The Hard Part: Collecting Data
•Pre-processing Object Images:
–Size normalization and Spatial Alignment
–Intensity Normalization and Lighting Correction – Separate normalizations for left and right parts of face (5 discrete values)
–Synthesizing data : Positional perturbation, Overcomplete evaluation of wavelet transform, background substitution, low pass filtering
•Non-object images : Bootstrapping
Alignment – use hand-labeled landmark points
Lighting correction – manual (not for cars)