The uniqueness of human fingerprints has been accepted by the scientific community since long time ago. Proof of this is the fact that, among all physiological characteristics, fingerprints are the oldest and most deeply used signs of identity for personal recognition. However up to date, the development of an automatic fingerprint-based human authentication system is an open research problem. Most of the difficulties rely on the complexity and the high computational power needed to develop a fingerprint matching algorithm reliable enough to guarantee the accuracy of the result even when only low-quality fingerprint impressions are available from the users. In order to deal with the processing power requested by the system, an application-specific hardware accelerator developed by means of hardware-software co-design techniques is suggested in this work for the fingerprint alignment stage. The hardware processor permits to speed up the alignment phase and to reach real-time performance, which is not guaranteed when developing the same algorithm under a purely-software platform.