Vitality detection in personal authentication systems using fingerprints

Fingerprints have always been an identification mean due to their some important properties: universality (everyone have one), permanence in the time (they do not change when the time passes), individuality (there are no two identical fingerprints). From the first forensic applications to the last biometric technology applied to access control, fingerprints are considered as the sign of each human being. But in 2002 an important vulnerability has been shown: it is possible to deceive fingerprint scanners through artificial replicas of fingertips. Several studies, using different materials, have demonstrated that all tested scanners (based on different physical principles) are not able to recognize fake to live fingertips. The first goal of this Ph.D. thesis has been to investigate the current state-of-the-art in fingerprint vitality detection. Since the state-of-the-art is lack of a systematic classification of all the current methods, we arranged the above hardware-based and software-based approaches into a specific taxonomy on the basis of the sensing methodology or the physical phenomenon which is considered as a life sign (elastic deformation, perspiration or morphology of the skin). The second contribution of this Ph.D. thesis is the development of two different new approaches, which we indicated as power spectrum and ridge-width fingerprint vitality detection. We believe this Ph.D. thesis contributed to a first interpretation key of all the current methods and to innovative proposals in fingerprint vitality detection.