 5.4. Comparison for the Pre-Trained CNNs
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 6. Conclusions and Future Works · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Additionally, the ethnicity dataset was made publicly available as a novel contribution to this work.”
§ Face Recognition Based on Deep Learning and FPGA for Ethnicity Identification > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“AlexNet offers the lowest power usage and execution time due to its basic design.”
§ Face Recognition Based on Deep Learning and FPGA for Ethnicity Identification > 5.4. Comparison for the Pre-Trained CNNs
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A network proposal was used to group the human face by its race, specifically from Chinese, Pakistani, and Russian citizens;”
§ Face Recognition Based on Deep Learning and FPGA for Ethnicity Identification > 1. Introduction
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on 2 assumptions not shown here.
11 more claims
Create a free account to see all 52 claims and to verify the 3 references still open.
- It may state two separate claims as one. 19
- Probably not a substantial claim. 21
- The quote only partly states this claim. 1
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00444-8 · Cited by 7,906
Self-citationShin, H.-C., Roth, H. R., Gao, M., Lu, L., Xu, Z., Nogues, I., Yao, J., Mollura, D., & Summers, R. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2528162 · Cited by 5,759
Shin, H.-C., Roth, H. R., Gao, M., Lu, L., Xu, Z., Nogues, I., Yao, J.-H., Mollura, D., & Summers, R. (2016) · IEEE Transactions on Medical Imaging · doi:10.48550/arxiv.1602.03409 · Cited by 5,217
Efficient Processing of Deep Neural Networks: A Tutorial and Survey
Sze, V., Chen, Y.-H., Yang, T.-J., & Emer, J. S. (2017) · Proceedings of the IEEE · doi:10.1109/jproc.2017.2761740 · Cited by 4,215
Fully Convolutional Networks for Semantic Segmentation
Long, J., Shelhamer, E., & Darrell, T. J. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1411.4038 · Cited by 2,489
A convolutional neural network cascade for face detection
Li, H., Lin, Z., Shen, X., Brandt, J., & Hua, G. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299170 · Cited by 1,390
An improved deep learning architecture for person re-identification
Ahmed, E., Jones, M., & Marks, T. K. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299016 · Cited by 1,248
Human activity recognition with smartphone sensors using deep learning neural networks
Ronao, C. A., & Cho, S.-B. (2016) · Expert Systems with Applications · doi:10.1016/j.eswa.2016.04.032 · Cited by 1,215
Cited by
Alzubaidi, L., Bai, J., Al-Sabaawi, A., Santamaría, J., Albahri, A. S., Al-dabbagh, B. S. N., Fadhel, M. A., Manoufali, M., Zhang, J., Al-Timemy, A. H., et al. (2023) · Journal of Big Data · doi:10.1186/s40537-023-00727-2 · Cited by 907
Self-citationA Novel Deep Learning Approach for Deepfake Image Detection
Raza, A., Munir, K., & Almutairi, M. (2022) · Applied Sciences · doi:10.3390/app12199820 · Cited by 220
Quantum convolutional neural network based on variational quantum circuits
Gong, L.-H., Pei, J.-J., Zhang, T.-F., & Zhou, N.-R. (2024) · Optics Communications · doi:10.1016/j.optcom.2023.129993 · Cited by 165
Zhu, X., Liu, Z., Cambria, E., Yu, X., Fan, X., Chen, H., & Wang, R. (2024) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2024.108564 · Cited by 159
Alzubaidi, L., Al-Dulaimi, K., Salhi, A., Alammar, Z., Fadhel, M. A., Albahri, A. S., Alamoodi, A. H., Albahri, O. S., Hasan, A. F., Bai, J., et al. (2024) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2024.102935 · Cited by 84
