Title: Automatic blush detection in ‘concealed information’ test using visual stimuli

Authors: Shigang Yue; Karl Harmer; Kun Guo; Karen Adams; Andrew Hunter

Addresses: Lincoln School of Computer Science, University of Lincoln, Brayford Pool Campus, Lincoln, LN6 7TS, UK ' School of Engineering and Digital Arts, University of Kent, Canterbury, Kent, CT2 7NZ, UK ' School of Psychology, University of Lincoln, Lincoln, LN6 7TS, UK ' School of Psychology, University of Lincoln, Lincoln, LN6 7TS, UK ' School of Computer Science, University of Lincoln, Lincoln, LN6 7TS, UK

Abstract: Blushing has been identified as an indicator of deception, shame, anxiety and embarrassment. Although normally associated with the skin coloration of the face, a blush response also affects skin surface temperature. In this paper, an approach to detect a blush response automatically is presented using the Argus P7225 thermal camera from e2v. The algorithm was tested on a sample population of 51 subjects, while using visual stimuli to elicit a response, and achieved recognition rates of ∼77% TPR and ∼60% TNR, indicating a thermal image sensor is the prospective device to pick up subtle temperature change synchronised with stimuli.

Keywords: blush detection; thermal imaging; psychophysiology; deception; visual cues; temperature change; visual stimuli; blushing.

DOI: 10.1504/IJDMMM.2014.063197

International Journal of Data Mining, Modelling and Management, 2014 Vol.6 No.2, pp.187 - 201

Published online: 06 Aug 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article