| With the advent of Information society, the demand on the security of Information is increasing in the civilian fields such as web-access, finance, safeguard and electronic business. Biometrics, which refers to identifying an individual based on his or her physiological or behavioral characteristics, has the capability to reliably distinguish between an authorized person and an imposter. Among all biometrics (e.g., face, fingerprint, iris, retina, DNA, voice, etc.), fingerprint-based identification is one of the most mature and dependable techniques.This paper focuses on one of the most important techniques in automatic fingerprint identification system: Fingerprint Matching. The template of the input fingerprint and the template of fingerprints from the database are compared to decide whether both of the two fingerprints belong to the same finger. The accurate rate of matching results is the last criterion of the success of automatic fingerprint identification systems.The fingerprint-matching algorithm based on the vector triangle has been realized by programming. This method utilizes information of two nearest minutiae to determine the reference points in fingerprint image and to fulfill fingerprint matching. Experimental results demonstrate that the method doesn't rely on the core points, and furthermore, it is invariant to rotation. But, it demands good quality of images. The fingerprint-matching algorithm based on the aligned ridges and the vector triangle incorporates much ridge information into the matching process. At the same time, it uses the vector triangle to verify the location of reference point to confirm the reliability of reference point. The experimental results can prove that the fingerprint-matching algorithm used in this paper is effective. The hardware-simulation of the fingerprint identification algorithm is accomplished in the integrated software-developing tool CCS (Code Composer Studio). |
PDF Full Text Request