Detection of lies by facial thermal imagery analysis

Abstract

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.

A Comprehensive Review on Features Extraction and Features Matching Techniques for Deception Detection

“…Su, Levine, Owayjan, Kashour, Al Haddad, Fadel, Al Souki, Bailey, Demyanov, Ramamohanarao, and Leckie all studied facial analysis techniques for deception detection [18], [30], [37]. Thermal imaging was studied by both Bedoya-Echeverry et al and Dcosta et al [36], [38]. [34] used head movement analysis to study how it could be used to detect deception.…”

“…This paper provides an overview on deception detection techniques and classification methods specifically Linear Regression [1], J48 Decision Tree [1], [72], Multi-Layer Perceptron [1], Gradient Boosting Decision Tree [1], Levenberg-Marquardt [6], [44], BFGS Quasi-Newton [6], Long Short Term Memory [6], [39], [41], [58], Support Vector Machine [1], [13], [15], [39], [41], [45], [46] [58], [79], GMM [13], RVM [15], ensemble [39], Random Forest Decision Tree classifier [73], improved dense trajectories and OpenFace [79] and Ripper rule induction classifier [74]. In addition, non-verbal features like thermal facial analysis [7], [23], [32], [36], [38] eye movement analysis [8], [22], [26]- [28], visual cues [9], [10], text analysis with BERT [16], brain activity analysis [21], [33], [35], multimodal features [24], [29], infrared imaging [31], and facial expressions…”

Optimized Action Units Features for Efficient Design of Deception Detection System

“…ISSN:2222-758X e-ISSN:2789-7362 motion, head movement, facial expressions, eye gaze, pupil dilation and eye blinking [7]. Bedoya-Echeverry et al [8] designed a lie detection system by utilizing temperature change in a lacrimal puncta area. This study was performed on 27 subjects and utilized the simplest classification technique that depends on comparing the estimated temperatures in control questions and the remaining parts of the interrogation.…”