An efficient multi-spectral palmprint identification using contourlet decomposition and Hidden Markov Model

Automatic personal identification is playing an important role in security systems. Biometrics technologies has been emerging as a new and effective methods to achieve accurate and reliable identification results. A number of biometric traits exist and are in use in various applications. Palmprint is one of the relatively new biometrics due to its stable and unique characteristics. In this paper, multi-spectral information for the unique palmprint are integrated in order to construct an efficient multi-modal identification system based on matching score level fusion. For that, the palm lines are characterized by the contourlet coefficients sub-bands and compressed using the Principal Components Analysis (PCA). Subsequently, we use the Hidden Markov Model (HMM) for modeling. Finally, log-likelihood scores are used for palmprint matching. Experimental results show that our proposed scheme yields the best performance for identifying palmprints and it is able to provide an excellent identification rate and provide more security.