人工知能 技法을 利用한 ARM프로세서 基盤의 指紋認識 信號處理보드 設計에 관한 硏究

Abstract

Fingerprint is a unique feature to an individual. It stays with a person throughout his or her life. This makes the fingerprint the most reliable kind of personal identification because it can't be forgotten, misplaced, or stolen.

Now, social requirements of personal identification techniques are expanding in a number of new application area. Especially fingerprint recognition technologies among biometrics technologies has more spot lighting beacuse fingerprint authorization is the most profitable and convenient method of Biometric Authentics System(BAS).

Generally, BAS is classfied into PC(personal computer) BAS and Standard-alone BAS. PC-BAS is only designed for using into computer and Standard-alone BAS(S-BAS) represents independent system of using microprocessor.

In this paper, neural network was used(one for core and another for delta)in feature extraction and the processor of designed Fin-gerprint identification Signal processing Board(FSB) used SA(St-rongARM), it was used into network, set-top box, PDA(Perso-nal Digital Assistant), PCS(Personal Communications Services), etc. and in the most BAS, fingerprint sensor uses optics sensor but in this paper, fingerprint sensor used cmos E-Field type.

After test, designed S-BAS proved that it is possible to imp-lement independently whitout PC.