CK+ Expression Classification Dataset

CK+ stands for Extended Cohn-Kanade dataset, which is a dataset containing 593 video sequences. The videos come from 123 different subjects, ranging in age from 18 to 50 years old, with different genders and ancestries. Each video shows the facial transition from neutral expression to directional extreme expression, recorded at 30 frames per second (FPS) with a resolution of 640 x 490 or 640 x 480 pixels.

Of these videos, 327 were labeled as belonging to one of seven expression categories: anger, contempt, disgust, fear, happiness, sadness, and surprise. The CK+ dataset is widely considered to be the most widely used laboratory-manipulated facial expression classification database and is used in major facial expression classification methods.