Research On Iris Recognition System Based On Embedded System

Biometric identification technology distinguishes different individuals by body behav iors and characteristics.Iris identification is one of the biometric identification technology,iris contains very rich texture information,and with a lifetime of stable properties,it has great value in research and development potential.The security is more and more attention in today's society,the iris recognition technology are also gradually spread to people's life.In order to adapt itself to the requirements of the identity authentication in today's society,must seek a kind of low power consumption,low cost,good stability,high recognition rate,mobility strong biological identification system,this paper studies a kind of based on embedded iris recognition system.The main research content includes the following several aspects:Designed an embedded iris recognition system,this design uses an arm9-based kernel mini2440 development board as hardware module of the iris recognition system,on the mini2440 development board transplant the Linux operating system,complete the USB,serial port,LCD liquid crystal display driver.And use the Qt as the integrated development environment of iris recognition graphical interface design,make it has a good man-machine interface.On the iris localization algorithm,based on Hough transform and calculus circle detection,the advantages and disadvantages of using these two algorithms of improved method to locate the edge of the iris,through a large number of experiments,the positioning of the method presented in this paper the effect is very good,but also has a certain anti-interference ability.According to the Hamming distance characteristics of traditional matching shift than a lot of problems,this paper puts forward an improved iris feature matching algorithm,through the automatic shift control than the number of times to achieve a reasonable reduction ratio on the effect,the number of short the time of the iris feature matching,improve the performance of the iris recognition system.Using CASIA1.0 iris database of Chinese academy of sciences,in PC,and in this paper,the design of the embedded iris recognition system platform for a large number of experiments,the iris recognition and the amount of time of the time.Through comparing with the traditional method,the method on the recognition time is shorter,higher precisionand confirmed in this paper,the design of the iris recognition system has good recognition performance.After a lot of experiments and testing,this paper designed an embedded iris recognition system has a high recognition rate,strong anti-interference ability,low cost and good mobility,has certain value in practical application.