Citation

Ong, Jia Xiang and Mogan, Jashila Nair and Ganesan, Thinesh (2025) Anger Expression Recognition using Raspberry Pi. In: 2025 International Conference on Information and Communication Technology, ICoICT 2025, 30 July 2025 - 31 July 2025, Hybrid, Bandung.

Text Anger_Expression_Recognition_using_Raspberry_Pi.pdf - Published Version Restricted to Repository staff only Download (346kB)

Abstract

Road rage incidents are increasingly prevalent in Malaysia, with the Malaysian Institute of Road Safety Research reporting that 18% of registered drivers are affected. Prolonged exposure to heavy traffic can lead to impatience, which heightens stress and negatively impacts drivers' emotions, fostering feelings of rage, aggression, and anxiety. Such emotional states impair decision-making on the road. This project aims to develop a system for detecting drivers' anger expressions using computer vision and embedded technology. This project aims to develop a system for detecting drivers' anger expressions using computer vision and embedded technology. The system integrates a Raspberry Pi 4 and a webcam to capture and analyze drivers' facial expressions. By employing a custom dataset categorized into anger and neutral expressions, the proposed facial recognition framework enables real-time detection. The dataset was compiled from facial expression captures of 23 participants, and the system's performance was evaluated based on accuracy, computation time, and recognition rates. Using a Convolutional Neural Network (CNN) with a 64x64 input size, the system achieved an accuracy of 73.19%. This study addresses the gap in existing research by proposing an edge-deployable, low-cost system capable of real-time anger expression classification. Future improvements include expanding the dataset to achieve better gender balance and reducing bias in anger detection, necessitating collaboration with a different participant pool. Additionally, a larger dataset focused on anger expressions across various age groups and ethnicities will enhance the system's effectiveness.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Anger, deep learning, rmbedded device, facial expressions
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800-8360 Electronics > TK7885-7895 Computer engineering. Computer hardware
Divisions:	Faculty of Information Science and Technology (FIST)
Depositing User:	Nor Afiqah Mohd Adnan
Date Deposited:	09 Dec 2025 03:29
Last Modified:	09 Dec 2025 03:29
URII:	http://shdl.mmu.edu.my/id/eprint/14975

Downloads

Edit (login required)