Deception Detection
This Project is no longer active.
Interviews are a primary tool in suspect interrogation and intelligence gathering. In many criminal justice scenarios, the ability to detect deception and suspicious behavior is critical. Traditional approaches to detect deception (e.g. the polygraph) are obtrusive and have limited validity and utility. Recent studies in multimodal non-verbal communication (e.g. involuntary posture changes, facial cues, voice modulations) offer a new approach to the problem of deception detection. Experienced interviewers can potentially detect multimodal signs (indicators) of deception and intention. The main limitations of this approach are the human tendency to overlook non-verbal indictors, over-focusing on ones that have little relevance to deception, individual differences in interviewer performance, and the difficulty of integrating multi-modal information. The aim of this project is to objectively extract facial-expression and body-gesture indicators of intention and deception using unobtrusive remote sensors such as video surveillance.
current head
current staff
current contact
past staff
- Zara Ambadar
- Alexandre Collado I Castells
- Jun-Su Jang
- Ricardo Cervera Navarro
- Joan Perez