Reconnecting broken ridges in fingerprints

Fingerprint is the oldest and the most widely used biometric. The performance of any Automatic Fingerprint Identification System (AFIS) highly depends on the quality of the fingerprint used. Fingerprint comprises of parallel ridges and valleys. For various reasons, ridges could be broken. Most of the fingerprint recognition algorithms are based on minutiae information. The accuracy of minutiae extraction could be affected by the presence of unwanted broken ridges. A technique for automatically detecting and reconnecting broken ridges is presented here. This technique utilizes a combination of directional information and watershed transform to identify the regions of the broken area. Results using real fingerprint data are presented and discussed.