Abstract
In this thesis, we are devoted to the implementation of an automatic fingerprint identification system (AFIS). Fingerprint is considered to be a popular characteristic for personal identification which is necessary for access control, criminal identification and credit card usage. An AFIS can reduce time and laborious effort taken by manual identification effectively. Our AFIS is a minutiae-based matching system. Each fingerprint is recorded with its minutiae and is also classified into one of loop, whorl and arch types. The data set is acquired by FPS 110 Silicon Fingerprint Sensor manufactured by Veridicom. We will describe the whole procedures and show the experimental results.