Mohammad Esmaeel Yahyatabar - Department of Electrical and Computer Engineering, Babol University of Technology, Babol, Iran
Yasser Baleghi - Department of Electrical and Computer Engineering, Babol University of Technology, Babol, Iran
Mohammad Reza Karami - Department of Electrical and Computer Engineering, Babol University of Technology, Babol, Iran

In this paper, the specific trait of Persian signatures is applied to signature verification. Efficient features, which can discriminate among Persian signatures, are investigated in this approach. Persian signatures, in comparison with other languages signatures, have more curvature and end in a specific style. An experiment has been designed to determine the function indicating the most robust features of Persian signatures. To improve the performance of verification, a combination of shape based and dynamic extracted features is applied to Persian signature verification. To classify these signatures, Support Vector Machine (SVM) is applied. The proposed method is examined on two common Persian datasets, the new proposed Persian dataset in this paper (Noshirvani Dynamic Signature Dataset) and an international dataset (SVC2004). For three Persian datasets EER value are equal to 3, 3.93, 4.79, while for SVC2004 the EER value is 4.43. These experiments led to identification of new features combinations that are more robust. The results show the overperformance of these features among all of the previous works on the Persian signature databases; however, it does not reach the best reported results in an international database. This can be deduced that language specific approaches may show better results.

Online Signature Verification; Support Vector Machine; Robust Feature Extraction; Online Signature Dataset