Facial Recognition for Drunk People Using Thermal Imaging
Face recognition using thermal imaging has the main advantage of being less affected by lighting conditions compared to images in the visible spectrum. However, there are factors such as the process of human thermoregulation that cause variations in the surface temperature of the face. These variati...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2020-01-01
|
Series: | Mathematical Problems in Engineering |
Online Access: | http://dx.doi.org/10.1155/2020/1024173 |
id |
doaj-7ca25e9023ce47d0b777c0d6c788bd15 |
---|---|
record_format |
Article |
spelling |
doaj-7ca25e9023ce47d0b777c0d6c788bd152020-11-25T03:27:59ZengHindawi LimitedMathematical Problems in Engineering1024-123X1563-51472020-01-01202010.1155/2020/10241731024173Facial Recognition for Drunk People Using Thermal ImagingAgustin Sancen-Plaza0Luis M. Contreras-Medina1Alejandro Israel Barranco-Gutiérrez2Carlos Villaseñor-Mora3Juan J Martínez-Nolasco4José A. Padilla-Medina5Tecnológico Nacional de México en Celaya, Department of Electrical and Electronic Engineering, A. García-Cubas No. 600 Pte. Esq. Av. Tecnológico, Col. Alfredo V. Bonfil, C.P. 38010-Celaya Gunajuato, MexicoUniversidad Autónoma de Querétaro, Campus Amazcala, Faculty of Engineering, Carretera Chichimequillas-Amazcala Km 1 S/N. Amazcala, El Marques, Querétaro, C.P.76265, MexicoTecnológico Nacional de México en Celaya, Department of Electrical and Electronic Engineering, A. García-Cubas No. 600 Pte. Esq. Av. Tecnológico, Col. Alfredo V. Bonfil, C.P. 38010-Celaya Gunajuato, MexicoUniversidad de Guanajuato, Campus León, División de Ciencias e Ingenierías, Loma del Bosque 103, Col. Lomas del Campestre, León, Guanajuato, C.P. 37150, MexicoTecnológico Nacional de México en Celaya, Department of Mechatronics Engineering, A. García-Cubas No. 600 Pte. Esq. Av. Tecnológico, Col. Alfredo V. Bonfil, C.P. 38010 - Celaya Guenajuato, MexicoTecnológico Nacional de México en Celaya, Department of Electrical and Electronic Engineering, A. García-Cubas No. 600 Pte. Esq. Av. Tecnológico, Col. Alfredo V. Bonfil, C.P. 38010-Celaya Gunajuato, MexicoFace recognition using thermal imaging has the main advantage of being less affected by lighting conditions compared to images in the visible spectrum. However, there are factors such as the process of human thermoregulation that cause variations in the surface temperature of the face. These variations cause recognition systems to lose effectiveness. In particular, alcohol intake causes changes in the surface temperature of the face. It is of high relevance to identify not only if a person is drunk but also their identity. In this paper, we present a technique for face recognition based on thermal face images of drunk people. For the experiments, the Pontificia Universidad Católica de Valparaíso-Drunk Thermal Face database (PUCV-DTF) was used. The recognition system was carried out by using local binary patterns (LBPs). The LBP features were obtained from the bioheat model from thermal image representation and a fusion of thermal images and a vascular network extracted from the same image. The feature vector for each image is formed by the concatenation of the LBP histogram of the thermogram with an anisotropic filter and the fused image, respectively. The proposed technique has an average percentage of 99.63% in the Rank-10 cumulative classification; this performance is superior compared to using LBP in thermal images that do not use the bioheat model.http://dx.doi.org/10.1155/2020/1024173 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Agustin Sancen-Plaza Luis M. Contreras-Medina Alejandro Israel Barranco-Gutiérrez Carlos Villaseñor-Mora Juan J Martínez-Nolasco José A. Padilla-Medina |
spellingShingle |
Agustin Sancen-Plaza Luis M. Contreras-Medina Alejandro Israel Barranco-Gutiérrez Carlos Villaseñor-Mora Juan J Martínez-Nolasco José A. Padilla-Medina Facial Recognition for Drunk People Using Thermal Imaging Mathematical Problems in Engineering |
author_facet |
Agustin Sancen-Plaza Luis M. Contreras-Medina Alejandro Israel Barranco-Gutiérrez Carlos Villaseñor-Mora Juan J Martínez-Nolasco José A. Padilla-Medina |
author_sort |
Agustin Sancen-Plaza |
title |
Facial Recognition for Drunk People Using Thermal Imaging |
title_short |
Facial Recognition for Drunk People Using Thermal Imaging |
title_full |
Facial Recognition for Drunk People Using Thermal Imaging |
title_fullStr |
Facial Recognition for Drunk People Using Thermal Imaging |
title_full_unstemmed |
Facial Recognition for Drunk People Using Thermal Imaging |
title_sort |
facial recognition for drunk people using thermal imaging |
publisher |
Hindawi Limited |
series |
Mathematical Problems in Engineering |
issn |
1024-123X 1563-5147 |
publishDate |
2020-01-01 |
description |
Face recognition using thermal imaging has the main advantage of being less affected by lighting conditions compared to images in the visible spectrum. However, there are factors such as the process of human thermoregulation that cause variations in the surface temperature of the face. These variations cause recognition systems to lose effectiveness. In particular, alcohol intake causes changes in the surface temperature of the face. It is of high relevance to identify not only if a person is drunk but also their identity. In this paper, we present a technique for face recognition based on thermal face images of drunk people. For the experiments, the Pontificia Universidad Católica de Valparaíso-Drunk Thermal Face database (PUCV-DTF) was used. The recognition system was carried out by using local binary patterns (LBPs). The LBP features were obtained from the bioheat model from thermal image representation and a fusion of thermal images and a vascular network extracted from the same image. The feature vector for each image is formed by the concatenation of the LBP histogram of the thermogram with an anisotropic filter and the fused image, respectively. The proposed technique has an average percentage of 99.63% in the Rank-10 cumulative classification; this performance is superior compared to using LBP in thermal images that do not use the bioheat model. |
url |
http://dx.doi.org/10.1155/2020/1024173 |
work_keys_str_mv |
AT agustinsancenplaza facialrecognitionfordrunkpeopleusingthermalimaging AT luismcontrerasmedina facialrecognitionfordrunkpeopleusingthermalimaging AT alejandroisraelbarrancogutierrez facialrecognitionfordrunkpeopleusingthermalimaging AT carlosvillasenormora facialrecognitionfordrunkpeopleusingthermalimaging AT juanjmartineznolasco facialrecognitionfordrunkpeopleusingthermalimaging AT joseapadillamedina facialrecognitionfordrunkpeopleusingthermalimaging |
_version_ |
1715207102447747072 |