Facial Expression Recognition System on SoC FPGA
The DOI matches its Crossref record; 14 of the 15 references it cites were found in a registry or an index.
Abstract
In this paper, we present a facial expression recognition (FER) system implemented on a SoC FPGA device. Our system can operate independently and automatically classify 7 different types of basic emotions. We designed a processing engine on FPGA that is able to calculate convolutional layers of convolutional neural networks and designed a CNN optimal with a designed hardware for the task of emotions recognition and achieving 66% of accuracy in FER2013 dataset. The whole hardware system is designed on SoC FPGA which can process up to 15 image frames per second at an operating frequency of 130 MHz.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“9.07 times fewer BRAMs”
From A Resource Efficient Integer-Arithmetic-Only FPGA-Based CNN Accelerator for Real-Time Facial Emotion Recognition (2021) · cites this paper as [42]
In the citing paper
“and to have frame rate approximately 25 times faster.”
From A Resource Efficient Integer-Arithmetic-Only FPGA-Based CNN Accelerator for Real-Time Facial Emotion Recognition (2021) · cites this paper as [40]
In the citing paper
“but has a frame rate of about 5 FPS slower.”
From A Resource Efficient Integer-Arithmetic-Only FPGA-Based CNN Accelerator for Real-Time Facial Emotion Recognition (2021) · cites this paper as [42]
In the citing paper
“Compared with the method of [40], the new Type-2 method was found to be more accurate”
From A Resource Efficient Integer-Arithmetic-Only FPGA-Based CNN Accelerator for Real-Time Facial Emotion Recognition (2021) · cites this paper as [40]
In the citing paper
“to use fewer resources”
From A Resource Efficient Integer-Arithmetic-Only FPGA-Based CNN Accelerator for Real-Time Facial Emotion Recognition (2021) · cites this paper as [40]
3 more claims about this paper
Create a free account to see every claim other papers make about this one.
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 · cited 2×
“BACKGROUND A. VGG neural network The VGG architecture was first introduced in Image-Net LargeScale Vision Recognition Challenge (ILSVRC) 2014 by Simonyan et al [6] and it was also a first runner up in this competition.”
MethodAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“In the training phase, the model uses ADAM [10] optimizer and Relu as an activation function for each convolution layer.”
MethodLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
(2014) · Cited by 33,419
Rapid object detection using a boosted cascade of simple features
Viola, P., & Jones, M. (2005) · Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 · doi:10.1109/cvpr.2001.990517 · Cited by 18,300 · cited 2×
“Face Detection stage OpenCV is a library containing many pre-trained models for face detection so we used OpenCV’s Haar Cascade [8] for face detection as it is one of the most effective and common algorithms.”
Constants across cultures in the face and emotion.
Ekman, P., & Friesen, W. V. (1971) · Journal of Personality and Social Psychology · doi:10.1037/h0030377 · Cited by 5,509 · cited 2×
“Our goal is to build an independent, automatic and emotional classification system that can identify the face and classify the seven basic emotions of a person including six emotions, proposed by Ekman and Friesen [1] and also a neutral face state.”
BackgroundChallenges in Representation Learning: A Report on Three Machine Learning Contests
Goodfellow, I. J., Erhan, D., Carrier, P. L., Courville, A., Mirza, M., Hamner, B., Cukierski, W., Tang, Y., Thaler, D., Lee, D.-H., et al. (2013) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-42051-1_16 · Cited by 1,719
Going Deeper with Embedded FPGA Platform for Convolutional Neural Network
Qiu, J., Wang, J., Yao, S., Guo, K., Li, B., Zhou, E., Yu, J., Tang, T., Xu, N., Song, S., et al. (2016) · Proceedings of the 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays · doi:10.1145/2847263.2847265 · Cited by 1,252 · cited 1×
“In addition, SoC has a hardware component of FPGA and there have been recent studies that show effective optimization of the CNN network on FPGA [3-5].”
MethodChallenges in representation learning: A report on three machine learning contests
Goodfellow, I. J., Erhan, D., Luc Carrier, P., Courville, A., Mirza, M., Hamner, B., Cukierski, W., Tang, Y., Thaler, D., Lee, D.-H., et al. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.005 · Cited by 697
Cited by
Deep-Emotion: Facial Expression Recognition Using Attentional Convolutional Network
Minaee, S., Minaei, M., & Abdolrashidi, A. (2021) · Sensors · doi:10.3390/s21093046 · Cited by 851
Debnath, T., Reza, M. M., Rahman, A., Beheshti, A., Band, S. S., & Alinejad‐Rokny, H. (2022) · Scientific Reports · doi:10.1038/s41598-022-11173-0 · Cited by 153
Kim, J., Kang, J.-K., & Kim, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3099075 · Cited by 50
Khan, N., Singh, A. V., & Agrawal, R. K. (2023) · Annals of Emerging Technologies in Computing · doi:10.33166/aetic.2023.02.002 · Cited by 14
Kalsum, T., & Mehmood, Z. (2023) · Journal of Sensors · doi:10.1155/2023/6987708 · Cited by 14
Secure and efficient implementation of facial emotion detection for smart patient monitoring system
Zaman, K. S., & Reaz, M. B. I. (2023) · Quantitative Biology · doi:10.15302/j-qb-022-0312 · Cited by 10
An FPGA-Based BNN Real-Time Facial Emotion Recognition Algorithm
Zhao, G., Wei, W., Xie, X., Fan, S., & Sun, K. (2022) · IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) · doi:10.1109/icaica54878.2022.9844526 · Cited by 8
Novel Approach of Facial Expression Recognition for Cross-Datasets
Khan, N., Singh, A. V., & Agrawal, R. K. (2023) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt56998.2023.10307597 · Cited by 6
WITHDRAWN: Intelligent recognition of motion posture based on FPGA and neural network
Weifei, F. (2020) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2020.103374 · Cited by 7
RetractedDriver's Companion-Drowsiness Detection and Emotion Based Music Recommendation System
Pant, M., Trivedi, S., Aggarwal, S., Rani, R., Dev, A., & Bansal, P. (2022) · International Conference on Computing, Communication, and Intelligent Systems (ICCCIS) · doi:10.1109/icccis56430.2022.10037226 · Cited by 4
Attentional Deep Learning novel approach for Facial Expression Recognition
Khan, N., Singh, A. V., & Agrawal, R. K. (2023) · International Conference on Information Systems and Computer Networks (ISCON) · doi:10.1109/iscon57294.2023.10112135 · Cited by 6
“Using deep learning techniques, the programme attempts to determine which of the saven basic emotions is being conveyed by the supplied face during the feature extraction and classification phases [28 – 34]”
BackgroundMethodInfluentialCNN-Based Model for Facial Expression Recognition Using FER 2013 Dataset
Roy, S., Dutta, M., Ghosh, A., Choudhury, T., & Dutta, S. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-6066-7_28 · Cited by 2
Elsokkary, S. K., Taher, M., Amer, H. H., & Salama, C. R. (2022) · Novel Intelligent and Leading Emerging Sciences Conference (NILES) · doi:10.1109/niles56402.2022.9942391 · Cited by 2
“Reference [13] implemented a basic emotions classifier.”
