Improving faces/non-faces discrimination in video sequences by using a local spatio-temporal representation

In the last years spatio-temporal representations have shown to be successful for the analysis of video sequences in applications such as event detection, action and face recognition in videos. In this paper, we propose the use of local spatio-temporal features for the faces/non-faces classification stage, in the process of face detection in videos. Specifically, the extension of the Local Binary Patterns operator to the spatio-temporal domain is evaluated and compared with other schemes based on the same operator without considering the temporal information. The obtained results in the very challenged YouTube Faces database show that combining local appearance with motion can help to discriminate between faces and non-faces in the context of video applications.