Research On Multiple Biological Characteristics Identification System Based On SOPC

With the rapid development of information in today's society,personal information security is a concern in the information age.Identity information recognition technology as a means to effectively protect information security has always been a hot research direction.Biometric-based identity information authentication and recognition technology is widely used in various fields due to its stability,reliability,and security.However,in practical applications,single-modal biometric recognition technology has such problems as damage or lack of biological characteristics of special populations.Poor anti-counterfeiting and other inherent defects.In response to this problem,this paper proposes a SOPC-based fusion recognition scheme of three single-modal biometrics of face,iris,and fingerprint,which can effectively make up for the shortcomings of the single-feature recognition technology mentioned above.The specific work of this paper is as follows:1.Research on single-modal biological feature recognition.After reading a large number of documents,this design selects the three relevant algorithms of face,iris and fingerprint biometric identification and verifies them.Among them,this article has made improvements to the iris location algorithm,by estimating the center of the pupil,and on this basis,using prior knowledge to reduce a large number of useless edge points to achieve rapid iris location.At the same time,this paper has also made improvements to the traditional fingerprint feature extraction algorithm,removing false feature points while extracting features,and improving the speed of fingerprint feature extraction.2.Research on fusion recognition of face,iris and fingerprint.This paper chooses to fuse three biological characteristics at the fractional level,and designs three fusion schemes of face+iris,face+fingerprint,and iris+fingerprint according to actual needs.Aiming at the shortcomings of traditional fractional layer weighted fusion algorithm such as large amount of calculation and fixed weight distribution,this paper proposes an adaptive weighted fusion algorithm.The fusion scheme is determined by judging the reliability of the single biometric recognition system,and then the final optimal fusion weight is determined according to the reliability of the fusion system with different weights to obtain the best performance fusion system.3.SOPC system development.In this paper,the hardware description language is used to connect the IP cores added according to the system requirements to complete the hardware development of the system.The feasible algorithm on the PC side is written in C language and run on the Nios II processor to complete the system software development.Finally,the entire system was verified on the DE2-115 development board,and the integrated identification system was initially realized.