This paper presents a prototype automatic identity-authentication system that uses fingerprints for individual verification. The authors have developed an improved minutiae-extraction algorithm that is faster and more accurate than their previous version. They also propose an alignment-based minutiae-matching algorithm that can find correspondences between input minutiae and stored templates without exhaustive search, compensating for nonlinear deformations and inexact transformations. The system's performance is evaluated using the Michigan State University and NIST 9 fingerprint databases, showing good results. The authentication process, on average, takes about 1.4 seconds on a Sun ULTRA F workstation. The paper discusses the design and implementation of the system, including the acquisition, representation, feature extraction, and matching components. The authors also detail their minutiae-extraction and matching algorithms, emphasizing the importance of reliable minutiae extraction and the challenges of matching in the presence of noise and deformations.This paper presents a prototype automatic identity-authentication system that uses fingerprints for individual verification. The authors have developed an improved minutiae-extraction algorithm that is faster and more accurate than their previous version. They also propose an alignment-based minutiae-matching algorithm that can find correspondences between input minutiae and stored templates without exhaustive search, compensating for nonlinear deformations and inexact transformations. The system's performance is evaluated using the Michigan State University and NIST 9 fingerprint databases, showing good results. The authentication process, on average, takes about 1.4 seconds on a Sun ULTRA F workstation. The paper discusses the design and implementation of the system, including the acquisition, representation, feature extraction, and matching components. The authors also detail their minutiae-extraction and matching algorithms, emphasizing the importance of reliable minutiae extraction and the challenges of matching in the presence of noise and deformations.