Methods of Alignment for On-Line Signature Verification

S ize, location and rotation angle of on-line handwritten signature will have effects on the performance of verification. Methods of alignment for on- line signature verification are proposed in this paper, the size, location and rotation angle of test and reference signatures are aligned effectively to reduce the variations of different inputting. A method of S CLC-DTW with signature curves location constraint is proposed also to improved efficiency of similarity calculation. Several experiments are carried out on standard on-line signature dataset DB1, which consists of 5000 signatures from 100 individuals in total. The best result is given by EER=2.99%, which indicates the effectiveness of our proposed methods.