Virtual Identity Creation by Fingerprint Combination for Privacy Protection?

Now a days both forensic and civilian applications makes use of biometric data as concerns about privacy and misuse of data increases. Thus protecting biometric data is one of the prime issues. Although, over the years many template protection schemes have been discovered and much research and progress have been made on fingerprint authentication system, performance of even state-of-the-art matchers is still much low. In addition to this, securing a stored fingerprint template is of paramount importance because compromised fingerprint cannot be easily revoked. Therefore, to tackle these problems, much effort is still needed to improve the performance, security and speed of fingerprint authentication systems. In this project a biometric authentication system for protecting fingerprint privacy is proposed. The idea is to combine two different fingerprints, pertaining to two different fingers into a new identity. The proposed work of this project is carried out in two phases. In the first phase combined minutiae template will be generated based on the information extracted from two different fingerprints. And in the next phase a Fingerprint-Matching process is proposed for matching the query fingerprints against a combined minutiae template by using minutiae matching algorithm. Furthermore, the proposed work is more robust to attacks in sense that by storing combined minutiae template into the database, the complete minutiae feature of a single fingerprint will not be compromised when database is stolen. The experimental results show that our system can achieve a very low error rate with FRR = 0.1% at FAR = 0.1%. Compared with the state-of-the-art technique, our work has the advantage in creating a better new virtual identity.