DC Coefficients comparison based Approach for Fingerprint Identification System

Abstract

Fingerprint Recognition is the most preferred method for verification of an individual’s identity. There are two main issues in fingerprint recognition which are fingerprint classification and fingerprint matching which require proper identification of fingerprints. This paper focuses on the fingerprint identification; generally fingerprint identification is carried out on the basis of features like ridges and minutiae. This paper proposes a new approach for identification of fingerprints by calculating the DC Coefficients. Based on the comparison for matched percentage of DC Coefficients from both fingerprint images along with the pixel locations of the specified DC Coefficients the system will decide whether the fingerprints are same or not provided that all the fingerprints are acquired from the same device to avoid any ambiguity. Proposed method is tested on FVC (Fingerprint Verification Competition) database for the authenticity of the results. Furthermore an analysis of the proposed method in terms of computational complexity has been carried out with reference to the size (resolution) of the fingerprint image. The proposed method has also been compared with existing methods in terms of Computational Complexity to evaluate the performance of the proposed algorithm. The results show that the proposed algorithm requires least computational time to perform the identification and can be used with large databases with minimum operational time.