Fingerprint enhancement with dyadic scale-space

Fingerprint enhancement is a critical step in automatic fingerprint verification system. Most of the existing enhancement uses a set of contextual filters to enhance fingerprint. The main drawback of these methods is these contextual filters based on the local information of the fingerprint, such as ridge width, orientation, curvature etc. This information is unreliable in the areas corrupted by the noise. This paper introduces the scale space theory in the computer vision to enhance the fingerprint. In the enhancement process, decompose fingerprint into a series of images and organize the images by courser to finer scheme. Thus a globe and integrate interpretation is available and it enables us to get rid of the influence of noise to the largest extent. Experiments show our algorithm is fast and improve the performance of fingerprint verification system.