Posed and spontaneous expression distinguishment from infrared thermal images

In this paper, we try to distinguish between the posed and spontaneous facial expressions through infrared thermal images. Firstly, six statistical features are extracted from the temperature difference matrices between the apex and onset facial expression frames in each facial subregion. Secondly, the thermal differences between the posed facial expressions and spontaneous ones are analyzed by a Paired-Samples T-test. Thirdly, Bayesian Networks are adopted to classify posed and spontaneous expressions based on these temperature statistical features. Experimental results on the thermal subdatabase of the USTC-NIVE demonstrate the feasibility and effectiveness of posed and spontaneous expression recognition through facial temperature changes. This study also illustrates that the importance of different facial subregions´ temperature variances for differentiating different kinds of posed and spontaneous expressions.