Self-citationRehman, A. U., Mujahid, M., Elyassih, A., Alghofaily, B., & Bahaj, S. A. (2025) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.058036 · Cited by 51
Facial Emotion Recognition in-the-Wild Using Deep Neural Networks: A Comprehensive Review
Boughanem, H., Ghazouani, H., & Barhoumi, W. (2023) · SN Computer Science · doi:10.1007/s42979-023-02423-7 · Cited by 38
Kadhim, S. M., Paw, J. K. S., Tak, Y. C., & Al‐Latief, S. T. A. (2024) · Journal of Smart Internet of Things · doi:10.2478/jsiot-2024-0007 · Cited by 29
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
Wang, Y., Liu, J., Xu, L., Yu, F., & Zhang, S. (2023) · Water · doi:10.3390/w15071422 · Cited by 14
Automatic Segmentation of Facial Regions of Interest and Stress Detection Using Machine Learning
Jaramillo-Quintanar, D., Gómez-Reyes, J. K., Morales-Hernandez, L. A., Trejo, B. D., Medina, D. A. R., & Cruz-Albarrán, I. A. (2023) · Sensors · doi:10.3390/s24010152 · Cited by 17
Hardware Design of Lightweight Binary Classification Algorithms for Small-Size Images on FPGA
Saglam, S., & Bayar, S. (2024) · IEEE Access · doi:10.1109/access.2024.3390564 · Cited by 9
Indriyani, I., Giriantari, I. A. D., Sudarma, M., & Widyantara, I. M. O. (2023) · Journal of Wireless Mobile Networks Ubiquitous Computing and Dependable Applications · doi:10.58346/jowua.2023.i2.004 · Cited by 6
An Intelligent Human Pose Detection Comparing with Random forest and Recurrent Neural Network
Kumar, R. N., Surendran, R., & Madhusundar., N. (2024) · International Conference on Electronics, Communication and Aerospace Technology (ICECA) · doi:10.1109/iceca63461.2024.10800936 · Cited by 6
City Architectural Color Recognition Based on Deep Learning and Pattern Recognition
Zhuang, Y., & Guo, C. (2023) · Applied Sciences · doi:10.3390/app132011575 · Cited by 7
Zayed, N. M., Tawfik, N., Mahmoud, M. M. A., Fawzy, A. M., Cho, Y. I., & Abdallah, M. S. (2025) · AI · doi:10.3390/ai6010008 · Cited by 7
Multiple Face Detection and Recognition for System-an-Chip FPGAs
Santiwiwat, S., Hajian, A., Ruangsang, W., et al. (2024) · International Joint Conference on Computer Science and Software Engineering · doi:10.1109/jcsse61278.2024.10613695 · Cited by 4
Real-Time Analysis of Facial Expressions for Mood Estimation
Filippini, J. S., Varona, J., & Manresa-Yee, C. (2024) · Applied Sciences · doi:10.3390/app14146173 · Cited by 4
TraceGuard: Fine-Tuning Pre-Trained Model by Using Stego Images to Trace Its User
Zhou, L., Ren, X., Qian, C., & Sun, G. (2024) · Mathematics · doi:10.3390/math12213333 · Cited by 3
3D Human Facial Traits’ Analysis for Ethnicity Recognition Using Deep Learning
Reda, N. H., & Abbas, H. H. (2024) · Ingénierie des systèmes d information · doi:10.18280/isi.290211 · Cited by 3
Security Technologies Using Facial Recognition
Salama, R., & Nour, M. (2023) · Global Journal of Computer Sciences Theory and Research · doi:10.18844/gjcs.v13i1.8294 · Cited by 2
Yu, Y., Virupakshappa, K., & Oruklu, E. (2023) · Journal of Signal Processing Systems · doi:10.1007/s11265-023-01901-8 · Cited by 4
Yu, X., Lu, C., Park, E., et al. (2025) · Remote Sensing · doi:10.3390/rs17060988 · Cited by 1
Explainable Deep Fake Framework for Images Creation and Classification
Alwateer, M. M. (2024) · Journal of Computer and Communications · doi:10.4236/jcc.2024.125006 · Cited by 3
Survey on object detection in VLSI architecture through deep learning
Francis, N. C., & Mathana, J. M. (2024) · AIP conference proceedings · doi:10.1063/5.0209400 · Cited by 2
Modeling and implementing the behavior of RR robot using FPGA
(2022) · doi:10.1117/12.2623821 · Cited by 1
- Retracted
FPGA-Based Implementations of Biometric Recognition: A Review
