Abstract
In recently years, fingerprint identification becomes more and more important for security. In this thesis, we introduce an automatic fingerprint matching system (AFMS). It includes three stages: fingerprint classification, minutiae extraction and fingerprint matching. In the stage of fingerprint classification, a fingerprint is classified into one of the five types, Arch, Right Loop, Left Loop, Whorl and Others. In the stage of minutiae extraction, the minutiae, composed of ridge endings and bifurcations, are detected. In the stage of fingerprint matching, a matching score between two minutiae pattern is computed.