Fingerprint singularity and core point detection

Abstract

Fingerprint has been widely applied as a personal identification. Due to reliability and uniqueness features. In fingerprint, there are two kinds of features: the global feature and local feature. The global feature includes the ridge orientation map, core and delta locations, while the local feature form by minutiae points. Singular points are the most important global features that contain the significant global information which play an important role in fingerprint pattern classification (Hong and Jain, 1999) and fingerprint matching (Sharath et al., 2000). One of the features of fingerprint identification and verification is singularity (see Figure 1.0). The accuracy of singularity extraction basically depends on the quality of images. Therefore, in order to improve the identification and verification process, we need to enhance the fingerprint image. The poor quality of fingerprint image makes efficient singularity extraction algorithm degrades rapidly and we cannot identify the singular points area efficiently. A majority of techniques that used to enhance the fingerprint images are based on the use of contextual filters whose parameters depend on the local ridge frequency and orientation. The filters themselves may be spatial (Gorman and Nickerson, 1989; Jain et al. 1998) or based on Fourier domain analysis (Sherlock et al. 1994; Watson et al. 1994).