Journal de biométrie et biostatistique

Classification-based Automatic Fingerprint Identification System for Large Distributed Fingerprint Database

Abstract

Seungjin Sul

Fingerprint is the cheapest, fastest, most convenient and most reliable way to identify someone. And the tendency, due to scale, easiness and the existing foundation, is that the use of fingerprint will only increase. Cars, cell phones, PDAs, personal computers and dozens of products and devices are using fingerprints more and more. When it comes to deal with large-scale fingerprint database, the scalability of current fingerprint recognition system is not proved yet. Our target application is a centralized user authentication system for e-commerce including online shopping malls and for user identification for government web services. In this paper, we introduce a large-scale fingerprint recognition system which incorporates fingerprint classification, large-scale identification, multiple server based identification. Our experimental result shows that our multi-server system takes 5.2 - 5.36 seconds to identify a fingerprint from 100,000 fingerprints.