Monitoring of periorbital blood flow rate through thermal image analysis and its application to polygraph testing

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 thermodynamic 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.