Smile Veracity Recognition Using LBP Features for Image Sequence Processing

Correct recognition of emotion veracity exhibited in facial gestures is troublesome for people. Yet, there is a belief that computer systems are able to perceive some tiny changes correlated to veracity expression, invisible for people, and therefore are able to improve proper perception of emotions. This work addresses the problem of spontaneous and posed smile recognition and suggests two approaches. The first one uses the visual cues, in which the feature vector describes the content of evenly sampled frames in the movie by applying uniform local binary patterns. The second one, describes the video sequence with smile intensity information derived from information extracted from each frame, where the feature vector is built using simple statistical measures calculated from this data. These two systems and a combination of them are tested on UVA-NEMO database and proved to deliver encouraging results.