Research On Embedded Fingerprint Recognition System

Fingerprint identification refers to an identification technique of a person, based on her/his inherent fingerprint physical characteristic by computer. Due to the uniqueness and invariability of fingerprint, the fingerprint recognition is more attractive compared with traditional methods such as passwords and ID certificate. As practical biometric recognition technologies, fingerprint recognition technology is becoming the most popular technology of which the research institutes of home and abroad made a study. The traditional fingerprint recognition technology based on PC is restricted to home applications because of hardly mobility and high power consumption. So the embedded fingerprint recognition system with low power consumption and high performance will have bright future.This thesis makes a research of the embedded fingerprint recognition system. The work can be summarized as the following three points.Firstly on the basis of analyzing the development of recognition system of home and abroad, this thesis set forth the necessity of this research. Then it analyses the hardware framework, and introduces the capture set of which MBF200 produced by FUJITSU is the main chip, and explain the detail process of module designing. In the following part it's emphasized to the popular embedded operating system LINUX, the study of the device driver so that the capture can be used under Linux. In the following part it introduces compiling system of Linux OS and describes the steps of porting it to arm920 architecture. Finally based on the chip TMS320VC5509A produced by TI, this thesis introduces the general procedure of fingerprint recognition and the difference between Float-point arithmetic and Fixed-point arithmetic. Taking fingerprint arithmetic as an example, it describes the realizing and optimizing of Fix pointed arithmetic.Relative key segment of the fingerprint recognition system has been described in detail in this paper. It is valuable to people who are developing the fingerprint recognition system in other fields.