| Automatic fingerprint identification is a method to identify a person based on his fingerprint characteristics. Compared to the traditional identification ways such as using passwords or PIN numbers, fingerprint identification is inherently more reliable and more capable in differentiating an authorized person from a fraudulent imposter. Now most of the automatic fingerprint identification systems are realized on the PC-based platform. But the newly developed market for civil application has demand more for system's portability and convenience. So the trend of miniaturizing and embedding the system for Automatic fingerprint identification become more and more distinct.In this thesis, our objective is to design a fingerprint verification system to perform fully automatic personal identification with high security by composing the DSP technology and the advanced PC-based algorithm for fingerprint processing properly. To achieve this object, we have done a great deal of work on software algorithm and hardware frame design; many of them are original. For algorithm design, according to the characteristics of DSP-based embedded platform, we did a lot to improve the previous PC-based fingerprint algorithm so as to reduce quantity of operation. This work includes: refining and improving the Gabor filter algorithm, reducing the image normalizing and thinning algorithm, innovating in matching algorithm and optimizing the whole program. In hardware design aspect, in order to obtain a better performance-price rate, we tried all means to cut down the cost in chip selection, and focused on how to make the best output from the selected chips. Therefore lots of innovative work has been done including the design for data flow, memory controller and hardware logic.Experimental results show that our system has achieved satisfied performance on portability, reliability and real-time ability. Also, our system is much more cheaper than those products based on PC.
|
PDF Full Text Request