An Efficient DTW Matching for On-line Signature Verification

Abstract

Abstract. On-line signature verification is one of widely acceptable biometrics. Dynamic time warping (DTW) is a nonlinear optimization method, which is widely used in on-line signature verification. DTW provides a computational technique of normalization and alignment to make best matching between two signatures, which might have different number of sample points. However, heavy computation is one of defects of DTW when sampled points included in signatures are increased. A simple and efficient method of DTW with signature curves location constraint (DTW with SCC) is proposed to improved efficiency of DTW matching. Several experiments are carried out on standard on-line signature dataset MCYT_Subcorpus_100 (DB1), which consists of 5000 signatures from 100 individuals in total. Experiment results demonstrate that the efficiency of on-line signature verification is improved greatly by our proposed method. The best result is given by EER=2.33%, which also indicates the effectiveness of our proposed methods.