An extension to the FEEDB multimodal database of facial expressions and emotions

FEEDB is a multimodal database that contains recordings of people expressing different emotions, captured by using a Microsoft Kinect sensor. Data were originally provided in the device's proprietary format (XED), requiring both the Microsoft Kinect Studio application and a Kinect sensor attached to the system to use the files. In this paper, we present an extension of the database. For a selection of recordings, we also provide a frame by frame analysis in text format, that allows one to use the data directly for classification purposes. The data provided includes many different features computed from the original recordings, namely tracking status, 6 animation units, head position, head pose (pitch, roll and yaw) and 100 tracked points. These were extracted by using the Microsoft Face Tracking capabilities and are provided for each frame.