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.
yale
A 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.