DISFA: Denver Intensity of Spontaneous Facial Action Database is a non-posed facial expression database for those who are interested in developing computer algorithms for automatic action unit detection and their intensities described by FACS.
This database contains stereo videos of 27 adult subjects(12 females and 15 males) with different ethnicities. The images were acquired using PtGrey stereo imaging system at high resolution (1024x768). The intensity of AU's (0-5 scale) for all video frames were manually scored by two human FACS experts. The database also includes 66 facial landmark points of each image in the database. More description about this database can be found in our paper published in the IEEE Transactions on Affective Computing [pdf]. You can find more info about DISFA here.
The database is available for distribution for research purposes. Please complete the DISFAagreement form to only request DISFA and send it back to Dr. Mahoor (firstname.lastname@example.org). You need a separate agreement if you need Extended DISFA (DISFA+). Please see below!DSIFA+: Extended Denver Intensity of Spontaneous Facial Action Database is an extension of DISFA, a previously released and well-accepted face dataset. Extended DISFA (DISFA+) has the following features: 1) it contains a large set of posed and non-posed facial expressions data for a same group of individuals, 2) it provides the manually labeled frame-based annotations of 5-level intensity of twelve FACS facial actions, 3) it provides meta data (i.e. facial landmark points in addition to the self-report of each individual regarding every posed facial expression).
More description about DISFA+ can be found in our paper presented in CVPRW'16 here [pdf]. This dataset is suitable for those who want to study differences between posed and non-posed action units and dynamics of facial expressions (see Fig. 1).
The database is available for distribution for research purposes. Please complete the DISFA+agreement form to only request DISFA+ and send it back to Dr. Mahoor (email@example.com).