A Fingerprint Verification Tool Using Adaptive Resonance Theory Nets

Accurate verification o f fingerprints is important to prevent hassles related to one's identification. The hassle could be at the recognition of one's own as well as the forged prints of others. The objective of this work is to develop a fingerprint verification tool using JA VA . The algorith ms of Adaptive Resonance Theory (ART) net - ART-1 and A RT-2 have been used. These algorithms have been implemented with 'C' language. Two hundred and twenty two genuine versions of finger prints have been used as training cases and 518 very similar looking but forged fingerprints have been used as test cases. Here, the optimu m v igilance parameter (ρ) is obtained through carefully conducted parametric studies. Finally, a flexib le error threshold has been selected to accept fingerprints with 95% matching in the pixel patterns and the rest are rejected. The study observes that, ART 1 and 2 are ab le to identify forged fingerprints with Total Success Rate (TSR) of 95.80% and 97.37%, respectively.

[1]  Andrew Beng Jin Teoh,et al.  An efficient fingerprint verification system using integrated wavelet and Fourier-Mellin invariant transform , 2004, Image Vis. Comput..

[2]  Anil K. Jain,et al.  Performance evaluation of fingerprint verification systems , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  S. H. Gerez,et al.  A correlation-based fingerprint verification system , 2000 .

[4]  Herb Schildt,et al.  C++: The Complete Reference, 4th Edition , 2002 .

[5]  Anil K. Jain,et al.  FVC2000: Fingerprint Verification Competition , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Arun Ross,et al.  Information fusion in biometrics , 2003, Pattern Recognit. Lett..

[7]  Peng Li,et al.  An effective biometric cryptosystem combining fingerprints with error correction codes , 2012, Expert Syst. Appl..

[8]  Ju Cheng Yang,et al.  A fingerprint verification algorithm using tessellated invariant moment features , 2008, Neurocomputing.

[9]  Subhagata Chattopadhyay,et al.  Neurofuzzy models to automate the grading of old‐age depression , 2014, Expert Syst. J. Knowl. Eng..

[10]  Bir Bhanu,et al.  Fingerprint Indexing Based on Novel Features of Minutiae Triplets , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Herbert Schildt.  Java: The Complete Reference , 1996 .

[12]  U. Rajendra Acharya,et al.  Neural Network Approaches to Grade Adult Depression , 2012, Journal of Medical Systems.

[13]  Anil K. Jain,et al.  Decision-Level Fusion in Fingerprint Verification , 2001, Multiple Classifier Systems.

[14]  Subhagata Chattopadhyay,et al.  An Automated System to Diagnose the Severity of Adult Depression , 2011, 2011 Second International Conference on Emerging Applications of Information Technology.

[15]  Subhagata Chattopadhyay,et al.  Fingerprint Identification System using Tree based Matching , 2012 .

[16]  Raffaele Cappelli,et al.  A fingerprint retrieval system based on level-1 and level-2 features , 2012, Expert Syst. Appl..

[17]  Subhagata Chattopadhyay,et al.  Offline Verification of Hand Written Signature using Adaptive Resonance Theory Net (Type-1) , 2013, SiPS 2013.

[18]  Subhagata Chattopadhyay,et al.  Handwritten Signature Verification (Offline) using Neural Network Approaches: A Comparative Study , 2012 .