Article Preview
Top1. Introduction
Biometric authentication has received extensive attention over the past decade with increasing demands in automated personal identification as fingerprints are assumed to be unique across individuals, and fingers of the same individual (Pankanti et al., 2002). However, contact based fingerprint systems have some drawbacks due to skin elasticity, inconsistent finger placement, contact pressure, small sensing area, environment conditions and sensor noise. Additionally, problems like contagious diseases spreading make the use of contact based scanners not very safe. We are then interested in a fingerprint matching method using contactless images for fingerprint verification.
Depending on the application context, a biometric system may be called either a verification system or an identification system (Maltoni et al., 2003). A verification system authenticates a person’s identity by comparing the captured biometric reference template pre-stored in the system. It conducts one-to-one comparison to confirm whether the claim of identity by the individual is true. An identification system recognizes an individual by searching the entire enrollment template database for a match. It conducts one-to-many comparisons to establish if the individual is present in the database and if so, returns the identifier of the enrollment reference that matched.
Fingerprint matching techniques can be coarsely classified into three categories, namely minutiae-based matching (Jain et al., 1997; Medina-pérez et al., 2012), image-based matching (A. Qader et al., 2006; Ito et al., 2009; Jain et al., 2000, Sha et al., 2003) and hybrid matching technique (Khalila et al., 2010; Kumar et al., 2012). Minutiae-based matching essentially consists of finding the alignment between the template and the input minutiae feature sets that result in the maximum number of minutiae pairings.
In this paper, we present a contactless fingerprint verification method using a minutiae matching technique, based on the alignment between template images acquired by a contactless system and input images acquired by the same way. Contactless images have been acquired and stored in a database during an enrollment step. The first stage in an Automatic Fingerprint Verification procedure is to extract minutiae from fingerprints. In our contactless fingerprint verification system, we have implemented a minutia extraction algorithm which has been presented in (Djara et al., 2010). The extracted features are ridge bifurcation, ridge ending and ridges orientations. Authors in (Kumar et al., 2012; He et al., 2002; Virk & Maini, 2012) determine orientations using horizontal axis.
Most of the matching or verification of the fingerprint verification systems use minutiae types and orientation angle to find matched minutiae pairs from the input and template fingerprints (Tiko & Kuosmanen, 2003). Thus, accuracy of the verification stage largely depends on the minutiae extraction process. Unfortunately, due to some non-linear distortion, like excessive pressure and twisting of fingers during enrollment, this process can cause the minutiae features to be distorted from the original. Some authors have used the Smallest Minimum Sum of Closest Euclidean Distance of bifurcation points to improve the accuracy of fingerprint verification (Bhowmik et al., 2009).