AI-Based Blink and Emotion Detection System for Paralysis Patients

Authors

  • Subashri M UG Student , Electronics and Communication Engineering, St. Joseph’s Institute of Technology, Chennai, India
  • Samyuktha B UG Student, Electronics and Communication Engineering, St. Joseph’s Institute of Technology, Chennai, India

DOI:

https://doi.org/10.63252/JCBECA/2.2.2025.15-22

Keywords:

Paralysis, Eye Blink Detection, Emotion Recognition, CNN, ESP32, IoT Healthcare

Abstract

Paralysis often restricts patients from speaking or moving, which creates a major communication barrier with caregivers and family members. Without proper channels, patients are unable to express even their basic needs, leading to frustration and dependency. To overcome this limitation, we propose a non-invasive and affordable system that enables communication through eye blinks and facial emotions. The system uses an eye-blink sensor integrated with an ESP32 microcontroller for blink detection, while a Convolutional Neural Network (CNN) trained on the FER-2013 dataset recognizes facial emotions. These signals are processed and transferred to a Blynk IoT platform, where caregivers receive instant alerts and status updates on a mobile application. The proposed system is designed to be low-cost, portable, and practical, offering an effective way to restore communication ability and independence for paralysis patients.

Downloads

Download data is not yet available.

Downloads

Published

2025-08-31

How to Cite

M, S., & B, S. (2025). AI-Based Blink and Emotion Detection System for Paralysis Patients. Journal for Communication and Biomedical Engineering With Computer Applications (JCBECA), 2(2), 15–22. https://doi.org/10.63252/JCBECA/2.2.2025.15-22

Issue

Volume 2, Issue 2, May-August 2025

Section

Articles
Crossref
Scopus
Google Scholar
Europe PMC

References

[1] J. Spiers and A. M. Dollar, "Design and Evaluation of a Multifunctional Assistive Communication Interface for Individuals with Severe Motor Impairments," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 29, pp. 2403–2412, 2021.

[2] M. Chauhan, R. K. Sharma, and S. Kumar, "Eye-Blink Controlled Communication System for Patients with Motor Neuron Diseases," Biomedical Signal Processing and Control, vol. 65, p. 102358, 2021.

[3] Y. Li, J. Zheng, and H. Wang, "Facial Emotion Recognition Using Deep Learning for Assistive Healthcare Applications," Journal of Ambient Intelligence and Humanized Computing, vol. 12, pp. 8457–8468, 2021.

[4] J. R. Wolpaw and E. W. Wolpaw, Brain-Computer Interfaces: Principles and Practice. New York, NY: Oxford University Press, 2012.

[5] M. A. Lebedev and M. A. L. Nicolelis, “Method and system for brain-machine interface,” U.S. Patent 7,756,576, issued Jul. 13, 2010.