CFP last date
21 July 2025
Call for Paper
August Edition
IJCA solicits high quality original research papers for the upcoming August edition of the journal. The last date of research paper submission is 21 July 2025

Submit your paper
Know more
The week's pick
Responsive image
Design and Theoretical Framework of a GPS-Enabled Smart Cane for the Visually Impaired

Sk. Md Azmayeen Tajwar Ayman Raeef Khan Md. Sahidullah
Random Articles
Reseach Article

FPGA-based Real-Time Emotion Recognition System using Facial Expressions for Physically Disabled Individuals

by M. Kamaraju, K. Ujwala, B. Rajasekhar
journal cover thumbnail

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 187 - Number 12
Year of Publication: 2025
Authors: M. Kamaraju, K. Ujwala, B. Rajasekhar
10.5120/ijca2025925109

M. Kamaraju, K. Ujwala, B. Rajasekhar . FPGA-based Real-Time Emotion Recognition System using Facial Expressions for Physically Disabled Individuals. International Journal of Computer Applications. 187, 12 ( Jun 2025), 22-28. DOI=10.5120/ijca2025925109

@article{ 10.5120/ijca2025925109,
author = { M. Kamaraju, K. Ujwala, B. Rajasekhar },
title = { FPGA-based Real-Time Emotion Recognition System using Facial Expressions for Physically Disabled Individuals },
journal = { International Journal of Computer Applications },
issue_date = { Jun 2025 },
volume = { 187 },
number = { 12 },
month = { Jun },
year = { 2025 },
issn = { 0975-8887 },
pages = { 22-28 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume187/number12/fpga-based-real-time-emotion-recognition-system-using-facial-expressions-for-physically-disabled-individuals/ },
doi = { 10.5120/ijca2025925109 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2025-06-21T01:56:52.766728+05:30
%A M. Kamaraju
%A K. Ujwala
%A B. Rajasekhar
%T FPGA-based Real-Time Emotion Recognition System using Facial Expressions for Physically Disabled Individuals
%J International Journal of Computer Applications
%@ 0975-8887
%V 187
%N 12
%P 22-28
%D 2025
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Emotion recognition through facial expressions is a critical enabler of non-verbal communication, particularly for individuals with physical disabilities who may face barriers in speech or motor-based interaction. This paper proposes a real-time, FPGA-based facial emotion recognition system optimized for embedded deployment and low-power operation. The system utilizes a quantized MobileNetV2 Convolutional Neural Network (CNN) trained on an enhanced FERPlus dataset (FERPlus-A), which is refined using CLAHE, bilateral filtering, and sharpening to improve feature clarity. The trained model is quantized to 8-bit integer arithmetic for efficient synthesis via Vivado HLS and deployed onto a ZYNQ SoC platform. Integration through AXI interfaces enables seamless communication between the CNN accelerator and the processing system. Simulation results demonstrate high inference speed with a latency of approximately 1.174 milliseconds per frame and an estimated throughput of 851 frames per second. Despite the absence of hardware testing due to board unavailability, functional verification confirms the model’s readiness for real-time assistive applications. This work presents a scalable and energy-efficient solution for enhancing emotional communication in assistive technologies, offering significant potential for integration in healthcare, smart interfaces, and human-centered embedded systems.

References
  1. A. G. Howard et al., “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” Proc. IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 4510–4520, 2018.
  2. Y. Choi et al., “Quantization-aware Training for Efficient Deployment on FPGAs,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 10, pp. 3863–3876, Oct. 2021.
  3. S. K. Esser et al., “Learned Step Size Quantization,” Int. Conf. on Learning Representations (ICLR), 2020.
  4. H. Phan-Xuan et al., “FPGA-Based CNN Accelerator for Facial Emotion Recognition,” IEEE Access, vol. 8, pp. 139989–140001, 2020.
  5. Y. Ding et al., “A Reconfigurable CNN Engine Using HLS for Facial Analytics on FPGA,” J. Real-Time Image Processing, vol. 18, pp. 233–244, 2021.
  6. D. Vinhe et al., “High-Speed FPGA CNN Accelerator for Emotion Detection Using Parallel Processing,” Microelectronics Journal, vol. 103, pp. 104855, 2020.
  7. J. Kim et al., “Resource-Efficient Integer-Arithmetic-Only CNN Accelerator on FPGA,” IEEE Access, vol. 9, pp. 13416–13428, 2021.
  8. H. Wang et al., “Improving Emotion Recognition with Preprocessed FER Dataset,” Image and Vision Computing, vol. 101, pp. 103970, 2020.
  9. A. Rastegari et al., “XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks,” European Conf. on Computer Vision (ECCV), pp. 525–542, 2016.
  10. M. Lin et al., “A Compact Quantized CNN for Real-Time Facial Expression Recognition,” Sensors, vol. 21, no. 3, pp. 1–18, 2021.
  11. K. Nair et al., “Modular VHDL IP Core Based Facial Expression Detection System,” Procedia Computer Science, vol. 132, pp. 947–954, 2018.
  12. Y. Shi et al., “Reconfigurable CNN Engine Using High-Level Synthesis for Low-Resource FPGAs,” IEEE Design & Test, vol. 38, no. 3, pp. 73–82, 2021.
  13. J. Ortega et al., “Edge-Assisted Emotion Recognition System Using FPGA and IoT,” IEEE Internet of Things Journal, vol. 7, no. 9, pp. 7982–7994, 2020.
  14. M. Mahmood et al., “Optimized CNN Execution on FPGAs Through Loop Tiling and Data Reuse,” IEEE Embedded Systems Letters, vol. 13, no. 1, pp. 1–4, 2021.
  15. D. Farooq et al., “Facial Emotion Recognition on FPGA Using CLAHE and LeNet Architecture,” Int. J. of Reconfigurable Computing, vol. 2019, pp. 1–8, 2019.
Index Terms

Computer Science
Information Sciences

Keywords

Convolutional Neural Network (CNN) MobileNetV2 FERPlus-A Vivado HLS.

Powered by PhDFocusTM