Novel Chaff Generation for Fingerprint Fuzzy Vault
Rahul Hooda *
Department of Computer Science and Engineering, PEC University of Technology, Chandigarh, India.
Manavjeet Kaur
Department of Computer Science and Engineering, PEC University of Technology, Chandigarh, India.
*Author to whom correspondence should be addressed.
Abstract
Aims: To propose a new chaff generation method and to compare the results with the standard Clancy’s Chaff Generation Method.
Place and Duration of Study: Department of Computer Science and Engineering, PEC University of Technology, Chandigarh during July 2012 and June 2013.
Methodology: Two databases are used to calculate the results. One is the FVC 2004-DB1 database which is approved by fingerprint recognition website. Other is the live database created using the Crossmatch’s Verifier 300 LC scanner. In both the databases 100 images of 10 different persons were compared with each other and performances are computed and compared.
Results: Results show that proposed algorithm takes less time to generate different number of chaff points (from 50 to 500) than Clancy’s algorithm. The performance metrics like Genuine Accept Ratio, False Accept Ratio and False Reject Ratio have same values of both the algorithms. Results are computed on both the databases.
Conclusion: Experiments results show that the proposed algorithm is faster than the Clancy’s algorithm in generating equal number of chaff points.
Keywords: Biometrics, fuzzy vault system, fingerprint, chaff generation