Detection of lies by facial thermal imagery analysis

An artificial vision system is presented for lie detection by analyzing face thermal image sequences. This system represents an alternative technique to the polygraph. Some of its features are: 1) it has no physical contact with the examinee, 2) it is non-intrusive, 3) it has a potential for private...

ver descrição completa

Detalhes bibliográficos
Main Authors: Bedoya-Echeverry, Sebastián, Belalcázar-Ramírez, Hernán, Loaiza-Correa, Humberto, Nope-Rodríguez, Sandra Esperanza, Pinedo-Jaramillo, Carlos Rafael, Restrepo-Girón, Andrés David
Formato: Online
Idioma:eng
Publicado em: Universidad Pedagógica y Tecnológica de Colombia 2017
Assuntos:
Acesso em linha:https://revistas.uptc.edu.co/index.php/ingenieria/article/view/5771
Descrição
Resumo:An artificial vision system is presented for lie detection by analyzing face thermal image sequences. This system represents an alternative technique to the polygraph. Some of its features are: 1) it has no physical contact with the examinee, 2) it is non-intrusive, 3) it has a potential for private use, and 4) it can simultaneously analyze several persons. The proposed system is based on the detection of physiological changes in temperature in the lacrimal puncta area caused by the subtle increase in blood flow through the nearby vascular network. These changes take place when anxiety appears as a consequence of deception. Thus, the system segments the periorbital area, and tracks consecutive frames using the Kanade-Lucas-Tomasi algorithm. The results show a success rate of 79.2 % in detecting lies using a simple classification based on the comparison between the estimated temperatures in control questions, and the rest of the interrogation procedure. The performance of this system is comparable with previous works, where cameras with better specifications were used.