Wavelet Based Finger Knuckle and Finger vein Authentication System

Biometrics is the prominent technology for accurate and safe detection of claim identity.  This paper proposes a novel multimodal authentication system using finger knuckle (FK) and finger vein (FV). Finger Knuckle has unique bending and makes this a distinctive biometric identifier. The vein pattern of all fingers of human being is not same. Each finger of same person has different vein pattern. It is the hidden part which is not seen by normal eye sight hence less possible to forge. The system consists of proposed prototype finger knuckle and finger vein image capturing devices, formation of own FK and FV image database acquired from proposed devices. Here feature extraction of FK images is based on Walsh Wavelet Transform and FV image on Hybrid Wavelet Transform. Proposed multimodal biometric authentications integrate transformed domain features vector of FK and FV at score level fusion using Bayesian and weighted sum method. The fusion of these two modalities using Bayesian method demonstrated the recognition accuracy of 98.3% and weighted sum 98.5 %.  Various weights of finger knuckle and finger vein affects the recognition accuracy. The better recognition accuracy is obtained at weight of 0.8 and 0.2. The performance index is improved i.e 98.5% and the Error equal rate is 1.5% as compare to unimodal biometric. Error equal rate is reduced by 10% than individual biometric system. For N user with M 1 and M 2 as test and training samples, for verification of one user, matching complexity is O (M 1 M 2 ) and for N user O(M 1 M 2 x N). For identification, (N x M 1 ) test samples and (N x M 2 ) training samples are considered. So matching complexity is O [N (N-1) x M 1 ] for each biometric. Using conventional matching the complexity is O [N (N-1) x M 1 M 2 ]. For multimodal biometric using FK and FV, matching complexity is O 2[N (N-1) x M 1 ].  It shows great reduction in matching complexity using the proposed algorithms.