Drunk Driver Detection Using Thermal Facial Images

This study aims to investigate and propose a machine learning approach that can accurately detect alcohol consumption by analyzing the thermal patterns of facial features. Thermal images from the Tufts Face Database and self-collected images were utilized to train the models in identifying temperatu...

Full description

Saved in:
Bibliographic Details
Main Authors: Chin-Heng Chai, Siti Fatimah Abdul Razak, Sumendra Yogarayan, Ramesh Shanmugam
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Information
Subjects:
Online Access:https://www.mdpi.com/2078-2489/16/5/413
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850257309713825792
author Chin-Heng Chai
Siti Fatimah Abdul Razak
Sumendra Yogarayan
Ramesh Shanmugam
author_facet Chin-Heng Chai
Siti Fatimah Abdul Razak
Sumendra Yogarayan
Ramesh Shanmugam
author_sort Chin-Heng Chai
collection DOAJ
description This study aims to investigate and propose a machine learning approach that can accurately detect alcohol consumption by analyzing the thermal patterns of facial features. Thermal images from the Tufts Face Database and self-collected images were utilized to train the models in identifying temperature variations in specific facial regions. Convolutional Neural Networks (CNNs) and YOLO (You Only Look Once) algorithms were employed to extract facial features, while classifiers such as Support Vector Machines (SVMs), Multi-Layer Perceptron (MLP), and K-Nearest Neighbors (KNN), as well as Random Forest and linear regression, classify individuals as sober or intoxicated based on their thermal images. The models’ effectiveness in analyzing thermal images to determine alcohol intoxication is expected to provide a foundation for the development of a realistic drunk driver detection system based on thermal images. In this study, MLP obtained 90% accuracy and outperformed the other models in classifying the thermal images, either as sober or showing signs of alcohol consumption. The trained models may be embedded in advanced drunk detection systems as part of an in-vehicle safety application.
format Article
id doaj-art-1e85f923bde44fb383a59ea1b7d33996
institution OA Journals
issn 2078-2489
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Information
spelling doaj-art-1e85f923bde44fb383a59ea1b7d339962025-08-20T01:56:28ZengMDPI AGInformation2078-24892025-05-0116541310.3390/info16050413Drunk Driver Detection Using Thermal Facial ImagesChin-Heng Chai0Siti Fatimah Abdul Razak1Sumendra Yogarayan2Ramesh Shanmugam3Faculty of Information Science and Technology, Multimedia University, Melaka 75450, MalaysiaFaculty of Information Science and Technology, Multimedia University, Melaka 75450, MalaysiaFaculty of Information Science and Technology, Multimedia University, Melaka 75450, MalaysiaDepartment of Mechatronics Engineering, Rajalakshmi Engineering College, Thandalam 602105, IndiaThis study aims to investigate and propose a machine learning approach that can accurately detect alcohol consumption by analyzing the thermal patterns of facial features. Thermal images from the Tufts Face Database and self-collected images were utilized to train the models in identifying temperature variations in specific facial regions. Convolutional Neural Networks (CNNs) and YOLO (You Only Look Once) algorithms were employed to extract facial features, while classifiers such as Support Vector Machines (SVMs), Multi-Layer Perceptron (MLP), and K-Nearest Neighbors (KNN), as well as Random Forest and linear regression, classify individuals as sober or intoxicated based on their thermal images. The models’ effectiveness in analyzing thermal images to determine alcohol intoxication is expected to provide a foundation for the development of a realistic drunk driver detection system based on thermal images. In this study, MLP obtained 90% accuracy and outperformed the other models in classifying the thermal images, either as sober or showing signs of alcohol consumption. The trained models may be embedded in advanced drunk detection systems as part of an in-vehicle safety application.https://www.mdpi.com/2078-2489/16/5/413drunk detectionthermal analysisfacial feature analysis
spellingShingle Chin-Heng Chai
Siti Fatimah Abdul Razak
Sumendra Yogarayan
Ramesh Shanmugam
Drunk Driver Detection Using Thermal Facial Images
Information
drunk detection
thermal analysis
facial feature analysis
title Drunk Driver Detection Using Thermal Facial Images
title_full Drunk Driver Detection Using Thermal Facial Images
title_fullStr Drunk Driver Detection Using Thermal Facial Images
title_full_unstemmed Drunk Driver Detection Using Thermal Facial Images
title_short Drunk Driver Detection Using Thermal Facial Images
title_sort drunk driver detection using thermal facial images
topic drunk detection
thermal analysis
facial feature analysis
url https://www.mdpi.com/2078-2489/16/5/413
work_keys_str_mv AT chinhengchai drunkdriverdetectionusingthermalfacialimages
AT sitifatimahabdulrazak drunkdriverdetectionusingthermalfacialimages
AT sumendrayogarayan drunkdriverdetectionusingthermalfacialimages
AT rameshshanmugam drunkdriverdetectionusingthermalfacialimages