Abstract
An automatic fingerprint identification system (AFIS) is one of the most important biometric technologies. How to reduce the time of computing in an AFIS with a huge database is an important and necessary issue. Fingerprint classification provides a practical method. In this thesis, we present a fingerprint classification algorithm based on singular points with novel criteria of a classification scheme. A fingerprint is classified into one of the four classes: arch, right loop, left loop, and whorl. The fingerprint classification was tested on 27,000 images in the Nist14 database as well as on 28 images in a live-scan database. The recognition rate of 83.13% for the Nist14 database and 96.4% for the live-scan database have been achieved.