Fingerprint verification using smart cards for access control systems

Over the past few years, the authors have tried to integrate biometrics into a smart card. In this paper, to improve error rates obtained with hand geometry biometrics and the costs with the iris recognition system, fingerprints are used. This technique, quite well known in the industry and deeply studied for the last century, has improved its electronic sensors, pulling down prices and, therefore, enabling its use in many more applications. The first step, as in every biometric system, is to obtain an image of the user's fingerprint. After this, a pre-processing algorithm is applied, which enables feature extraction to obtain the location and type of all minutiae, i.e., the discontinuities in the ridges and valleys of the fingerprint. Due to the fact that it is not possible to always catch the same number of minutiae, a special matching algorithm should be applied to compare the feature vector with the corresponding user's template. Efforts to integrate this matching algorithm in a low computer power device, such as a smart card, are given, showing the paths that should be followed in order to improve the security of access control and payment systems available today.