Try my background correction demo, attached. It uses John D'Errico's polyfitn to fit the background to a 2D polynomial. Then I divide the image by it.
Alternatively you can look for fingerprint articles here http://iris.usc.edu/Vision-Notes/bibliography/contentspeople.html#Face%20Recognition,%20Detection,%20Tracking,%20Gesture%20Recognition,%20Fingerprints,%20Biometrics to see how researchers in the field are doing it.
