Characterization of Palmprint Using Discrete Orthonormal S-Transform

In this paper, we propose a novel and efficient texture based approach to palmprint recognition based on a 2D discrete orthonormal S-Transform called as the 2D-DOST. 2D-DOST is a new powerful tool for texture analysis which can effectively extract the frequency contribution of image texture. In this work, First 2D-DOST is applied to the palmprint to characterize the frequency content of palmprint texture. Then, the local energy of 2D-DOST magnitudes in different bandwidths are computed and regarded as palmprint features. In the experiments, three databases, namely, CASIA, PolyU and IITD databases, are used to evaluate the performance of the proposed method. Also, The performance of 2D-DOST method is evaluated based on a set of different similarity/dissimilarity measures. The experimental results offer ERR equal to 0.93%, 0.97% and 0.12% for IITD, CASIA and PolyU databases, respectively which demonstrate the efficiency and validity of the proposed method.