Automatic blush detection in "concealed information" test using visual stimuli

Harmer, K., Yue, Shigang, Guo, Kun, Adams, Karen and Hunter, Andrew (2010) Automatic blush detection in "concealed information" test using visual stimuli. In: International Conference of Soft Computing and Pattern Recognition (SoCPaR), 7-10 Dec. 2010, Paris.

Full content URL:

Full text not available from this repository.

Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive


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.

Keywords:Deception, Human computer interaction
Subjects:G Mathematical and Computer Sciences > G440 Human-computer Interaction
C Biological Sciences > C800 Psychology
Divisions:College of Science > School of Computer Science
ID Code:9709
Deposited On:03 Jun 2013 16:34

Repository Staff Only: item control page