It has been demonstrated that there is correlation between increased blood perfusion in the orbital muscles and stress levels for human beings. It has also been suggested that this peri-orbital perfusion can be quantified through the processing of thermal video. The idea has been based on the fact that skin temperature is heavily modulated by superficial blood flow. We have developed a high-definition thermal-imaging technique that can detect stress by recording the thermal patterns from people's faces. This technique has an accuracy comparable to that of polygraph examination by experts and has potential for application in remote and rapid security screening, without the need for skilled staff or physical contact. Although polygraph examinations, which have high precision when applied by experts, are good at identifying liars, they are impracticable for mass screening because skilled operators are needed, subjects have to be attached to instrumentation for several minutes, data analysis is time-consuming and the interpretation of data is delayed. We explored the possibility of using high-definition thermal imaging of the face for detecting deceit because it enables rapid automated analysis of changes in regional facial blood flow to be quantified. For stress recognition, support vector machines (SVM) and LDA are applied to design the stress classifiers and its characteristics are investigated. Using gathered data under psychological polygraphy experiment; the classifiers are trained and tested. The pattern recognition method classifies stressful from non-stressful subjects, based on labels which come from polygraphy data. The successful classification rate is 96% for 12 subjects. This means that facial thermal imaging because of its non-contact advantages, could be a remarkable alternative for psycho physiological methods.