Multi-task Facial Expression Recognition With Joint Gender Learning
Pan, X., Xie, Q., Liu, W., & Liu, B. (2022) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc53654.2022.9945168 · Cited by 2
“31 FER on SoC [31] 66 .”
Facial Expression Recognition System Using DNN Accelerator with Multi-threading on FPGA
Ando, T., & Inoue, Y. (2024) · International Symposium on Computing and Networking Workshops (CANDARW) · doi:10.1109/candarw64572.2024.00025 · Cited by 1
“In contrast, Vinh et al. developed a standalone system that performs facial expression recognition on the detected faces after conducting face detection on a SoC FPGA [13].”
Quantized Separable Residual Network for Facial Expression Recognition on FPGA
Fan, X., Jiang, M., Zhang, H., Li, Y., & Yan, H. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-2336-3_1 · Cited by 1
Multi-dimension and Multi-level Information Fusion for Facial Expression Recognition
Bie, M., Xu, H., Liu, Q., Gao, Y., & Che, X. (2023) · Journal of Imaging Science and Technology · doi:10.2352/j.imagingsci.technol.2023.67.4.040410 · Cited by 1
Đokić, K., Mandušić, D., & Blašković, L. (2022) · doi:10.1109/csase51777.2022.9759761
Anchor-free face detection in the wild with an application to facial expression recognition
Huang, X. (2022) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc55077.2022.9886700
“Accuracy Soc FPGA [45] 66 CNN [46] 68.4 Yu [47] 62.1 HOG+CNN [48] 37.1 FaceLiveNet [49] 37.1 Ours w.o. Alignment 62.9 Ours 69.2 Firstly, we analyze the influence of Alignment.”
MethodInfluentialFPGA-Based Convolutional Neural Network for Classifying Image Blocks
Vysotskiy, A. S., Zinkevich, A. V., & Sai, S. V. (2023) · International Russian Automation Conference (RusAutoCon) · doi:10.1109/rusautocon58002.2023.10272870
“Optimizing the Circuit To improve the characteristics of the circuit, the following changes were implemented [16-20]:”
MethodFPGA-Based Neural Face Recognition Systems—A Survey
Gnanika, I. V., & Kavitha, K. J. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-3-032-07837-7_23
Deramgozin, M. M. (2023) · theses.fr (ABES) · doi:10.70675/8dd2ca31zdaacz4e5dz9dc8zdba9f54100c5
Hybrid LBPH-CNN for Interactive Web Interface-Based Multi-Face Emotion Recognition
Katti, A. G., & M V, C. M. (2026) · doi:10.2139/ssrn.6831425
“Vinh and Vinh [12] implemented a dedicated convolution engine on a SoC FPGA and classified FER2013 emotions at 66% accuracy while sustaining 15 fps at 130 MHz.”
Swin Transformer with Window-based Attention for Facial Expression Recognition on Navarasa FER
Chand, H. V., Sabharwal, S., Thomas, N., Onyema, E. M., & Shameem Ansar, A. (2026) · International Conference on Computing Methodologies and Communication (ICCMC) · doi:10.1109/iccmc69250.2026.11624809
“Furthermore, there have been several reports about practical deployment under computational constraints of lightweight and hardware-optimized FER systems [14] – [16].”
InfluentialAskri, O., Messaoud, S., Hajjaji, M. A., & Atri, M. (2026) · Algorithms · doi:10.3390/a19090794
Metadata
- Authors
- Vinh, P. T., & Quang Vinh, T.
- Affiliations
- Ho Chi Minh City University of Technology (VN)
- ORCID
- Vinh, Pham The
- Venue
- 2019 International Symposium on Electrical and Electronics Engineering (ISEE)
- Publisher
- IEEE
- Published
- 2019-10
- Pages
- 1-4
- OpenAlex
- W2993503860
- Cited by
- 22
- References
- 15
- Citations by year
- 2026: 3 · 2025: 1 · 2024: 1 · 2023: 6 · 2022: 7 · 2021: 3 · 2020: 1
- FWCI
- 4.38
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Embedded Systems and FPGA Applications
- Physical Sciences › Computer Science › Hardware and Architecture › Embedded Systems Design Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- facial expression recognition, FPGA, system-on-chip, convolutional neural networks, hardware acceleration, emotion recognition, FER2013 dataset, real-time image processing
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.