Online signature verification approach using Mellin transform and empirical mode decomposition

The signature is one of the most popular biometric modality. In this paper, we present a new method for online signature based on the use of the Mellin transform and the empirical mode decomposition (EMD) for online signature verification. A phase of pre-processing and normalization is carried out before the extracting of the signatures features by using the Mellin transform and the EMD. After that, three similarity measures are used to match the signatures where the signature verification competition (SVC 2004) is used as a database. Experimental results confirm the effectiveness of our approach and show the level of its reliability. Finally, the proposed method gives an EER of 2.13%.