Automatic Fingerprint Classifier and Its Application to Access Control

Satoshi HASHIMOTO  Yutaka HATA  Kyoichi NAKASHIMA  Kazuharu YAMATO  

IEICE TRANSACTIONS (1976-1990)   Vol.E73   No.7   pp.1120-1126
Publication Date: 1990/07/25
Online ISSN: 
Print ISSN: 0000-0000
Type of Manuscript: Special Section PAPER (Special Issue on Cryptography and Information Security)
Category: Applications

Full Text: PDF>>
Buy this Article

The purpose of this paper is to establish an access control system by using only fingerprint identification. In order to minimize the identification time, we propose a new fingerprint classification suitable for a personal computer, and the real machine by using the classification is introduced. Our classification is implemented by only cores which are one of the features on fingerprint pattern. Therefore, it classifies all fingerprints into one of 11 classes rapidly on a personal computer. In the machine, an input fingerprint is classified and compared with ones registered in the same class. If both the input fingerprint and the registered one match, the person is allowed entry to the restricted area. Simulation results show that 443 fingerprint patterns (45 persons) are classified completely and rapidly. And the machine is effective and useful as identifier for home and room security.