Biometrics-based security applications are used for accurate identification of person. It recognizes and determines an individual’s identity based on their physical or behavioral characteristics like fingerprint, ear, face, hand geometry, retina, voice, gait or iris. Any human physiological or behavioral characteristic can be a considered as biometric characteristic when it satisfies requirements like universality, permanence, uniqueness, and collectability. Fusing many biometric sources for authentication of identity is a method to alleviate sensing and signal processing technology’s imperfection. Fusion before matching considers raw data acquired from sensing devices and from processed data after feature extraction. This paper proposes a multimodal biometric system with palmprint and palmvein. Features are extracted using Wavelet based texture features and autoregressive model and fused. A novel feature selection based on Artificial Bee Colony (ABC) is proposed and the selected features are classified using k-Nearest Neighbor and Naïve Bayes. Experimental results demonstrates that the proposed technique improves the recognition rate.
Biometrics, Palmprint, Palmvein, Z Score Normalization, Artificial Bee Colony (ABC), k-Nearest Neighbor (kNN), Naïve Bayes
Share This Article
© The Author(s) 2015. Open Access. This article is distributed under the terms of the Creative Commons Attribution 4.0 International License which permits unrestricted use, sharing, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.