2D and 3D palmprint information and Hidden Markov Model for improved identification performance

Biometric systems based on a single source of information suffer from limitations such as the lack of uniqueness, non-universality of the chosen biometric trait, noisy data and spoof attacks. Multibiometrics are relatively new systems that overcome those problems. These systems fuse information from multiple biometric sources in order to achieve better identification performance. In this paper, 2D and 3D palmprint are integrated in order to construct an efficient multibiometric identification system based on matching score level fusion. For that, the texture information is characterized by the rotation invariant VARiance measures (VAR) and compressed using the Principal Components Analysis (PCA). Subsequently, we use the Hidden Markov Model (HMM) for modeling the feature vector of each palmprint. Finally, Log-likelihood scores are used for palmprint evaluation. The proposed scheme is tested and evaluated using PolyU 2D-3D palmprint database of 250 users. Our experimental results show the effectiveness and reliability of the proposed system, which brings high identification accuracy rate.