A study of fingerprint image filtering

Fingerprint image enhancement is a crucial step in automatic fingerprint recognition. A large number of approaches for filtering the fingerprint image have been suggested. Most of them perform oriented band pass filtering. However, such filters, for example, Gabor filters, may create spurious ridge structure information. This is harmful for the feature extraction and therefore is harmful for the automatic fingerprint recognition. This paper examines the properties of applying the Gabor filter in the fingerprint image enhancement. It shows that the nonsinusoidal-shaped ridge structure, the ridge frequency estimation error, and the small filter size are the causes of creating spurious ridge structures. As a solution, we suggest an adaptive oriented low pass filter instead of the Gabor filter to avoid producing undesired harmful side effects for the automatic fingerprint recognition