Kia, A., Ahmed, A., & Imtiaz, M. (2026) · Electronics · doi:10.3390/electronics15102145 · Cited by 4
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
A Survey of Privacy Preservation for Deep Learning Applications
Zhang, L., Nie, L., & Yu, L. (2022) · Journal of Information Hiding and Privacy Protection · doi:10.32604/jihpp.2022.039284
Automated ethnicity recognition using equilibrium optimizer with machine learning on facial images
Asiri, Y., Alhabeeb, A., Mashraqi, A. M., Algarni, A. D., & Abdel‐Khalek, S. (2022) · Thermal Science · doi:10.2298/tsci22s1353a · Cited by 1
Interference Recognition Algorithm Based on Convolutional Neural Network
Liu, J., Huang, C., Shan, C., et al. (2025) · IEEE International Conference on Communication Technology (ICCT) · doi:10.1109/icct67417.2025.11374081
FaceScanPaliGemma multi-agent vision language models for facial attribute recognition
AlDahoul, N., Tan, M. J. T., Kasireddy, H. R., & Zaki, Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-39584-3 · Cited by 19
Mba, M. L. (2023) · theses.fr (ABES) · doi:10.70675/160aa3e5z1fa4z4fcaz925dz43d5182ac131
D3Fuzz: Dynamic, directed and decaying LLM-driven fuzzing for deep learning libraries
Sun, J., Dong, J., Zhang, H., Tian, Z., & Zhang, Y. (2026) · Information and Software Technology · doi:10.1016/j.infsof.2026.108289
Gelar, T., Sholahuddin, M. R., Sari, A. N., Laksana, A., Haryo, S., Fadhilah, R., Julian, G., & Muzhaffar, D. (2026) · Journal of Innovation Information Technology and Application (JINITA) · doi:10.35970/jinita.v8i1.3021
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
Marouan, A., Badrani, M., Zannou, A., Kannouf, N., & Chetouani, A. (2026) · Journal of Cybersecurity and Privacy · doi:10.3390/jcp6050156
A review on automated facial recognition technology
Jiet, M. M., Verma, P., Kamble, A., Puri, C., & Kalbande, M. N. (2024) · AIP conference proceedings · doi:10.1063/5.0241110
Identification of Synthetic Streaming Based Media Applying Deep Learning Models in Digital Forensics
Krishnan, S. S. N., Selvaraj, K., & Sivasubramani, V. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-97-8946-7_20
OF10K: Digging Into a New Dataset Containing Diversified Naturally-Occluded Facial Images
Islam, M. S., Alnamlah, A. A. S., Noor, J., & Islam, A. B. M. A. A. (2026) · IEEE Access · doi:10.1109/access.2026.3654472
Metadata
- Authors
- AlBdairi, A. J. A., Xiao, Z., Alkhayyat, A., Humaidi, A. J., Fadhel, M. A., Taher, B. H., Alzubaidi, L., Santamaría, J., & Al-Shamma, O.
- Affiliations
- Hunan University (CN)
- Islamic University of Najaf (IQ)
- University of Technology - Iraq (IQ)
- University of Sumer (IQ)
- Queensland University of Technology (AU)
- Universidad de Jaén (ES)
- University of Information Technology and Communications (IQ)
- Corresponding author
- Alzubaidi, Laith
- Santamaría, José
- ORCID
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2022-03-02
- Volume
- 12
- Issue
- 5
- Pages
- 2605
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W4214813523
- Cited by
- 54
- References
- 45
- Citations by year
- 2026: 10 · 2025: 8 · 2024: 15 · 2023: 14 · 2022: 7
- FWCI
- 3.60
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- QUT ePrints (Queensland University of Technology) (submittedVersion, cc-by)
- 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 › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face and Expression Recognition
- Keywords
- face recognition, deep convolutional neural networks, FPGA acceleration, GPU comparison, facial features, energy efficiency, hardware resource utilization
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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.