Lie detection using thermal imaging

Ioannis T. Pavlidis

doi:10.1117/12.547806

12 April 2004 Lie detection using thermal imaging

Ioannis T. Pavlidis

Proceedings Volume 5405, Thermosense XXVI; (2004) https://doi.org/10.1117/12.547806
Event: Defense and Security, 2004, Orlando, Florida, United States

Abstract

In the present paper we describe a novel method for scoring polygraph tests using thermal image analysis. Our method features three stages: image acquisition, physiological correlation, and pattern classification. First, we acquire facial thermal imagery using an accurate mid-infrared camera. Then, we transform the raw thermal data to blood flow rate data through heat transfer modeling. Finally, we classify the subject as deceptive or non-deceptive based on the nearest-neighbor classification method. We perform our analysis on the periorbital area of the subjects’ faces. Our previous research has indicated that the periorbital area is the facial area affected the most from blood flow redistribution during anxious states. We present promising experimental results from 18 subjects. We henceforth anticipate that thermal image analysis will play an increasingly important role in polygraph testing as an additional scoring channel. Our ultimate objective is to increase the accuracy and reliability of polygraph testing through the fusion of traditional invasive 1D physiological measurements with novel non-invasive 2D physiological measurements.

Citation Download Citation

Ioannis T. Pavlidis "Lie detection using thermal imaging", Proc. SPIE 5405, Thermosense XXVI, (12 April 2004); https://doi.org/10.1117/12.547806

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available