This data set contains vectorised images of the faces of 10 different human subjects with different poses and lighting conditions. The images were compressed to 30x20 pixels.
yaleA list with entries $x (a 2000x600 matrix with each row corresponding to an image) and $y (a vector of labels indicating the human subject).
Georghiades, A.S. and Belhumeur, P.N. and Kriegman, D.J. (2001) From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(6) pp. 643--660.