Fingerprint´s Core Point Detection Using Orientation Field

Fingerprint recognition is a widely used biometric identification mechanism. In case of correlation based fingerprint recognition detection of a consistent registration point is a crucial issue; this point can be a core point of a fingerprint. Many techniques have been proposed but success rate is highly dependent on input used and accurate core point detection is still an open issue. Here we discuss a core point detection algorithm which is computationally simple and gives consistent detection of a core point. The proposed technique is based on orientation field of the fingerprint which is calculated using gradient based technique and optimized neighborhood averaging to generate a smoother orientation field, on which we operate a specially designed mask for detecting core point as the orientation field in the region of the core point is different than the other area. Though all fingerprints don´t possess core point still this algorithm is useful to detect high curvature regions. This algorithm is helpful in the development of correlation based Automatic Fingerprint Recognition System (AFIS).